|
1
|
Till T, Scherkl M, Stranger N, Singer G, Hankel S, Flucher C, Hržić F, Štajduhar I, Tschauner S. Impact of test set composition on AI performance in pediatric wrist fracture detection in X-rays. Eur Radiol 2025:10.1007/s00330-025-11669-z. [PMID: 40379941 DOI: 10.1007/s00330-025-11669-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2024] [Revised: 02/24/2025] [Accepted: 04/14/2025] [Indexed: 05/19/2025]
Abstract
OBJECTIVES To evaluate how different test set sampling strategies-random selection and balanced sampling-affect the performance of artificial intelligence (AI) models in pediatric wrist fracture detection using radiographs, aiming to highlight the need for standardization in test set design. MATERIALS AND METHODS This retrospective study utilized the open-sourced GRAZPEDWRI-DX dataset of 6091 pediatric wrist radiographs. Two test sets, each containing 4588 images, were constructed: one using a balanced approach based on case difficulty, projection type, and fracture presence and the other a random selection. EfficientNet and YOLOv11 models were trained and validated on 18,762 radiographs and tested on both sets. Binary classification and object detection tasks were evaluated using metrics such as precision, recall, F1 score, AP50, and AP50-95. Statistical comparisons between test sets were performed using nonparametric tests. RESULTS Performance metrics significantly decreased in the balanced test set with more challenging cases. For example, the precision for YOLOv11 models decreased from 0.95 in the random set to 0.83 in the balanced set. Similar trends were observed for recall, accuracy, and F1 score, indicating that models trained on easy-to-recognize cases performed poorly on more complex ones. These results were consistent across all model variants tested. CONCLUSION AI models for pediatric wrist fracture detection exhibit reduced performance when tested on balanced datasets containing more difficult cases, compared to randomly selected cases. This highlights the importance of constructing representative and standardized test sets that account for clinical complexity to ensure robust AI performance in real-world settings. KEY POINTS Question Do different sampling strategies based on samples' complexity have an influence in deep learning models' performance in fracture detection? Findings AI performance in pediatric wrist fracture detection significantly drops when tested on balanced datasets with more challenging cases, compared to randomly selected cases. Clinical relevance Without standardized and validated test datasets for AI that reflect clinical complexities, performance metrics may be overestimated, limiting the utility of AI in real-world settings.
Collapse
Affiliation(s)
- Tristan Till
- Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| | - Mario Scherkl
- Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| | - Nikolaus Stranger
- Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria.
| | - Georg Singer
- Department of Pediatric and Adolescent Surgery, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| | - Saskia Hankel
- Department of Pediatric and Adolescent Surgery, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| | - Christina Flucher
- Department of Pediatric and Adolescent Surgery, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| | - Franko Hržić
- Faculty of Engineering, Department of Computer Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000, Croatia
| | - Ivan Štajduhar
- Faculty of Engineering, Department of Computer Engineering, University of Rijeka, Vukovarska 58, Rijeka, 51000, Croatia
| | - Sebastian Tschauner
- Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Auenbruggerplatz 34, Graz, 8036, Austria
| |
Collapse
|
|
2
|
Wang HN, An JH, Wang FQ, Hu WQ, Zong L. Predicting gastric cancer survival using machine learning: A systematic review. World J Gastrointest Oncol 2025; 17:103804. [DOI: 10.4251/wjgo.v17.i5.103804] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/03/2024] [Revised: 02/20/2025] [Accepted: 02/26/2025] [Indexed: 05/15/2025] Open
Abstract
BACKGROUND Gastric cancer (GC) has a poor prognosis, and the accurate prediction of patient survival remains a significant challenge in oncology. Machine learning (ML) has emerged as a promising tool for survival prediction, though concerns regarding model interpretability, reliance on retrospective data, and variability in performance persist.
AIM To evaluate ML applications in predicting GC survival and to highlight key limitations in current methods.
METHODS A comprehensive search of PubMed and Web of Science in November 2024 identified 16 relevant studies published after 2019. The most frequently used ML models were deep learning (37.5%), random forests (37.5%), support vector machines (31.25%), and ensemble methods (18.75%). The dataset sizes varied from 134 to 14177 patients, with nine studies incorporating external validation.
RESULTS The reported area under the curve values were 0.669–0.980 for overall survival, 0.920–0.960 for cancer-specific survival, and 0.710–0.856 for disease-free survival. These results highlight the potential of ML-based models to improve clinical practice by enabling personalized treatment planning and risk stratification.
CONCLUSION Despite challenges concerning retrospective studies and a lack of interpretability, ML models show promise; prospective trials and multidimensional data integration are recommended for improving their clinical applicability.
Collapse
Affiliation(s)
- Hong-Niu Wang
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
- Graduate School of Medicine, Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Jia-Hao An
- Department of Graduate School of Medicine, Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Fu-Qiang Wang
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Wen-Qing Hu
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| | - Liang Zong
- Department of Gastrointestinal Surgery, Changzhi People’s Hospital, The Affiliated Hospital of Changzhi Medical College, Changzhi 046000, Shanxi Province, China
| |
Collapse
|
|
3
|
Chen J, Zhang B, Cheng Y, Jia Y, Zhou B. Machine Learning-Based Non-Invasive Prediction of Metabolic Dysfunction-Associated Steatohepatitis in Obese Patients: A Retrospective Study. Diagnostics (Basel) 2025; 15:1096. [PMID: 40361915 PMCID: PMC12072127 DOI: 10.3390/diagnostics15091096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2025] [Revised: 04/19/2025] [Accepted: 04/22/2025] [Indexed: 05/15/2025] Open
Abstract
Objectives: We aimed to develop and validate machine learning (ML) models that integrate clinical and laboratory data for the non-invasive prediction of metabolic dysfunction-associated steatohepatitis (MASH) in an obese population. Methods: In this retrospective study, clinical and laboratory data were collected from obese patients undergoing bariatric surgery. The cohort was divided using stratified random sampling, and optimal features were selected with SHapley Additive exPlanations (SHAP). Various ML models, including K-nearest neighbors, linear support vector machine, radial basis function support vector machine, Gaussian process, random forest, multilayer perceptron, adaptive boosting, and naïve Bayes, were developed through cross-validation and hyperparameter tuning. Diagnostic performance was assessed via the area under the curve (AUC) in both training and validation sets. Results: A total of 558 patients were analyzed, with 390 in the training set and 168 in the validation set. In the training cohort, the median age was 35 years, the median body mass index (BMI) was 39.8 kg/m2, 39.0% were male, 37.9% had diabetes mellitus, and 62.8% were diagnosed with MASH. The validation cohort had a median age of 34.1 years, a median BMI of 42.5 kg/m2, 41.7% male, 32.7% with diabetes, and 39.9% with MASH. Among the models, the random forest achieved the highest performance among the models with AUC values of 0.94 in the training set and 0.88 in the validation set. The Gaussian process model attained an AUC of 0.97 in the training cohort but 0.79 in the validation cohort, while the other models achieved AUC values ranging from 0.63 to 0.88 in the training cohort and 0.62 to 0.75 in the validation set. Conclusions: ML models, particularly the random forest, effectively predict MASH using readily available data, offering a promising non-invasive alternative to conventional serological scoring. Prospective studies and external validations are needed to further establish clinical utility.
Collapse
Affiliation(s)
- Jie Chen
- Department of Ultrasound, China-Japan Friendship Hospital, Beijing 100029, China
| | - Bo Zhang
- Department of Ultrasound, China-Japan Friendship Hospital, Beijing 100029, China
| | - Yong Cheng
- School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
| | - Yuanchen Jia
- School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
| | - Biao Zhou
- Department of General Surgery & Obesity and Metabolic Disease Center, China-Japan Friendship Hospital, Beijing 100029, China
| |
Collapse
|
|
4
|
Farha F, Abass S, Khan S, Ali J, Parveen B, Ahmad S, Parveen R. Transforming pulmonary health care: the role of artificial intelligence in diagnosis and treatment. Expert Rev Respir Med 2025:1-21. [PMID: 40210489 DOI: 10.1080/17476348.2025.2491723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2024] [Revised: 03/12/2025] [Accepted: 04/07/2025] [Indexed: 04/12/2025]
Abstract
INTRODUCTION Respiratory diseases like pneumonia, asthma, and COPD are major global health concerns, significantly impacting morbidity and mortality rates worldwide. AREAS COVERED A selective search on PubMed, Google Scholar, and ScienceDirect (up to 2024) focused on AI in diagnosing and treating respiratory conditions like asthma, pneumonia, and COPD. Studies were chosen for their relevance to prediction models, AI-driven diagnostics, and personalized treatments. This narrative review highlights technological advancements, clinical applications, and challenges in integrating AI into standard practice, with emphasis on predictive tools, deep learning for imaging, and patient outcomes. EXPERT OPINION Despite these advancements, significant challenges remain in fully integrating AI into pulmonary health care. The need for large, diverse datasets to train AI models is critical, and concerns around data privacy, algorithmic transparency, and potential biases must be carefully managed. Regulatory frameworks also need to evolve to address the unique challenges posed by AI in health care. However, with continued research and collaboration between technology developers, clinicians, and policymakers, AI has the potential to revolutionize pulmonary health care, ultimately leading to more effective, efficient, and personalized care for patients.
Collapse
Affiliation(s)
- Farzat Farha
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Sageer Abass
- Centre of Excellence in Unani Medicine (Pharmacognosy & Pharmacology), Bioactive Natural Product Laboratory, Department of Pharmacognosy and Phytochemistry, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Saba Khan
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Javed Ali
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Bushra Parveen
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
- Centre of Excellence in Unani Medicine (Pharmacognosy & Pharmacology), Bioactive Natural Product Laboratory, Department of Pharmacognosy and Phytochemistry, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Sayeed Ahmad
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
- Centre of Excellence in Unani Medicine (Pharmacognosy & Pharmacology), Bioactive Natural Product Laboratory, Department of Pharmacognosy and Phytochemistry, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| | - Rabea Parveen
- Department of Pharmaceutics, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
- Centre of Excellence in Unani Medicine (Pharmacognosy & Pharmacology), Bioactive Natural Product Laboratory, Department of Pharmacognosy and Phytochemistry, School of Pharmaceutical Education and Research, Jamia Hamdard, New Delhi, India
| |
Collapse
|
|
5
|
Ni P, Xu S, Zhang W, Wu C, Zhang G, Gu Q, Hu X, Zhu Y, Hu W, Diao M. Development and Validation of a Nomogram Prediction Model for In-hospital Mortality in Patients with Cardiac Arrest: A Retrospective Study. Rev Cardiovasc Med 2025; 26:33387. [PMID: 40351670 PMCID: PMC12059783 DOI: 10.31083/rcm33387] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2024] [Revised: 12/22/2024] [Accepted: 12/27/2024] [Indexed: 05/14/2025] Open
Abstract
Background Cardiac arrest (CA) is associated with high incidence and mortality rates. Hence, assessing the prognosis of CA patients is crucial for optimizing clinical treatment. This study aimed to develop and validate a clinically applicable nomogram for predicting the risk of in-hospital mortality in CA patients. Methods We retrospectively collected the clinical data of CA patients admitted to two hospitals in Zhejiang Province between January 2018 and June 2024. These patients were randomly assigned to the training set (70%) and the internal validation set (30%). Variables of interest included demographics, comorbidities, CA-related characteristics, vital signs, and laboratory results, and the outcome was defined as in-hospital death. Variables were selected using least absolute shrinkage and selection operator (LASSO) regression, recursive feature elimination (RFE), and eXtremely Gradient Boosting (XGBoost). Meanwhile, multivariate regression analysis was used to identify independent risk factors. Subsequently, prediction models were developed in the training set and validated in the internal validation set. Receiver operating characteristic (ROC) curves were plotted and the area under these curves (AUC) was calculated to compare the discriminative ability of the models. The model with the highest performance was further validated in an independent external cohort and was subsequently represented as a nomogram for predicting the risk of in-hospital mortality in CA patients. Results This study included 996 CA patients, with an in-hospital mortality rate of 49.9% (497/996). The LASSO regression model significantly outperformed the RFE and XGBoost models in predicting in-hospital mortality, with an AUC value of 0.81 (0.78, 0.84) in the training set and 0.85 (0.80, 0.89) in the internal validation set. The AUC values for these sets in the RFE model were 0.74 (0.70, 0.78) and 0.77 (0.72, 0.83), respectively, and those for the XGBoost model were 0.75 (0.71, 0.79) and 0.77 (0.72, 0.83), respectively. For the optimal prediction model, the AUC value of the LASSO regression model in the external validation set was 0.84 (0.78, 0.90). The LASSO regression model was represented as a nomogram incorporating several independent risk factors, namely age, hypertension, cause of arrest, initial heart rhythm, vasoactive drugs, continuous renal replacement therapy (CRRT), temperature, blood urea-nitrogen (BUN), lactate, and Sequential Organ Failure Assessment (SOFA) scores. Calibration and decision curves confirmed the predictive accuracy and clinical utility of the model. Conclusions We developed a nomogram to predict the risk of in-hospital mortality in CA patients, using variables selected via LASSO regression. This nomogram demonstrated strong discriminative ability and clinical practicality.
Collapse
Affiliation(s)
- Peifeng Ni
- Department of Critical Care Medicine, Zhejiang University School of Medicine, 310058 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Shurui Xu
- Department of Critical Care Medicine, Zhejiang University School of Medicine, 310058 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Weidong Zhang
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, The Fourth Clinical School of Zhejiang Chinese Medicine University, 310053 Hangzhou, Zhejiang, China
| | - Chenxi Wu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, The Fourth Clinical School of Zhejiang Chinese Medicine University, 310053 Hangzhou, Zhejiang, China
| | - Gensheng Zhang
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, 310009 Hangzhou, Zhejiang, China
| | - Qiao Gu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Xin Hu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Ying Zhu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Wei Hu
- Department of Critical Care Medicine, Zhejiang University School of Medicine, 310058 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| | - Mengyuan Diao
- Department of Critical Care Medicine, Zhejiang University School of Medicine, 310058 Hangzhou, Zhejiang, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, 310006 Hangzhou, Zhejiang, China
| |
Collapse
|
|
6
|
Ni P, Zhang S, Zhang G, Zhang W, Zhang H, Zhu Y, Hu W, Diao M. Development and validation of machine learning-based prediction model for outcome of cardiac arrest in intensive care units. Sci Rep 2025; 15:8691. [PMID: 40082569 PMCID: PMC11907063 DOI: 10.1038/s41598-025-93182-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2024] [Accepted: 03/05/2025] [Indexed: 03/16/2025] Open
Abstract
Cardiac arrest (CA) poses a significant global health challenge and often results in poor prognosis. We developed an interpretable and applicable machine learning (ML) model for predicting in-hospital mortality of CA patients who survived more than 72 h. A total of 721 patients were extracted from the Medical Information Mart for Intensive Care IV database, divided into the training set (n = 576) and the internal validation set (n = 145). The external validation set containing 856 cases were collected from four tertiary hospitals in Zhejiang Province. The primary outcome was in-hospital mortality. Eleven ML algorithms were utilized to establish prediction models based on data from 72 h after return of spontaneous circulation (ROSC). The results indicate that the CatBoost model exhibited the best performance at 72 h. Eleven variables were ultimately selected as key features by recursive feature elimination (RFE) to construct a compact model. The final model achieved the highest AUC of 0.86 (0.80, 0.92) in the internal validation and 0.76 (0.73, 0.79) in the external validation. SHAP summary plots and force plots visually explained the predicted outcomes. In conclusion, 72-h CatBoost showed promising performance in predicting in-hospital mortality of CA patients who survived more than 72 h. The model still requires further optimization and improvement.
Collapse
Affiliation(s)
- Peifeng Ni
- Department of Critical Care Medicine, Zhejiang University School of Medicine, No. 866 Yuhangtang Road, Hangzhou, 310000, Zhejiang, China
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China
| | - Sheng Zhang
- Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, No. 197 Ruijin 2nd Road, Shanghai, 200000, China
| | - Gensheng Zhang
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, No. 88 Jiefang Road, Hangzhou, 310000, China
| | - Weidong Zhang
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China
- Department of Critical Care Medicine, The Fourth Clinical School of Zhejiang Chinese Medicine University, No. 548 Binwen Road, Hangzhou, 310000, Zhejiang, China
| | - Hongwei Zhang
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China
| | - Ying Zhu
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China
| | - Wei Hu
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China.
| | - Mengyuan Diao
- Department of Critical Care Medicine, Zhejiang University School of Medicine, No. 866 Yuhangtang Road, Hangzhou, 310000, Zhejiang, China.
- Department of Critical Care Medicine, Hangzhou First People's Hospital, Westlake University School of Medicine, No. 261 Huansha Road, Hangzhou, 310000, Zhejiang, China.
| |
Collapse
|
|
7
|
He R, Sarwal V, Qiu X, Zhuang Y, Zhang L, Liu Y, Chiang J. Generative AI Models in Time-Varying Biomedical Data: Scoping Review. J Med Internet Res 2025; 27:e59792. [PMID: 40063929 PMCID: PMC11933772 DOI: 10.2196/59792] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 08/08/2024] [Accepted: 11/15/2024] [Indexed: 03/28/2025] Open
Abstract
BACKGROUND Trajectory modeling is a long-standing challenge in the application of computational methods to health care. In the age of big data, traditional statistical and machine learning methods do not achieve satisfactory results as they often fail to capture the complex underlying distributions of multimodal health data and long-term dependencies throughout medical histories. Recent advances in generative artificial intelligence (AI) have provided powerful tools to represent complex distributions and patterns with minimal underlying assumptions, with major impact in fields such as finance and environmental sciences, prompting researchers to apply these methods for disease modeling in health care. OBJECTIVE While AI methods have proven powerful, their application in clinical practice remains limited due to their highly complex nature. The proliferation of AI algorithms also poses a significant challenge for nondevelopers to track and incorporate these advances into clinical research and application. In this paper, we introduce basic concepts in generative AI and discuss current algorithms and how they can be applied to health care for practitioners with little background in computer science. METHODS We surveyed peer-reviewed papers on generative AI models with specific applications to time-series health data. Our search included single- and multimodal generative AI models that operated over structured and unstructured data, physiological waveforms, medical imaging, and multi-omics data. We introduce current generative AI methods, review their applications, and discuss their limitations and future directions in each data modality. RESULTS We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and reviewed 155 articles on generative AI applications to time-series health care data across modalities. Furthermore, we offer a systematic framework for clinicians to easily identify suitable AI methods for their data and task at hand. CONCLUSIONS We reviewed and critiqued existing applications of generative AI to time-series health data with the aim of bridging the gap between computational methods and clinical application. We also identified the shortcomings of existing approaches and highlighted recent advances in generative AI that represent promising directions for health care modeling.
Collapse
Affiliation(s)
- Rosemary He
- Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| | - Varuni Sarwal
- Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| | - Xinru Qiu
- Division of Biomedical Sciences, School of Medicine, University of California Riverside, Riverside, CA, United States
| | - Yongwen Zhuang
- Department of Biostatistics, University of Michigan, Ann Arbor, MI, United States
| | - Le Zhang
- Institute for Integrative Genome Biology, University of California Riverside, Riverside, CA, United States
| | - Yue Liu
- Institute for Cellular and Molecular Biology, University of Texas at Austin, Austin, TX, United States
| | - Jeffrey Chiang
- Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| |
Collapse
|
|
8
|
Halwani MA, Merdad G, Almasre M, Doman G, AlSharif S, Alshiakh SM, Mahboob DY, Halwani MA, Faqerah NA, Mosuily MT. Predicting triage of pediatric patients in the emergency department using machine learning approach. Int J Emerg Med 2025; 18:51. [PMID: 40065253 PMCID: PMC11892228 DOI: 10.1186/s12245-025-00861-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2024] [Accepted: 02/25/2025] [Indexed: 03/14/2025] Open
Abstract
BACKGROUND The efficient performance of an Emergency Department (ED) relies heavily on an effective triage system that prioritizes patients based on the severity of their medical conditions. Traditional triage systems, including those using the Canadian Triage and Acuity Scale (CTAS), may involve subjective assessments by healthcare providers, leading to potential inconsistencies and delays in patient care. OBJECTIVE This study aimed to evaluate six Machine Learning (ML) models K-Nearest Neighbors (KNN), Support Vector Machine (SCM), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Light GBM (Light Gradient Boosting Machine) for triage prediction in the King Abdulaziz University Hospital using the CTAS framework. METHODOLOGY We followed three essential phases: data collection (7125 records of ED patients), data exploration and processing, and the development of machine learning predictive models for ED triage at King Abdulaziz University Hospital. RESULTS AND CONCLUSION The overall predictive performance of CTAS was the highest using GNB = 0.984 accuracy. The CTAS-level model performance indicated that SVM, RF, and LGBM achieved the highest performance regarding the consistency of precision and recall values across all CTAS levels.
Collapse
Affiliation(s)
- Manal Ahmed Halwani
- Pediatric Emergency Unit, Department of Emergency, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia.
| | - Ghada Merdad
- Emergency Department, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Miada Almasre
- Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Ghadeer Doman
- Emergency Department, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Shafiqa AlSharif
- Pediatric Emergency Unit, Department of Emergency, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Safinaz M Alshiakh
- Emergency Department, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Duaa Yousof Mahboob
- Emergency Department, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Marwah A Halwani
- Management Information Systems Department, College of Business, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Nojoud Adnan Faqerah
- Department of Medical Microbiology, Faculty of Medicine in Rabigh, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Mahmoud Talal Mosuily
- Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| |
Collapse
|
|
9
|
Lin N, Abbas-Aghababazadeh F, Su J, Wu AJ, Lin C, Shi W, Xu W, Haibe-Kains B, Liu FF, Kwan JYY. Development of Machine Learning Models for Predicting Radiation Dermatitis in Breast Cancer Patients Using Clinical Risk Factors, Patient-Reported Outcomes, and Serum Cytokine Biomarkers. Clin Breast Cancer 2025:S1526-8209(25)00048-5. [PMID: 40155248 DOI: 10.1016/j.clbc.2025.03.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2024] [Revised: 02/27/2025] [Accepted: 03/01/2025] [Indexed: 04/01/2025]
Abstract
BACKGROUND Radiation dermatitis (RD) is a significant side effect of radiotherapy experienced by breast cancer patients. Severe symptoms include desquamation or ulceration of irradiated skin, which impacts quality of life and increases healthcare costs. Early identification of patients at risk for severe RD can facilitate preventive management and reduce severe symptoms. This study evaluated the utility of subjective and objective factors, such as patient-reported outcomes (PROs) and serum cytokines, for predicting RD in breast cancer patients. The performance of machine learning (ML) and logistic regression-based models were compared. PATIENTS AND METHODS Data from 147 breast cancer patients who underwent radiotherapy was analyzed to develop prognostic models. ML algorithms, including neural networks, random forest, XGBoost, and logistic regression, were employed to predict clinically significant Grade 2+ RD. Clinical factors, PROs, and cytokine biomarkers were incorporated into the risk models. Model performance was evaluated using nested cross-validation with separate loops for hyperparameter tuning and calculating performance metrics. RESULTS Feature selection identified 18 predictors of Grade 2+ RD including smoking, radiotherapy boost, reduced motivation, and the cytokines interleukin-4, interleukin-17, interleukin-1RA, interferon-gamma, and stromal cell-derived factor-1a. Incorporating these predictors, the XGBoost model achieved the highest performance with an area under the curve (AUC) of 0.780 (95% CI: 0.701-0.854). This was not significantly improved over the logistic regression model, which demonstrated an AUC of 0.714 (95% CI: 0.629-0.798). CONCLUSION Clinical risk factors, PROs, and serum cytokine levels provide complementary prognostic information for predicting severe RD in breast cancer patients undergoing radiotherapy. ML and logistic regression models demonstrated comparable performance for predicting clinically significant RD with AUC>0.70.
Collapse
Affiliation(s)
- Neil Lin
- Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
| | - Farnoosh Abbas-Aghababazadeh
- Princess Margaret Bioinformatics and Computational Genomics Laboratory, University Health Network, Toronto, Canada
| | - Jie Su
- Biostatistics Division, Princess Margaret Cancer Centre, Toronto, Canada
| | - Alison J Wu
- Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
| | - Cherie Lin
- Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
| | - Wei Shi
- Research Institute, Princess Margaret Cancer Centre, Toronto, Canada
| | - Wei Xu
- Biostatistics Division, Princess Margaret Cancer Centre, Toronto, Canada
| | - Benjamin Haibe-Kains
- Princess Margaret Bioinformatics and Computational Genomics Laboratory, University Health Network, Toronto, Canada; Research Institute, Princess Margaret Cancer Centre, Toronto, Canada; Department of Computer Science, University of Toronto, Toronto, Canada; Ontario Institute for Cancer Research, Toronto, Canada; Vector Institute for Artificial Intelligence, Toronto, Canada; Department of Medical Biophysics, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
| | - Fei-Fei Liu
- Research Institute, Princess Margaret Cancer Centre, Toronto, Canada; Department of Radiation Oncology, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Department of Medical Biophysics, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada
| | - Jennifer Y Y Kwan
- Institute of Medical Science, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Research Institute, Princess Margaret Cancer Centre, Toronto, Canada; Department of Radiation Oncology, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Radiation Medicine Program, Princess Margaret Cancer Centre, Toronto, Canada.
| |
Collapse
|
|
10
|
Arif U, Zhang C, Chaudhary MW, Hussain S. An Adaptive Dendritic Neural Model for Lung Cancer Prediction. Comput Methods Biomech Biomed Engin 2025:1-14. [PMID: 40026264 DOI: 10.1080/10255842.2025.2472013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2024] [Revised: 01/13/2025] [Accepted: 02/19/2025] [Indexed: 03/05/2025]
Abstract
Lung cancer is a leading cause of cancer-related deaths, often diagnosed late due to its aggressive nature. This study presents a novel Adaptive Dendritic Neural Model (ADNM) to enhance diagnostic accuracy in high-dimensional healthcare data. Utilizing hyperparameter optimization and activation mechanisms, ADNM improves scalability and feature selection for multi-class lung cancer prediction. Using a Kaggle dataset, Particle Swarm Optimization (PSO) selected features, while bootstrap assessed performance. ADNM achieved 98.39% accuracy, 99% AUC, and a Cohen's kappa of 96.95%, with rapid convergence via the Adam optimizer, demonstrating its potential for improving early diagnosis and personalized treatment in oncology.
Collapse
Affiliation(s)
- Umair Arif
- Department of Statistics, School of Mathematics and Statistics, Xi'an Jiaotong University, Xian Shaanxi, China
| | - Chunxia Zhang
- Department of Statistics, School of Mathematics and Statistics, Xi'an Jiaotong University, Xian Shaanxi, China
| | - Muhammad Waqas Chaudhary
- Department of Statistics, School of Mathematics and Statistics, Xi'an Jiaotong University, Xian Shaanxi, China
- Department of Statistics, University of WAH, Rawalpindi, Pakistan
| | - Sajid Hussain
- Department of Statistics, School of Mathematics and Statistics, Xi'an Jiaotong University, Xian Shaanxi, China
| |
Collapse
|
|
11
|
Liao J, Xu Z, Xie Y, Liang Y, Hu Q, Liu C, Yan L, Diao W, Liu Z, Wu L, Liang C. Assessing Axillary Lymph Node Burden and Prognosis in cT1-T2 Stage Breast Cancer Using Machine Learning Methods: A Retrospective Dual-Institutional MRI Study. J Magn Reson Imaging 2025; 61:1221-1231. [PMID: 39175033 DOI: 10.1002/jmri.29554] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2024] [Revised: 07/11/2024] [Accepted: 07/12/2024] [Indexed: 08/24/2024] Open
Abstract
BACKGROUND Pathological axillary lymph node (pALN) burden is an important factor for treatment decision-making in clinical T1-T2 (cT1-T2) stage breast cancer. Preoperative assessment of the pALN burden and prognosis aids in the individualized selection of therapeutic approaches. PURPOSE To develop and validate a machine learning (ML) model based on clinicopathological and MRI characteristics for assessing pALN burden and survival in patients with cT1-T2 stage breast cancer. STUDY TYPE Retrospective. POPULATION A total of 506 females (range: 24-83 years) with cT1-T2 stage breast cancer from two institutions, forming the training (N = 340), internal validation (N = 85), and external validation cohorts (N = 81), respectively. FIELD STRENGTH/SEQUENCE This study used 1.5-T, axial fat-suppressed T2-weighted turbo spin-echo sequence and axial three-dimensional dynamic contrast-enhanced fat-suppressed T1-weighted gradient echo sequence. ASSESSMENT Four ML methods (eXtreme Gradient Boosting [XGBoost], Support Vector Machine, k-Nearest Neighbor, Classification and Regression Tree) were employed to develop models based on clinicopathological and MRI characteristics. The performance of these models was evaluated by their discriminative ability. The best-performing model was further analyzed to establish interpretability and used to calculate the pALN score. The relationships between the pALN score and disease-free survival (DFS) were examined. STATISTICAL TESTS Chi-squared test, Fisher's exact test, univariable logistic regression, area under the curve (AUC), Delong test, net reclassification improvement, integrated discrimination improvement, Hosmer-Lemeshow test, log-rank, Cox regression analyses, and intraclass correlation coefficient were performed. A P-value <0.05 was considered statistically significant. RESULTS The XGB II model, developed based on the XGBoost algorithm, outperformed the other models with AUCs of 0.805, 0.803, and 0.818 in the three cohorts. The Shapley additive explanation plot indicated that the top variable in the XGB II model was the Node Reporting and Data System score. In multivariable Cox regression analysis, the pALN score was significantly associated with DFS (hazard ratio: 4.013, 95% confidence interval: 1.059-15.207). DATA CONCLUSION The XGB II model may allow to evaluate pALN burden and could provide prognostic information in cT1-T2 stage breast cancer patients. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Jiayi Liao
- Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Zeyan Xu
- Department of Radiology, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, Kunming, China
| | - Yu Xie
- Department of Radiology, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Peking University Cancer Hospital Yunnan, Kunming, China
| | - Yanting Liang
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Qingru Hu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Chunling Liu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Lifen Yan
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Wenjun Diao
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Zaiyi Liu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Lei Wu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Changhong Liang
- Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| |
Collapse
|
|
12
|
Liew CH, Ong SQ, Ng DCE. Utilizing machine learning to predict hospital admissions for pediatric COVID-19 patients (PrepCOVID-Machine). Sci Rep 2025; 15:3131. [PMID: 39856094 PMCID: PMC11760342 DOI: 10.1038/s41598-024-80538-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2023] [Accepted: 11/18/2024] [Indexed: 01/27/2025] Open
Abstract
The COVID-19 pandemic has burdened healthcare systems globally. To curb high hospital admission rates, only patients with genuine medical needs are admitted. However, machine learning (ML) models to predict COVID-19 hospitalization in Asian children are lacking. This study aimed to develop and validate ML models to predict pediatric COVID-19 hospitalization. We collected secondary data with 2200 patients and 65 variables from Malaysian aged 0 to 12 with COVID-19 between 1st February 2020 and 31st March 2022. The sample was partitioned into training, internal, and external validation groups. Recursive Feature Elimination (RFE) was employed for feature selection, and we trained seven supervised classifiers. Grid Search was used to optimize the hyperparameters of each algorithm. The study analyzed 1988 children and 30 study variables after data were processed. The RFE algorithm selected 12 highly predicted variables for COVID-19 hospitalization, including age, male sex, fever, cough, rhinorrhea, shortness of breath, vomiting, diarrhea, seizures, body temperature, chest indrawing, and abnormal breath sounds. With external validation, Adaptive Boosting was the highest-performing classifier (AUROC = 0.95) to predict COVID-19 hospital admission in children. We validated AdaBoost as the best to predict COVID-19 hospitalization among children. This model may assist front-line clinicians in making medical disposition decisions.
Collapse
Affiliation(s)
- Chuin-Hen Liew
- Hospital Tuanku Ampuan Najihah, Jalan Melang, 72000, Kuala Pilah, Negeri Sembilan, Malaysia
| | - Song-Quan Ong
- Institute for Tropical Biology and Conservation, University Malaysia Sabah, Jalan UMS, 88400, Kota Kinabalu, Sabah, Malaysia.
| | - David Chun-Ern Ng
- Hospital Tuanku Ja'afar, Jalan Rasah, 70300, Seremban, Negeri Sembilan, Malaysia
| |
Collapse
|
|
13
|
Wu H, Liao B, Ji T, Ma K, Luo Y, Zhang S. Comparison between traditional logistic regression and machine learning for predicting mortality in adult sepsis patients. Front Med (Lausanne) 2025; 11:1496869. [PMID: 39835102 PMCID: PMC11743956 DOI: 10.3389/fmed.2024.1496869] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2024] [Accepted: 12/10/2024] [Indexed: 01/22/2025] Open
Abstract
Background Sepsis is a life-threatening disease associated with a high mortality rate, emphasizing the need for the exploration of novel models to predict the prognosis of this patient population. This study compared the performance of traditional logistic regression and machine learning models in predicting adult sepsis mortality. Objective To develop an optimum model for predicting the mortality of adult sepsis patients based on comparing traditional logistic regression and machine learning methodology. Methods Retrospective analysis was conducted on 606 adult sepsis inpatients at our medical center between January 2020 and December 2022, who were randomly divided into training and validation sets in a 7:3 ratio. Traditional logistic regression and machine learning methods were employed to assess the predictive ability of mortality in adult sepsis. Univariate analysis identified independent risk factors for the logistic regression model, while Least Absolute Shrinkage and Selection Operator (LASSO) regression facilitated variable shrinkage and selection for the machine learning model. Among various machine learning models, which included Bagged Tree, Boost Tree, Decision Tree, LightGBM, Naïve Bayes, Nearest Neighbors, Support Vector Machine (SVM), and Random Forest (RF), the one with the maximum area under the curve (AUC) was chosen for model construction. Model validation and comparison with the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation (APACHE) scores were performed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves in the validation set. Results Univariate analysis was employed to assess 17 variables, namely gender, history of coronary heart disease (CHD), systolic pressure, white blood cell (WBC), neutrophil count (NEUT), lymphocyte count (LYMP), lactic acid, neutrophil-to-lymphocyte ratio (NLR), red blood cell distribution width (RDW), interleukin-6 (IL-6), prothrombin time (PT), international normalized ratio (INR), fibrinogen (FBI), D-dimer, aspartate aminotransferase (AST), total bilirubin (Tbil), and lung infection. Significant differences (p < 0.05) between the survival and non-survival groups were observed for these variables. Utilizing stepwise regression with the "backward" method, independent risk factors, including systolic pressure, lactic acid, NLR, RDW, IL-6, PT, and Tbil, were identified. These factors were then incorporated into a logistic regression model, chosen based on the minimum Akaike Information Criterion (AIC) value (98.65). Machine learning techniques were also applied, and the RF model, demonstrating the maximum Area Under the Curve (AUC) of 0.999, was selected. LASSO regression, employing the lambda.1SE criteria, identified systolic pressure, lactic acid, NEUT, RDW, IL6, INR, and Tbil as variables for constructing the RF model, validated through ten-fold cross-validation. For model validation and comparison with traditional logistic models, SOFA, and APACHE scoring. Conclusion Based on deep machine learning principles, the RF model demonstrates advantages over traditional logistic regression models in predicting adult sepsis prognosis. The RF model holds significant potential for clinical surveillance and interventions to enhance outcomes for sepsis patients.
Collapse
Affiliation(s)
- Hongsheng Wu
- Hepatobiliary Pancreatic Surgery Department, Huadu District People’s Hospital of Guangzhou, Guangzhou, China
| | | | | | | | | | - Shengmin Zhang
- Hepatobiliary Pancreatic Surgery Department, Huadu District People’s Hospital of Guangzhou, Guangzhou, China
| |
Collapse
|
|
14
|
Fan Z, Song W, Ke Y, Jia L, Li S, Li JJ, Zhang Y, Lin J, Wang B. XGBoost-SHAP-based interpretable diagnostic framework for knee osteoarthritis: a population-based retrospective cohort study. Arthritis Res Ther 2024; 26:213. [PMID: 39696605 DOI: 10.1186/s13075-024-03450-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2024] [Accepted: 12/01/2024] [Indexed: 12/20/2024] Open
Abstract
OBJECTIVE To use routine demographic and clinical data to develop an interpretable individual-level machine learning (ML) model to diagnose knee osteoarthritis (KOA) and to identify highly ranked features. METHODS In this retrospective, population-based cohort study, anonymized questionnaire data was retrieved from the Wu Chuan KOA Study, Inner Mongolia, China. After feature selections, participants were divided in a 7:3 ratio into training and test sets. Class balancing was applied to the training set for data augmentation. Four ML classifiers were compared by cross-validation within the training set and their performance was further analyzed with an unseen test set. Classifications were evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the curve(AUC), G-means, and F1 scores. The best model was explained using Shapley values to extract highly ranked features. RESULTS A total of 1188 participants were investigated in this study, among whom 26.3% were diagnosed with KOA. Comparatively, XGBoost with Boruta exhibited the highest classification performance among the four models, with an AUC of 0.758, G-means of 0.800, and F1 scores of 0.703. The SHAP method reveals the top 17 features of KOA according to the importance ranking, and the average of the experience of joint pain was recognized as the most important features. CONCLUSIONS Our study highlights the usefulness of machine learning in unveiling important factors that influence the diagnosis of KOA to guide new prevention strategies. Further work is needed to validate this approach.
Collapse
Affiliation(s)
- Zijuan Fan
- Department of Orthopaedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Qingchun Road No. 79, Hangzhou, China
- Department of Health Statistics, School of Public Health, Sun Yat-sen University, Guangzhou, China
| | - Wenzhu Song
- Department of Big Data in Health Science School of Public Health, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
| | - Yan Ke
- Arthritis Clinic & Research Center, Peking University People's Hospital, Beijing, China
| | - Ligan Jia
- School of Computer Science and Technology, Xinjiang University, Urumchi, China
| | - Songyan Li
- Department of Orthopaedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Qingchun Road No. 79, Hangzhou, China
| | - Jiao Jiao Li
- School of Biomedical Engineering, Faculty of Engineering and IT, University of Technology Sydney, Sydney, Australia
| | - Yuqing Zhang
- Harvard Medical School, Boston Massachusetts, USA
| | - Jianhao Lin
- Arthritis Clinic & Research Center, Peking University People's Hospital, Beijing, China.
| | - Bin Wang
- Department of Orthopaedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Qingchun Road No. 79, Hangzhou, China.
| |
Collapse
|
|
15
|
Silvey S, Liu J. Sample Size Requirements for Popular Classification Algorithms in Tabular Clinical Data: Empirical Study. J Med Internet Res 2024; 26:e60231. [PMID: 39689306 DOI: 10.2196/60231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2024] [Revised: 09/20/2024] [Accepted: 10/20/2024] [Indexed: 12/19/2024] Open
Abstract
BACKGROUND The performance of a classification algorithm eventually reaches a point of diminishing returns, where the additional sample added does not improve the results. Thus, there is a need to determine an optimal sample size that maximizes performance while accounting for computational burden or budgetary concerns. OBJECTIVE This study aimed to determine optimal sample sizes and the relationships between sample size and dataset-level characteristics over a variety of binary classification algorithms. METHODS A total of 16 large open-source datasets were collected, each containing a binary clinical outcome. Furthermore, 4 machine learning algorithms were assessed: XGBoost (XGB), random forest (RF), logistic regression (LR), and neural networks (NNs). For each dataset, the cross-validated area under the curve (AUC) was calculated at increasing sample sizes, and learning curves were fit. Sample sizes needed to reach the observed full-dataset AUC minus 2 points (0.02) were calculated from the fitted learning curves and compared across the datasets and algorithms. Dataset-level characteristics, minority class proportion, full-dataset AUC, number of features, type of features, and degree of nonlinearity were examined. Negative binomial regression models were used to quantify relationships between these characteristics and expected sample sizes within each algorithm. A total of 4 multivariable models were constructed, which selected the best-fitting combination of dataset-level characteristics. RESULTS Among the 16 datasets (full-dataset sample sizes ranging from 70,000-1,000,000), median sample sizes were 9960 (XGB), 3404 (RF), 696 (LR), and 12,298 (NN) to reach AUC stability. For all 4 algorithms, more balanced classes (multiplier: 0.93-0.96 for a 1% increase in minority class proportion) were associated with decreased sample size. Other characteristics varied in importance across algorithms-in general, more features, weaker features, and more complex relationships between the predictors and the response increased expected sample sizes. In multivariable analysis, the top selected predictors were minority class proportion among all 4 algorithms assessed, full-dataset AUC (XGB, RF, and NN), and dataset nonlinearity (XGB, RF, and NN). For LR, the top predictors were minority class proportion, percentage of strong linear features, and number of features. Final multivariable sample size models had high goodness-of-fit, with dataset-level predictors explaining a majority (66.5%-84.5%) of the total deviance in the data among all 4 models. CONCLUSIONS The sample sizes needed to reach AUC stability among 4 popular classification algorithms vary by dataset and method and are associated with dataset-level characteristics that can be influenced or estimated before the start of a research study.
Collapse
Affiliation(s)
- Scott Silvey
- Department of Biostatistics, School of Public Health, Virginia Commonwealth University, Richmond, VA, United States
| | - Jinze Liu
- Department of Biostatistics, School of Public Health, Virginia Commonwealth University, Richmond, VA, United States
| |
Collapse
|
|
16
|
Zhang B, Xu H, Xiao Q, Wei W, Ma Y, Chen X, Gu J, Zhang J, Lang L, Ma Q, Han L. Machine learning predictive model for aspiration risk in early enteral nutrition patients with severe acute pancreatitis. Heliyon 2024; 10:e40236. [PMID: 39654732 PMCID: PMC11626782 DOI: 10.1016/j.heliyon.2024.e40236] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2024] [Revised: 10/21/2024] [Accepted: 11/06/2024] [Indexed: 12/12/2024] Open
Abstract
Background The aim of this study was to build and validate a risk prediction model for aspiration in severe acute pancreatitis patients receiving early enteral nutrition (EN) by identifying risk factors for aspiration in these patients. Methods The risk factors for aspiration were analyzed to build a prediction model based on the data collected from 339 patients receiving enteral nutrition. Subsequently, we used six machine learning algorithms and the model was validated by the area under the curve. Results In this study, the collected data were divided into two groups: a training cohort and a validation cohort. The results showed that 28.31 % (77) of patients had aspiration and 71.69 % (195) of patients had non-aspiration in training cohort. Moreover, age, consciousness, mechanical ventilation, aspiration history, nutritional risk and number of comorbidities were included as predictive factors for aspiration in patients receiving EN. The XGBoost model is the best of all machine learning models, with an AUROC of 0.992 and an F1 value of 0.902. The specificity and accuracy of XGBoost are higher than those of traditional logistic regression. Conclusion In accordance with the predictive factors, XGBoost model, characterized by excellent discrimination and high accuracy, can be used to clinically identify severe acute pancreatitis patients with a high risk of enteral nutrition aspiration. Relevance to clinical practice This study contributed to the development of a predictive model for early enteral nutrition aspiration in severe acute pancreatitis patients during hospitalization that can be shared with medical staff and patients in the future. No patient or public contribution This is a retrospective cohort study, and no patient or public contribution was required to design or undertake this research.
Collapse
Affiliation(s)
- Bo Zhang
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Huanqing Xu
- School of Medical Information Engineering, Anhui University of Traditional Chinese Medicine, Hefei, Anhui Province, China
| | - Qigui Xiao
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Wanzhen Wei
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Yifei Ma
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Xinlong Chen
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Jingtao Gu
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Jiaoqiong Zhang
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Lan Lang
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Qingyong Ma
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| | - Liang Han
- Department of Hepatobiliary Surgery, The First Affiliated Hospital, Xi'an Jiaotong University, NO.277 Yanta West Road, Xi'an, China
| |
Collapse
|
|
17
|
Watson M, Boulitsakis Logothetis S, Green D, Holland M, Chambers P, Al Moubayed N. Performance of machine learning versus the national early warning score for predicting patient deterioration risk: a single-site study of emergency admissions. BMJ Health Care Inform 2024; 31:e101088. [PMID: 39632097 PMCID: PMC11624723 DOI: 10.1136/bmjhci-2024-101088] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Accepted: 11/14/2024] [Indexed: 12/07/2024] Open
Abstract
OBJECTIVES Increasing operational pressures on emergency departments (ED) make it imperative to quickly and accurately identify patients requiring urgent clinical intervention. The widespread adoption of electronic health records (EHR) makes rich feature patient data sets more readily available. These large data stores lend themselves to use in modern machine learning (ML) models. This paper investigates the use of transformer-based models to identify critical deterioration in unplanned ED admissions, using free-text fields, such as triage notes, and tabular data, including early warning scores (EWS). DESIGN A retrospective ML study. SETTING A large ED in a UK university teaching hospital. METHODS We extracted rich feature sets of routine clinical data from the EHR and systematically measured the performance of tree- and transformer-based models for predicting patient mortality or admission to critical care within 24 hours of presentation to ED. We compared our proposed models to the National EWS (NEWS). RESULTS Models were trained on 174 393 admission records. We found that models including free-text triage notes outperform structured tabular data models, achieving an average precision of 0.92, compared with 0.75 for tree-based models and 0.12 for NEWS. CONCLUSIONS Our findings suggests that machine learning models using free-text data have the potential to improve clinical decision-making in the ED; our techniques significantly reduce alert rate while detecting most high-risk patients missed by NEWS.
Collapse
Affiliation(s)
- Matthew Watson
- Department of Computer Science, Durham University, Durham, UK
| | | | - Darren Green
- Division of Cardiovascular Sciences, The University of Manchester, Manchester, UK
- Department of Renal Medicine, Northern Care Alliance NHS Foundation Trust, Salford, UK
| | - Mark Holland
- School of Clinical and Biomedical Sciences, University of Bolton, Bolton, UK
| | | | - Noura Al Moubayed
- Department of Computer Science, Durham University, Durham, UK
- Evergreen Life Ltd, Manchester, UK
| |
Collapse
|
|
18
|
Arif U, Zhang C, Hussain S, Abbasi AR. An efficient interpretable stacking ensemble model for lung cancer prognosis. Comput Biol Chem 2024; 113:108248. [PMID: 39426256 DOI: 10.1016/j.compbiolchem.2024.108248] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2024] [Revised: 09/29/2024] [Accepted: 10/09/2024] [Indexed: 10/21/2024]
Abstract
Lung cancer significantly contributes to global cancer mortality, posing challenges in clinical management. Early detection and accurate prognosis are crucial for improving patient outcomes. This study develops an interpretable stacking ensemble model (SEM) for lung cancer prognosis prediction and identifies key risk factors. Using a Kaggle dataset of 1000 patients with 22 variables, the model classifies prognosis into Low, Medium, and High-risk categories. The bootstrap method was employed for evaluation metrics, while SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations) assessed model interpretability. Results showed SEM's superior interpretability over traditional models, such as Random Forest, Logistic Regression, Decision Tree, Gradient Boosting Machine, Extreme Gradient Boosting Machine, and Light Gradient Boosting Machine. SEM achieved an accuracy of 98.90 %, precision of 98.70 %, F1 score of 98.85 %, sensitivity of 98.77 %, specificity of 95.45 %, Cohen's kappa value of 94.56 %, and an AUC of 98.10 %. The SEM demonstrated robust performance in lung cancer prognosis, revealing chronic lung cancer and genetic risk as major factors.
Collapse
Affiliation(s)
- Umair Arif
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xian, Shaanxi 710049, China.
| | - Chunxia Zhang
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xian, Shaanxi 710049, China.
| | - Sajid Hussain
- School of Mathematics and Statistics, Xi'an Jiaotong University, Xian, Shaanxi 710049, China.
| | - Abdul Rauf Abbasi
- Department of Statistics, COMSATS University Islamabad, Lahore Campus, Lahore 5400, Pakistan.
| |
Collapse
|
|
19
|
Ni P, Zhang S, Hu W, Diao M. Application of multi-feature-based machine learning models to predict neurological outcomes of cardiac arrest. Resusc Plus 2024; 20:100829. [PMID: 39639943 PMCID: PMC11617783 DOI: 10.1016/j.resplu.2024.100829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2024] [Revised: 11/01/2024] [Accepted: 11/12/2024] [Indexed: 12/07/2024] Open
Abstract
Cardiac arrest (CA) is a major disease burden worldwide and has a poor prognosis. Early prediction of CA outcomes helps optimize the therapeutic regimen and improve patients' neurological function. As the current guidelines recommend, many factors can be used to evaluate the neurological outcomes of CA patients. Machine learning (ML) has strong analytical abilities and fast computing speed; thus, it plays an irreplaceable role in prediction model development. An increasing number of researchers are using ML algorithms to incorporate demographics, arrest characteristics, clinical variables, biomarkers, physical examination findings, electroencephalograms, imaging, and other factors with predictive value to construct multi-feature prediction models for neurological outcomes of CA survivors. In this review, we explore the current application of ML models using multiple features to predict the neurological outcomes of CA patients. Although the outcome prediction model is still in development, it has strong potential to become a powerful tool in clinical practice.
Collapse
Affiliation(s)
- Peifeng Ni
- Department of Critical Care Medicine, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310000, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| | - Sheng Zhang
- Department of Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200000, China
| | - Wei Hu
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| | - Mengyuan Diao
- Department of Critical Care Medicine, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310000, China
- Department of Critical Care Medicine, Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang 310000, China
| |
Collapse
|
|
20
|
Alimohammadi E, Arjmandnia F, Ataee M, Bagheri SR. Predictive accuracy of machine learning models for conservative treatment failure in thoracolumbar burst fractures. BMC Musculoskelet Disord 2024; 25:922. [PMID: 39558324 PMCID: PMC11571883 DOI: 10.1186/s12891-024-08045-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/17/2024] [Accepted: 11/08/2024] [Indexed: 11/20/2024] Open
Abstract
BACKGROUND The management of patients with thoracolumbar burst fractures remains a topic of debate, with conservative treatment being successful in most cases but not all. This study aimed to assess the utility of machine learning models (MLMs) in predicting the need for surgery in patients with these fractures who do not respond to conservative management. METHODS A retrospective analysis of 357 patients with traumatic thoracolumbar burst fractures treated conservatively between January 2017 and October 2023 was conducted. Various potential risk factors for treatment failure were evaluated, including age, gender, BMI, smoking, diabetes, vertebral body compression rate, anterior height compression, Cobb angle, interpedicular distance, canal compromise, and pain intensity. Three MLMs-random forest (RF), support vector machine (SVM), and k-nearest neighborhood (k-NN)-were used to predict treatment failure, with the RF model also identifying factors associated with treatment failure. RESULTS Among the patients studied, most (85.2%) completed conservative treatment, while 14.8% required surgery during follow-up. Smoking (OR: 2.01; 95% CI: 1.54-2.86; p = 0.011) and interpedicular distance (OR: 2.31; 95% CI: 1.22-2.73; p = 0.003) were found to be independent risk factors for treatment failure. The MLMs demonstrated good performance, with SVM achieving the highest accuracy (0.931), followed by RF (0.911) and k-NN (0.896). SVM also exhibited superior sensitivity and specificity compared to the other models, with AUC values of 0.897, 0.854, and 0.815 for SVM, RF, and k-NN, respectively. CONCLUSION This study underscores the effectiveness of MLMs in predicting conservative treatment failure in patients with thoracolumbar burst fractures. These models offer valuable prognostic insights that can aid in optimizing patient management and clinical outcomes in this specific patient population.
Collapse
Affiliation(s)
- Ehsan Alimohammadi
- Department of Neurosurgery, Kermanshah University of Medical Sciences, Imam Reza Hospital, Kermanshah, Iran.
| | | | - Mohammadali Ataee
- Department of Radiology, Kermanshah University of Medical Sciences, Kermanshah, Iran
| | - Seyed Reza Bagheri
- Department of Neurosurgery, Kermanshah University of Medical Sciences, Imam Reza Hospital, Kermanshah, Iran
| |
Collapse
|
|
21
|
Sorayaie Azar A, Samimi T, Tavassoli G, Naemi A, Rahimi B, Hadianfard Z, Wiil UK, Nazarbaghi S, Bagherzadeh Mohasefi J, Lotfnezhad Afshar H. Predicting stroke severity of patients using interpretable machine learning algorithms. Eur J Med Res 2024; 29:547. [PMID: 39538301 PMCID: PMC11562860 DOI: 10.1186/s40001-024-02147-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2024] [Accepted: 11/05/2024] [Indexed: 11/16/2024] Open
Abstract
BACKGROUND Stroke is a significant global health concern, ranking as the second leading cause of death and placing a substantial financial burden on healthcare systems, particularly in low- and middle-income countries. Timely evaluation of stroke severity is crucial for predicting clinical outcomes, with standard assessment tools being the Rapid Arterial Occlusion Evaluation (RACE) and the National Institutes of Health Stroke Scale (NIHSS). This study aims to utilize Machine Learning (ML) algorithms to predict stroke severity using these two distinct scales. METHODS We conducted this study using two datasets collected from hospitals in Urmia, Iran, corresponding to stroke severity assessments based on RACE and NIHSS. Seven ML algorithms were applied, including K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Hyperparameter tuning was performed using grid search to optimize model performance, and SHapley Additive Explanations (SHAP) were used to interpret the contribution of individual features. RESULTS Among the models, the RF achieved the highest performance, with accuracies of 92.68% for the RACE dataset and 91.19% for the NIHSS dataset. The Area Under the Curve (AUC) was 92.02% and 97.86% for the RACE and NIHSS datasets, respectively. The SHAP analysis identified triglyceride levels, length of hospital stay, and age as critical predictors of stroke severity. CONCLUSIONS This study is the first to apply ML models to the RACE and NIHSS scales for predicting stroke severity. The use of SHAP enhances the interpretability of the models, increasing clinicians' trust in these ML algorithms. The best-performing ML model can be a valuable tool for assisting medical professionals in predicting stroke severity in clinical settings.
Collapse
Affiliation(s)
- Amir Sorayaie Azar
- SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark
- Department of Computer Engineering, Urmia University, Urmia, Iran
| | - Tahereh Samimi
- Department of Health Information Technology, Urmia University of Medical Sciences, Urmia, Iran
- Health and Biomedical Informatics Research Center, Urmia University of Medical Sciences, Urmia, Iran
| | - Ghanbar Tavassoli
- Department of Health Information Technology, Urmia University of Medical Sciences, Urmia, Iran
- Health and Biomedical Informatics Research Center, Urmia University of Medical Sciences, Urmia, Iran
- Department of Computer Engineering, Urmia Branch, Islamic Azad University, Urmia, Iran
| | - Amin Naemi
- SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark
| | - Bahlol Rahimi
- Department of Health Information Technology, Urmia University of Medical Sciences, Urmia, Iran
- Health and Biomedical Informatics Research Center, Urmia University of Medical Sciences, Urmia, Iran
| | - Zahra Hadianfard
- Department of Health Information Technology, Urmia University of Medical Sciences, Urmia, Iran
| | - Uffe Kock Wiil
- SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark
| | - Surena Nazarbaghi
- Department of Neurology, School of Medicine, Urmia University of Medical Sciences, Urmia, Iran
| | - Jamshid Bagherzadeh Mohasefi
- SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark.
- Department of Computer Engineering, Urmia University, Urmia, Iran.
| | - Hadi Lotfnezhad Afshar
- Department of Health Information Technology, Urmia University of Medical Sciences, Urmia, Iran.
- Health and Biomedical Informatics Research Center, Urmia University of Medical Sciences, Urmia, Iran.
| |
Collapse
|
|
22
|
Zhang AD, Shi QL, Zhang HT, Duan WH, Li Y, Ruan L, Han YF, Liu ZK, Li HF, Xiao JS, Shi GF, Wan X, Wang RZ. Pairwise machine learning-based automatic diagnostic platform utilizing CT images and clinical information for predicting radiotherapy locoregional recurrence in elderly esophageal cancer patients. Abdom Radiol (NY) 2024; 49:4151-4161. [PMID: 38831075 PMCID: PMC11519085 DOI: 10.1007/s00261-024-04377-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 05/04/2024] [Accepted: 05/06/2024] [Indexed: 06/05/2024]
Abstract
OBJECTIVE To investigate the feasibility and accuracy of predicting locoregional recurrence (LR) in elderly patients with esophageal squamous cell cancer (ESCC) who underwent radical radiotherapy using a pairwise machine learning algorithm. METHODS The 130 datasets enrolled were randomly divided into a training set and a testing set in a 7:3 ratio. Clinical factors were included and radiomics features were extracted from pretreatment CT scans using pyradiomics-based software, and a pairwise naive Bayes (NB) model was developed. The performance of the model was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). To facilitate practical application, we attempted to construct an automated esophageal cancer diagnosis system based on trained models. RESULTS To the follow-up date, 64 patients (49.23%) had experienced LR. Ten radiomics features and two clinical factors were selected for modeling. The model demonstrated good prediction performance, with area under the ROC curve of 0.903 (0.829-0.958) for the training cohort and 0.944 (0.849-1.000) for the testing cohort. The corresponding accuracies were 0.852 and 0.914, respectively. Calibration curves showed good agreement, and DCA curve confirmed the clinical validity of the model. The model accurately predicted LR in elderly patients, with a positive predictive value of 85.71% for the testing cohort. CONCLUSIONS The pairwise NB model, based on pre-treatment enhanced chest CT-based radiomics and clinical factors, can accurately predict LR in elderly patients with ESCC. The esophageal cancer automated diagnostic system embedded with the pairwise NB model holds significant potential for application in clinical practice.
Collapse
Affiliation(s)
- An-du Zhang
- Department of Radiotherapy, Hebei Medical University Fourth Affiliated Hospital and Hebei Provincial Tumor Hospital, 12 Jiankang Road, Shijiazhuang, Hebei, 050011, People's Republic of China
| | - Qing-Lei Shi
- School of Medicine, Chinese University of Hong Kong (Shenzhen), No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China
- Medical Big Data Laboratory, Shenzhen Research Institute of Big Data, Daoyuan Building, No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China
| | - Hong-Tao Zhang
- Department of Oncology, Hebei General Hospital, NO. 348 Heping West Road, Xinhua District, Shijiazhuang, Hebei, 050051, People's Republic of China
| | - Wen-Han Duan
- School of Computer Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100191, People's Republic of China
| | - Yang Li
- Department of Radiotherapy, Hebei Medical University Fourth Affiliated Hospital and Hebei Provincial Tumor Hospital, 12 Jiankang Road, Shijiazhuang, Hebei, 050011, People's Republic of China
| | - Li Ruan
- School of Computer Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100191, People's Republic of China
| | - Yi-Fan Han
- School of Computer Science and Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100191, People's Republic of China
| | - Zhi-Kun Liu
- Department of Radiotherapy, Hebei Medical University Fourth Affiliated Hospital and Hebei Provincial Tumor Hospital, 12 Jiankang Road, Shijiazhuang, Hebei, 050011, People's Republic of China
| | - Hao-Feng Li
- Medical Big Data Laboratory, Shenzhen Research Institute of Big Data, Daoyuan Building, No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China
| | - Jia-Shun Xiao
- Medical Big Data Laboratory, Shenzhen Research Institute of Big Data, Daoyuan Building, No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China
| | - Gao-Feng Shi
- Department of Radiotherapy, Hebei Medical University Fourth Affiliated Hospital and Hebei Provincial Tumor Hospital, 12 Jiankang Road, Shijiazhuang, Hebei, 050011, People's Republic of China.
| | - Xiang Wan
- Medical Big Data Laboratory, Shenzhen Research Institute of Big Data, Daoyuan Building, No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China.
| | - Ren-Zhi Wang
- School of Medicine, Chinese University of Hong Kong (Shenzhen), No. 2001, Longxiang Avenue, Longgang District, Shenzhen, 518172, People's Republic of China.
| |
Collapse
|
|
23
|
Yin M, Jiang Y, Yuan Y, Li C, Gao Q, Lu H, Li Z. Optimizing vancomycin dosing in pediatrics: a machine learning approach to predict trough concentrations in children under four years of age. Int J Clin Pharm 2024; 46:1134-1142. [PMID: 38861047 DOI: 10.1007/s11096-024-01745-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Accepted: 04/25/2024] [Indexed: 06/12/2024]
Abstract
BACKGROUND Vancomycin trough concentration is closely associated with clinical efficacy and toxicity. Predicting vancomycin trough concentrations in pediatric patients is challenging due to significant inter-individual variability and rapid physiological changes during maturation. AIM This study aimed to develop a machine learning model to predict vancomycin trough concentrations and determine optimal dosing regimens for pediatric patients < 4 years of age using ML algorithms. METHOD A single-center retrospective observational study was conducted from January 2017 to March 2020. Pediatric patients who received intravenous vancomycin and underwent therapeutic drug monitoring were enrolled. Seven ML models [linear regression, gradient boosted decision trees, support vector machine, decision tree, random forest, Bagging, and extreme gradient boosting (XGBoost)] were developed using 31 variables. Performance metrics including R-squared (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) were compared, and important features were ranked. RESULTS The study included 120 eligible trough concentration measurements from 112 patients. Of these, 84 measurements were used for training and 36 for testing. Among the seven algorithms tested, XGBoost showed the best performance, with a low prediction error and high goodness of fit (MAE = 2.55, RMSE = 4.13, MSE = 17.12, and R2 = 0.59). Blood urea nitrogen, serum creatinine, and creatinine clearance rate were identified as the most important predictors of vancomycin trough concentration. CONCLUSION An XGBoost ML model was developed to predict vancomycin trough concentrations and aid in drug treatment predictions as a decision-support technology.
Collapse
Affiliation(s)
- Minghui Yin
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Yuelian Jiang
- Department of Pharmacy, Shanghai Children's Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Yawen Yuan
- Department of Pharmacy, Shanghai Children's Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Chensuizi Li
- School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Qian Gao
- School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Hui Lu
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, 200127, China
| | - Zhiling Li
- Department of Pharmacy, Shanghai Children's Medical Center, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200127, China.
- NHC Key Laboratory of Medical Embryogenesis and Developmental Molecular Biology & Shanghai Key Laboratory of Embryo and Reproduction Engineering, Shanghai, 200040, China.
| |
Collapse
|
|
24
|
Li Z, Huang C, Zhao X, Gao Y, Tian S. Abnormal postcentral gyrus voxel-mirrored homotopic connectivity as a biomarker of mild cognitive impairment: A resting-state fMRI and support vector machine analysis. Exp Gerontol 2024; 195:112547. [PMID: 39168359 DOI: 10.1016/j.exger.2024.112547] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2024] [Revised: 08/11/2024] [Accepted: 08/14/2024] [Indexed: 08/23/2024]
Abstract
BACKGROUND While patients affected by mild cognitive impairment (MCI) exhibit characteristic voxel-mirrored homotopic connectivity (VMHC) alterations, the ability of such VMHC abnormalities to predict the diagnosis of MCI in these patients remains uncertain. As such, this study was performed to evaluate the potential role of VMHC abnormalities in the diagnosis of MCI. METHODS MCI patients and healthy controls (HCs) were enrolled and subjected to resting-state functional magnetic resonance imaging (rs-fMRI) and neuropsychological testing. VMHC and support vector machine (SVM) techniques were then used to examine the collected imaging data. RESULTS Totally, 53 MCI patients and 68 healthy controls were recruited. Compared to HCs, MCI patients presented with an increase in postcentral gyrus VMHC. SVM classification demonstrated the ability of postcentral gyrus VMHC values to classify HCs and MCI patients with accuracy, sensitivity, and specificity values of 63.64 %, 71.69 %, and 89.71 %, respectively. CONCLUSION VMHC abnormalities in the postcentral gyrus may be mechanistically involved in the pathophysiological progression of MCI patients, and these abnormal VMHC patterns may also offer utility as a neuroimaging biomarker for MCI patient diagnosis.
Collapse
Affiliation(s)
- Ziruo Li
- Department of General Practice, Tianyou Hospital, Affiliated to Wuhan University of Science and Technology, Wuhan 430064, Hubei, China
| | - Chunyan Huang
- Wuhan Third Hospital, Tongren Hospital of Wuhan University, Wuhan 430060, Hubei, China
| | - Xingfu Zhao
- Wuxi Mental Health Center, Nanjing Medical University, Wuxi 214151, Jiangsu, China
| | - Yujun Gao
- Department of Psychiatry, Wuhan Wuchang Hospital, Wuhan University of Science and Technology, Wuhan 430063, Hubei, China.
| | - Shenglan Tian
- Department of General Practice, Tianyou Hospital, Affiliated to Wuhan University of Science and Technology, Wuhan 430064, Hubei, China.
| |
Collapse
|
|
25
|
Huang X, Wu L, Liu Y, Xu Z, Liu C, Liu Z, Liang C. Development and validation of machine learning models for predicting HER2-zero and HER2-low breast cancers. Br J Radiol 2024; 97:1568-1576. [PMID: 38991838 PMCID: PMC11332671 DOI: 10.1093/bjr/tqae124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2024] [Revised: 02/03/2024] [Accepted: 06/23/2024] [Indexed: 07/13/2024] Open
Abstract
OBJECTIVES To develop and validate machine learning models for human epidermal growth factor receptor 2 (HER2)-zero and HER2-low using MRI features pre-neoadjuvant therapy (NAT). METHODS Five hundred and sixteen breast cancer patients post-NAT surgery were randomly divided into training (n = 362) and internal validation sets (n = 154) for model building and evaluation. MRI features (tumour diameter, enhancement type, background parenchymal enhancement, enhancement pattern, percentage of enhancement, signal enhancement ratio, breast oedema, and apparent diffusion coefficient) were reviewed. Logistic regression (LR), support vector machine (SVM), k-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) models utilized MRI characteristics for HER2 status assessment in training and validation datasets. The best-performing model generated a HER2 score, which was subsequently correlated with pathological complete response (pCR) and disease-free survival (DFS). RESULTS The XGBoost model outperformed LR, SVM, and KNN, achieving an area under the receiver operating characteristic curve (AUC) of 0.783 (95% CI, 0.733-0.833) and 0.787 (95% CI, 0.709-0.865) in the validation dataset. Its HER2 score for predicting pCR had an AUC of 0.708 in the training datasets and 0.695 in the validation dataset. Additionally, the low HER2 score was significantly associated with shorter DFS in the validation dataset (hazard ratio: 2.748, 95% CI, 1.016-7.432, P = .037). CONCLUSIONS The XGBoost model could help distinguish HER2-zero and HER2-low breast cancers and has the potential to predict pCR and prognosis in breast cancer patients undergoing NAT. ADVANCES IN KNOWLEDGE HER2-low-expressing breast cancer can benefit from the HER2-targeted therapy. Prediction of HER2-low expression is crucial for appropriate management. MRI features offer a solution to this clinical issue.
Collapse
Affiliation(s)
- Xu Huang
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| | - Lei Wu
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| | - Yu Liu
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
- Department of Ultrasound, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
| | - Zeyan Xu
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| | - Chunling Liu
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| | - Zaiyi Liu
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| | - Changhong Liang
- Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou 510080, China
| |
Collapse
|
|
26
|
Keles A, Ozisik PA, Algin O, Celebi FV, Bendechache M. Decoding pulsatile patterns of cerebrospinal fluid dynamics through enhancing interpretability in machine learning. Sci Rep 2024; 14:17854. [PMID: 39090141 PMCID: PMC11294568 DOI: 10.1038/s41598-024-67928-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2024] [Accepted: 07/17/2024] [Indexed: 08/04/2024] Open
Abstract
Analyses of complex behaviors of Cerebrospinal Fluid (CSF) have become increasingly important in diseases diagnosis. The changes of the phase-contrast magnetic resonance imaging (PC-MRI) signal formed by the velocity of flowing CSF are represented as a set of velocity-encoded images or maps, which can be thought of as signal data in the context of medical imaging, enabling the evaluation of pulsatile patterns throughout a cardiac cycle. However, automatic segmentation of the CSF region in a PC-MRI image is challenging, and implementing an explained ML method using pulsatile data as a feature remains unexplored. This paper presents lightweight machine learning (ML) algorithms to perform CSF lumen segmentation in spinal, utilizing sets of velocity-encoded images or maps as a feature. The Dataset contains 57 PC-MRI slabs by 3T MRI scanner from control and idiopathic scoliosis participants are involved to collect data. The ML models are trained with 2176 time series images. Different cardiac periods image (frame) numbers of PC-MRIs are interpolated in the preprocessing step to align to features of equal size. The fivefold cross-validation procedure is used to estimate the success of the ML models. Additionally, the study focusses on enhancing the interpretability of the highest-accuracy eXtreme gradient boosting (XGB) model by applying the shapley additive explanations (SHAP) technique. The XGB algorithm presented its highest accuracy, with an average fivefold accuracy of 0.99% precision, 0.95% recall, and 0.97% F1 score. We evaluated the significance of each pulsatile feature's contribution to predictions, offering a more profound understanding of the model's behavior in distinguishing CSF lumen pixels with SHAP. Introducing a novel approach in the field, develop ML models offer comprehension into feature extraction and selection from PC-MRI pulsatile data. Moreover, the explained ML model offers novel and valuable insights to domain experts, contributing to an enhanced scholarly understanding of CSF dynamics.
Collapse
Affiliation(s)
- Ayse Keles
- Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Ankara Medipol University, Ankara, Turkey.
| | - Pinar Akdemir Ozisik
- Department of Neurosurgery, School of Medicine, Ankara Yildirim Beyazit University, Ankara, Turkey
- Ankara City Hospital, Orthopedics and Neurology Tower, Bilkent, 06800, Ankara, Turkey
| | - Oktay Algin
- Interventional MR Clinical R&D Institute, Ankara University, Ankara, Turkey
- National MR Research Center (UMRAM), Bilkent University, Ankara, Turkey
- Radiology Department, Medical Faculty, Ankara University, Ankara, Turkey
| | - Fatih Vehbi Celebi
- Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Ankara Yildirim Beyazit University, 06010, Ayvalı, Keçiören, Ankara, Turkey
| | - Malika Bendechache
- Lero and ADAPT Research Centres, School of Computer Science, University of Galway, Galway, Ireland
| |
Collapse
|
|
27
|
Sharma CM, Chariar VM. Diagnosis of mental disorders using machine learning: Literature review and bibliometric mapping from 2012 to 2023. Heliyon 2024; 10:e32548. [PMID: 38975193 PMCID: PMC11225745 DOI: 10.1016/j.heliyon.2024.e32548] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2024] [Revised: 06/05/2024] [Accepted: 06/05/2024] [Indexed: 07/09/2024] Open
Abstract
Background Mental disorders (MDs) are becoming a leading burden in non-communicable diseases (NCDs). As per the World Health Organization's 2022 assessment report, there was a steep increase of 25 % in MDs during the COVID-19 pandemic. Early diagnosis of MDs can significantly improve treatment outcome and save disability-adjusted life years (DALYs). In recent times, the application of machine learning (ML) and deep learning (DL)) has shown promising results in the diagnosis of MDs, and the field has witnessed a huge research output in the form of research publications. Therefore, a bibliometric mapping along with a review of recent advancements is required. Methods This study presents a bibliometric analysis and review of the research, published over the last 10 years. Literature searches were conducted in the Scopus database for the period from January 1, 2012, to June 9, 2023. The data was filtered and screened to include only relevant and reliable publications. A total of 2811 journal articles were found. The data was exported to a comma-separated value (CSV) format for further analysis. Furthermore, a review of 40 selected studies was performed. Results The popularity of ML techniques in diagnosing MDs has been growing, with an annual research growth rate of 17.05 %. The Journal of Affective Disorders published the most documents (n = 97), while Wang Y. (n = 64) has published the most articles. Lotka's law is observed, with a minority of authors contributing the majority of publications. The top affiliating institutes are the West China Hospital of Sichuan University followed by the University of California, with China and the US dominating the top 10 institutes. While China has more publications, papers affiliated with the US receive more citations. Depression and schizophrenia are the primary focuses of ML and deep learning (DL) in mental disease detection. Co-occurrence network analysis reveals that ML is associated with depression, schizophrenia, autism, anxiety, ADHD, obsessive-compulsive disorder, and PTSD. Popular algorithms include support vector machine (SVM) classifier, decision tree classifier, and random forest classifier. Furthermore, DL is linked to neuroimaging techniques such as MRI, fMRI, and EEG, as well as bipolar disorder. Current research trends encompass DL, LSTM, generalized anxiety disorder, feature fusion, and convolutional neural networks.
Collapse
Affiliation(s)
- Chandra Mani Sharma
- CRDT, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India
- School of Computer Science, UPES, Dehradun, Uttarakhand, India
| | | |
Collapse
|
|
28
|
Wang Q, Liang T, Li Y, Liu X. Machine Learning for Prediction of Non-Small Cell Lung Cancer Based on Inflammatory and Nutritional Indicators in Adults: A Cross-Sectional Study. Cancer Manag Res 2024; 16:527-535. [PMID: 38832344 PMCID: PMC11146620 DOI: 10.2147/cmar.s454638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Accepted: 05/23/2024] [Indexed: 06/05/2024] Open
Abstract
Purpose The aim of this study was to evaluate the potential benefit of blood inflammation in the diagnosis of non-small cell lung cancer (NSCLC) and propose a machine-learning-based method to predict NSCLC in asymptomatic adults. Patients and Methods A cross-sectional study was evaluated using medical records of 139 patients with non-small cell lung cancer and physical examination data from May 2022 to May 2023 of 198 healthy controls. The NSCLC cohort comprised 128 cases of adenocarcinoma, 3 cases of squamous cell carcinoma, and 8 cases of other NSCLC subtypes. The correlation between inflammatory and nutritional markers, such as monocytes, neutrophils, LMR, NLR, PLR, PHR and non-small cell lung cancer was examined. Features were selected using Python's feature selection library and analyzed by five algorithms. The predictive ability of the model for non-small cell lung cancer diagnosis was assessed by precision, accuracy, recall, F1 score, and area under the curve (AUC). Results The results showed that the top 14 important factors were PDW, age, TP, RBC, HGB, LYM, LYM%, RDW, PLR, LMR, PHR, MONO, MONO%, gender. Additionally, the naive Bayes (NB) algorithm demonstrated the highest overall performance in predicting adult NSCLC among the five machine learning algorithms, achieving an accuracy of 0.87, a macro average F1 score of 0.85, a weighted average F1 score of 0.87, and an AUC of 0.84. Conclusion In feature ranking, platelet distribution width was the most important feature, and the NB algorithm performed best in predicting adult NSCLC diagnosis.
Collapse
Affiliation(s)
- Qiaoli Wang
- Department of Health Screening Center, Deyang Peoples' Hospital, Deyang, Sichuan, 618000, People's Republic of China
| | - Tao Liang
- Department of Gastroenterology, Deyang Peoples' Hospital, Deyang, Sichuan, 618000, People's Republic of China
| | - Yuexi Li
- Department of Health Screening Center, Deyang Peoples' Hospital, Deyang, Sichuan, 618000, People's Republic of China
| | - Xiaoqin Liu
- Department of Health Screening Center, Deyang Peoples' Hospital, Deyang, Sichuan, 618000, People's Republic of China
| |
Collapse
|
|
29
|
Alkanj A, Godet J, Johns E, Gourieux B, Michel B. Deep learning application to automated classification of recommendations made by hospital pharmacists during medication prescription review. Am J Health Syst Pharm 2024; 81:e296-e303. [PMID: 38294025 DOI: 10.1093/ajhp/zxae011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2024] [Indexed: 02/01/2024] Open
Abstract
PURPOSE Recommendations to improve therapeutics are proposals made by pharmacists during the prescription review process to address suboptimal use of medicines. Recommendations are generated daily as text documents but are rarely reused beyond their primary use to alert prescribers and caregivers. If recommendation data were easier to summarize, they could be used retrospectively to improve safeguards for better prescribing. The objective of this work was to train a deep learning algorithm for automated recommendation classification to valorize the large amount of recommendation data. METHODS The study was conducted in a French university hospital, at which recommendation data were collected throughout 2017. Data from the first 6 months of 2017 were labeled by 2 pharmacists who assigned recommendations to 1 of the 29 possible classes of the French Society of Clinical Pharmacy classification. A deep neural network classifier was trained to predict the class of recommendations. RESULTS In total, 27,699 labeled recommendations from the first half of 2017 were used to train and evaluate a classifier. The prediction accuracy calculated on a validation dataset was 78.0%. We also predicted classes for unlabeled recommendations collected during the second half of 2017. Of the 4,460 predictions reviewed, 67 required correction. When these additional labeled data were concatenated with the original dataset and the neural network was retrained, accuracy reached 81.0%. CONCLUSION To facilitate analysis of recommendations, we have implemented an automated classification system using deep learning that achieves respectable performance. This tool can help to retrospectively highlight the clinical significance of daily medication reviews performed by hospital clinical pharmacists.
Collapse
Affiliation(s)
- Ahmad Alkanj
- Laboratoire de Pharmacologie et Toxicologie NeuroCardiovasculaire UR7296, Département Universitaire de Pharmacologie, Addictologie, Toxicologie et Thérapeutique, Centre de Recherche en Biomédecine de Strasbourg, Université de Strasbourg, Strasbourg, France
| | - Julien Godet
- ICube-IMAGeS, UMR 7357, Université de Strasbourg, Strasbourg, and Groupe Méthodes Recherche Clinique, Pôle de Santé Publique, Hôpitaux Universitaires de Strasbourg, Strasbourg, France
| | - Erin Johns
- Laboratoire de Pharmacologie et Toxicologie NeuroCardiovasculaire UR7296, Département Universitaire de Pharmacologie, Addictologie, Toxicologie et Thérapeutique, Centre de Recherche en Biomédecine de Strasbourg, Université de Strasbourg, Strasbourg, and ICube-IMAGeS, UMR 7357, Université de Strasbourg, Strasbourg, France
| | - Bénédicte Gourieux
- Laboratoire de Pharmacologie et Toxicologie NeuroCardiovasculaire UR7296, Département Universitaire de Pharmacologie, Addictologie, Toxicologie et Thérapeutique, Centre de Recherche en Biomédecine de Strasbourg, Université de Strasbourg, Strasbourg, and Service de Pharmacie, Hôpitaux Universitaires de Strasbourg, Strasbourg, France
| | - Bruno Michel
- Laboratoire de Pharmacologie et Toxicologie NeuroCardiovasculaire UR7296, Département Universitaire de Pharmacologie, Addictologie, Toxicologie et Thérapeutique, Centre de Recherche en Biomédecine de Strasbourg, Université de Strasbourg, Strasbourg, and Service de Pharmacie, Hôpitaux Universitaires de Strasbourg, Strasbourg, France
| |
Collapse
|
|
30
|
Clifford JO, Anand S, Tarpin-Bernard F, Bergeron MF, Ashford CB, Bayley PJ, Ashford JW. Episodic memory assessment: effects of sex and age on performance and response time during a continuous recognition task. Front Hum Neurosci 2024; 18:1304221. [PMID: 38638807 PMCID: PMC11024362 DOI: 10.3389/fnhum.2024.1304221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 03/08/2024] [Indexed: 04/20/2024] Open
Abstract
Introduction Continuous recognition tasks (CRTs) assess episodic memory (EM), the central functional disturbance in Alzheimer's disease and several related disorders. The online MemTrax computerized CRT provides a platform for screening and assessment that is engaging and can be repeated frequently. MemTrax presents complex visual stimuli, which require complex involvement of the lateral and medial temporal lobes and can be completed in less than 2 min. Results include number of correct recognitions (HITs), recognition failures (MISSes = 1-HITs), correct rejections (CRs), false alarms (FAs = 1-CRs), total correct (TC = HITs + CRs), and response times (RTs) for each HIT and FA. Prior analyses of MemTrax CRT data show no effects of sex but an effect of age on performance. The number of HITs corresponds to faster RT-HITs more closely than TC, and CRs do not relate to RT-HITs. RT-HITs show a typical skewed distribution, and cumulative RT-HITs fit a negative survival curve (RevEx). Thus, this study aimed to define precisely the effects of sex and age on HITS, CRs, RT-HITs, and the dynamics of RTs in an engaged population. Methods MemTrax CRT online data on 18,255 individuals was analyzed for sex, age, and distributions of HITs, CRs, MISSes, FAs, TC, and relationships to both RT-HITs and RT-FAs. Results HITs corresponded more closely to RT-HITs than did TC because CRs did not relate to RT-HITs. RT-FAs had a broader distribution than RT-HITs and were faster than RT-HITs in about half of the sample, slower in the other half. Performance metrics for men and women were the same. HITs declined with age as RT-HITs increased. CRs also decreased with age and RT-FAs increased, but with no correlation. The group over aged 50 years had RT-HITs distributions slower than under 50 years. For both age ranges, the RevEx model explained more than 99% of the variance in RT-HITs. Discussion The dichotomy of HITs and CRs suggests opposing cognitive strategies: (1) less certainty about recognitions, in association with slower RT-HITs and lower HIT percentages suggests recognition difficulty, leading to more MISSes, and (2) decreased CRs (more FAs) but faster RTs to HITs and FAs, suggesting overly quick decisions leading to errors. MemTrax CRT performance provides an indication of EM (HITs and RT-HITs may relate to function of the temporal lobe), executive function (FAs may relate to function of the frontal lobe), processing speed (RTs), cognitive ability, and age-related changes. This CRT provides potential clinical screening utility for early Alzheimer's disease and other conditions affecting EM, other cognitive functions, and more accurate impairment assessment to track changes over time.
Collapse
Affiliation(s)
- James O. Clifford
- Department of Psychology, College of San Mateo, San Mateo, CA, United States
| | - Sulekha Anand
- Department of Biological Sciences, San Jose State University, San Jose, CA, United States
| | | | - Michael F. Bergeron
- Department of Health Sciences, University of Hartford, West Hartford, CT, United States
| | - Curtis B. Ashford
- MemTrax, LLC, Redwood City, CA, United States
- CogniFit, LLC, Redwood City, CA, United States
| | - Peter J. Bayley
- VA Palo Alto Health Care System, Palo Alto, CA, United States
- Department of Psychiatry and Behavioral Sciences, Stanford, CA, United States
| | - John Wesson Ashford
- VA Palo Alto Health Care System, Palo Alto, CA, United States
- Department of Psychiatry and Behavioral Sciences, Stanford, CA, United States
| |
Collapse
|
|
31
|
Wang C, Chen A, He X, Balian P, George TJ, Wang F, Bian J, Guo Y. Effect of Eligibility Criteria on Patients' Survival and Serious Adverse Events in Colorectal Cancer Drug Trials. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.04.03.24305265. [PMID: 38633798 PMCID: PMC11023646 DOI: 10.1101/2024.04.03.24305265] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/19/2024]
Abstract
This study investigates the impact of clinical trial eligibility criteria on patient survival and serious adverse events (SAEs) in colorectal cancer (CRC) drug trials using real-world data. We utilized the OneFlorida+ network's data repository, conducting a retrospective analysis of CRC patients receiving FDA-approved first-line metastatic treatments. Propensity score matching created balanced case-control groups, which were evaluated using survival analysis and machine learning algorithms to assess the effects of eligibility criteria. Our study included 68,375 patients, with matched case-control groups comprising 1,126 patients each. Survival analysis revealed ethnicity and race, along with specific medical history (eligibility criteria), as significant survival outcome predictors. Machine learning models, particularly the XgBoost regressor, were employed to analyze SAEs, indicating that age and study groups were notable factors in SAEs occurrence. The study's findings highlight the importance of considering patient demographics and medical history in CRC trial designs.
Collapse
|
|
32
|
Kasun M, Ryan K, Paik J, Lane-McKinley K, Dunn LB, Roberts LW, Kim JP. Academic machine learning researchers' ethical perspectives on algorithm development for health care: a qualitative study. J Am Med Inform Assoc 2024; 31:563-573. [PMID: 38069455 PMCID: PMC10873830 DOI: 10.1093/jamia/ocad238] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 10/20/2023] [Accepted: 12/05/2023] [Indexed: 02/18/2024] Open
Abstract
OBJECTIVES We set out to describe academic machine learning (ML) researchers' ethical considerations regarding the development of ML tools intended for use in clinical care. MATERIALS AND METHODS We conducted in-depth, semistructured interviews with a sample of ML researchers in medicine (N = 10) as part of a larger study investigating stakeholders' ethical considerations in the translation of ML tools in medicine. We used a qualitative descriptive design, applying conventional qualitative content analysis in order to allow participant perspectives to emerge directly from the data. RESULTS Every participant viewed their algorithm development work as holding ethical significance. While participants shared positive attitudes toward continued ML innovation, they described concerns related to data sampling and labeling (eg, limitations to mitigating bias; ensuring the validity and integrity of data), and algorithm training and testing (eg, selecting quantitative targets; assessing reproducibility). Participants perceived a need to increase interdisciplinary training across stakeholders and to envision more coordinated and embedded approaches to addressing ethics issues. DISCUSSION AND CONCLUSION Participants described key areas where increased support for ethics may be needed; technical challenges affecting clinical acceptability; and standards related to scientific integrity, beneficence, and justice that may be higher in medicine compared to other industries engaged in ML innovation. Our results help shed light on the perspectives of ML researchers in medicine regarding the range of ethical issues they encounter or anticipate in their work, including areas where more attention may be needed to support the successful development and integration of medical ML tools.
Collapse
Affiliation(s)
- Max Kasun
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| | - Katie Ryan
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| | - Jodi Paik
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| | - Kyle Lane-McKinley
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| | - Laura Bodin Dunn
- Department of Psychiatry, University of Arkansas for Medical Sciences, Little Rock, AK 72205, United States
| | - Laura Weiss Roberts
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| | - Jane Paik Kim
- Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94305, United States
| |
Collapse
|
|
33
|
Hedelius BE, Tingey D, Della Corte D. TrIP─Transformer Interatomic Potential Predicts Realistic Energy Surface Using Physical Bias. J Chem Theory Comput 2024; 20:199-211. [PMID: 38150692 DOI: 10.1021/acs.jctc.3c00936] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2023]
Abstract
Accurate interatomic energies and forces enable high-quality molecular dynamics simulations, torsion scans, potential energy surface mappings, and geometry optimizations. Machine learning algorithms have enabled rapid estimates of the energies and forces with high accuracy. Further development of machine learning algorithms holds promise for producing universal potentials that support many different atomic species. We present the Transformer Interatomic Potential (TrIP): a chemically sound potential based on the SE(3)-Transformer. TrIP's species-agnostic architecture, which uses continuous atomic representation and homogeneous graph convolutions, encourages parameter sharing between atomic species for more general representations of chemical environments, maintains a reasonable number of parameters, serves as a form of regularization, and is a step toward accurate universal interatomic potentials. TrIP achieves state-of-the-art accuracies on the COMP6 benchmark with an energy prediction of just 1.02 kcal/mol MAE. We introduce physical bias in the form of Ziegler-Biersack-Littmark-screened nuclear repulsion and constrained atomization energies. An energy scan of a water molecule demonstrates that these changes improve long- and near-range interactions compared to other neural network potentials. TrIP also demonstrates stability in molecular dynamics simulations, demonstrating reasonable exploration of Ramachandran space.
Collapse
Affiliation(s)
- Bryce E Hedelius
- Department of Physics and Astronomy, Brigham Young University, Provo, Utah 84602, United States
| | - Damon Tingey
- Department of Physics and Astronomy, Brigham Young University, Provo, Utah 84602, United States
| | - Dennis Della Corte
- Department of Physics and Astronomy, Brigham Young University, Provo, Utah 84602, United States
| |
Collapse
|
|
34
|
Evans HG, Murphy MF, Foy R, Dhiman P, Green L, Kotze A, von Neree L, Palmer AJ, Robinson SE, Shah A, Tomini F, Trompeter S, Warnakulasuriya S, Wong WK, Stanworth SJ. Harnessing the potential of data-driven strategies to optimise transfusion practice. Br J Haematol 2024; 204:74-85. [PMID: 37964471 DOI: 10.1111/bjh.19158] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Revised: 09/24/2023] [Accepted: 10/03/2023] [Indexed: 11/16/2023]
Abstract
No one doubts the significant variation in the practice of transfusion medicine. Common examples are the variability in transfusion thresholds and the use of tranexamic acid for surgery with likely high blood loss despite evidence-based standards. There is a long history of applying different strategies to address this variation, including education, clinical guidelines, audit and feedback, but the effectiveness and cost-effectiveness of these initiatives remains unclear. Advances in computerised decision support systems and the application of novel electronic capabilities offer alternative approaches to improving transfusion practice. In England, the National Institute for Health and Care Research funded a Blood and Transplant Research Unit (BTRU) programme focussing on 'A data-enabled programme of research to improve transfusion practices'. The overarching aim of the BTRU is to accelerate the development of data-driven methods to optimise the use of blood and transfusion alternatives, and to integrate them within routine practice to improve patient outcomes. One particular area of focus is implementation science to address variation in practice.
Collapse
Affiliation(s)
- H G Evans
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - M F Murphy
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK
- NHS Blood and Transplant, John Radcliffe Hospital, Oxford, UK
| | - R Foy
- Leeds Institute of Health Sciences, University of Leeds, Leeds, UK
| | - P Dhiman
- Centre for Statistics in Medicine, Botnar Research Centre, Oxford, UK
| | - L Green
- Blizard Institute, Queen Mary University of London, London, UK
- Barts Health NHS Trust, London, UK
- NHS Blood and Transplant, London, UK
| | - A Kotze
- Leeds Teaching Hospitals, Leeds, UK
| | - L von Neree
- University College London Hospitals NHS Foundation Trust, London, UK
| | - A J Palmer
- Nuffield Orthopaedic Centre, Oxford University NHS Foundation Trust, Oxford, UK
| | - S E Robinson
- Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - A Shah
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - F Tomini
- Queen Mary University of London, London, UK
| | - S Trompeter
- University College London Hospitals NHS Foundation Trust, London, UK
- University College London, London, UK
| | - S Warnakulasuriya
- University College London Hospitals NHS Foundation Trust, London, UK
- University College London, London, UK
| | - W K Wong
- Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
| | - S J Stanworth
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK
- NHS Blood and Transplant, John Radcliffe Hospital, Oxford, UK
| |
Collapse
|
|
35
|
Kim NH, Kim M, Han JS, Sohn H, Oh B, Lee JW, Ahn S. Machine-learning model for predicting depression in second-hand smokers in cross-sectional data using the Korea National Health and Nutrition Examination Survey. Digit Health 2024; 10:20552076241257046. [PMID: 38784054 PMCID: PMC11113066 DOI: 10.1177/20552076241257046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 05/07/2024] [Indexed: 05/25/2024] Open
Abstract
Objective Depression among non-smokers at risk of second-hand smoke (SHS) exposure has been a neglected public health concern despite their vulnerability. The objective of this study was to develop high-performance machine-learning (ML) models for the prediction of depression in non-smokers and to identify important predictors of depression for second-hand smokers. Methods ML algorithms were created using demographic and clinical data from the Korea National Health and Nutrition Examination Survey (KNHANES) participants from 2014, 2016, and 2018 (N = 11,463). The Patient Health Questionnaire was used to diagnose depression with a total score of 10 or higher. The final model was selected according to the area under the curve (AUC) or sensitivity. Shapley additive explanations (SHAP) were used to identify influential features. Results The light gradient boosting machine (LGBM) with the highest positive predictive value (PPV; 0.646) was selected as the best model among the ML algorithms, whereas the support vector machine (SVM) had the highest AUC (0.900). The most influential factors identified using the LGBM were stress perception, followed by subjective health status and quality of life. Among the smoking-related features, urine cotinine levels were the most important, and no linear relationship existed between the smoking-related features and the values of SHAP. Conclusions Compared with the previously developed ML models, our LGBM models achieved excellent and even superior performance in predicting depression among non-smokers at risk of SHS exposure, suggesting potential goals for depression-preventive interventions for non-smokers during public health crises.
Collapse
Affiliation(s)
- Na Hyun Kim
- Health Promotion Center, Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Myeongju Kim
- Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital Healthcare Innovation Park, Seongnam, South Korea
| | - Jong Soo Han
- Health Promotion Center, Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Hyoju Sohn
- Center for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital Healthcare Innovation Park, Seongnam, South Korea
| | - Bumjo Oh
- Department of Family Medicine, SMG-SNU Boramae Medical Center, Seoul, Republic of Korea
| | - Ji Won Lee
- Department of Urology, Seoul National University Bundang Hospital, Seongnam, South Korea
| | - Sumin Ahn
- Department of Digital Healthcare, Seoul National University Bundang Hospital, Seongnam, South Korea
| |
Collapse
|
|
36
|
Maynard S, Farrington J, Alimam S, Evans H, Li K, Wong WK, Stanworth SJ. Machine learning in transfusion medicine: A scoping review. Transfusion 2024; 64:162-184. [PMID: 37950535 PMCID: PMC11497333 DOI: 10.1111/trf.17582] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 09/25/2023] [Accepted: 09/27/2023] [Indexed: 11/12/2023]
Affiliation(s)
- Suzanne Maynard
- Medical Sciences Division, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
- NHSBT and Oxford University Hospitals NHS Foundation TrustOxfordUK
| | | | - Samah Alimam
- Haematology DepartmentUniversity College London Hospitals NHS Foundation TrustLondonUK
| | - Hayley Evans
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
| | - Kezhi Li
- Institute of Health InformaticsUniversity College LondonLondonUK
| | - Wai Keong Wong
- Director of DigitalCambridge University Hospitals NHS Foundation TrustCambridgeUK
| | - Simon J. Stanworth
- Medical Sciences Division, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of MedicineUniversity of OxfordOxfordUK
- NHSBT and Oxford University Hospitals NHS Foundation TrustOxfordUK
| |
Collapse
|
|
37
|
Ratna HVK, Jeyaraman M, Jeyaraman N, Nallakumarasamy A, Sharma S, Khanna M, Gupta A. Machine learning and deep neural network-based learning in osteoarthritis knee. World J Methodol 2023; 13:419-425. [PMID: 38229942 PMCID: PMC10789099 DOI: 10.5662/wjm.v13.i5.419] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Revised: 09/14/2023] [Accepted: 09/28/2023] [Indexed: 12/20/2023] Open
Abstract
Osteoarthritis (OA) of the knee joint is considered the commonest musculoskeletal condition leading to marked disability for patients residing in various regions around the globe. Application of machine learning (ML) in doing research regarding OA has brought about various clinical advances viz, OA being diagnosed at preliminary stages, prediction of chances of development of OA among the population, discovering various phenotypes of OA, calculating the severity in OA structure and also discovering people with slow and fast progression of disease pathology, etc. Various publications are available regarding machine learning methods for the early detection of osteoarthritis. The key features are detected by morphology, molecular architecture, and electrical and mechanical functions. In addition, this particular technique was utilized to assess non-interfering, non-ionizing, and in-vivo techniques using magnetic resonance imaging. ML is being utilized in OA, chiefly with the formulation of large cohorts viz, the OA Initiative, a cohort observational study, the Multi-centre Osteoarthritis Study, an observational, prospective longitudinal study and the Cohort Hip & Cohort Knee, an observational cohort prospective study of both hip and knee OA. Though ML has various contributions and enhancing applications, it remains an imminent field with high potential, also with its limitations. Many more studies are to be carried out to find more about the link between machine learning and knee osteoarthritis, which would help in the improvement of making decisions clinically, and expedite the necessary interventions.
Collapse
Affiliation(s)
- Harish V K Ratna
- Department of Orthopaedics, Rathimed Speciality Hospital, Chennai 600040, Tamil Nadu, India
| | - Madhan Jeyaraman
- Department of Orthopaedics, ACS Medical College and Hospital, Dr MGR Educational and Research Institute, Chennai 600077, Tamil Nadu, India
- Department of Orthopaedics, South Texas Orthopaedic Research Institute, Laredo, TX 78045, United States
| | - Naveen Jeyaraman
- Department of Orthopaedics, ACS Medical College and Hospital, Dr MGR Educational and Research Institute, Chennai 600077, Tamil Nadu, India
| | - Arulkumar Nallakumarasamy
- Department of Orthopaedics, ACS Medical College and Hospital, Dr MGR Educational and Research Institute, Chennai 600077, Tamil Nadu, India
| | - Shilpa Sharma
- Department of Paediatric Surgery, All India Institute of Medical Sciences, New Delhi 110029, India
| | - Manish Khanna
- Department of Orthopaedics, Autonomous State Medical College, Ayodhya 224133, Uttar Pradesh, India
| | - Ashim Gupta
- Department of Orthopaedics, South Texas Orthopaedic Research Institute, Laredo, TX 78045, United States
- Department of Regenerative Medicine, Regenerative Orthopaedics, Noida 201301, Uttar Pradesh, India
- Department of Regenerative Medicine, Future Biologics, Lawrenceville, GA 30043, United States
- Department of Regenerative Medicine, BioIntegarte, Lawrenceville, GA 30043, United States
| |
Collapse
|
|
38
|
Ghorbian M, Ghorbian S. Usefulness of machine learning and deep learning approaches in screening and early detection of breast cancer. Heliyon 2023; 9:e22427. [PMID: 38076050 PMCID: PMC10709063 DOI: 10.1016/j.heliyon.2023.e22427] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Revised: 11/07/2023] [Accepted: 11/13/2023] [Indexed: 10/16/2024] Open
Abstract
Breast cancer (BC) is one of the most common types of cancer in women, and its prevalence is on the rise. The diagnosis of this disease in the first steps can be highly challenging. Hence, early and rapid diagnosis of this disease in its early stages increases the likelihood of a patient's recovery and survival. This study presents a systematic and detailed analysis of the various ML approaches and mechanisms employed during the BC diagnosis process. Further, this study provides a comprehensive and accurate overview of techniques, approaches, challenges, solutions, and important concepts related to this process in order to provide healthcare professionals and technologists with a deeper understanding of new screening and diagnostic tools and approaches, as well as identify new challenges and popular approaches in this field. Therefore, this study has attempted to provide a comprehensive taxonomy of applying ML techniques to BC diagnosis, focusing on the data obtained from the clinical methods diagnosis. The taxonomy presented in this study has two major components. Clinical diagnostic methods such as MRI, mammography, and hybrid methods are presented in the first part of the taxonomy. The second part involves implementing machine learning approaches such as neural networks (NN), deep learning (DL), and hybrid on the dataset in the first part. Then, the taxonomy will be analyzed based on implementing ML approaches in clinical diagnosis methods. The findings of the study demonstrated that the approaches based on NN and DL are the most accurate and widely used models for BC diagnosis compared to other diagnostic techniques, and accuracy (ACC), sensitivity (SEN), and specificity (SPE) are the most commonly used performance evaluation criteria. Additionally, factors such as the advantages and disadvantages of using machine learning techniques, as well as the objectives of each research, separately for ML technology and BC detection, as well as evaluation criteria, are discussed in this study. Lastly, this study provides an overview of open and unresolved issues related to using ML for BC diagnosis, along with a proposal to resolve each issue to assist researchers and healthcare professionals.
Collapse
Affiliation(s)
- Mohsen Ghorbian
- Department of Computer Engineering, Qom Branch, Islamic Azad University, Qom, Iran
| | - Saeid Ghorbian
- Department of Molecular Genetics, Ahar Branch, Islamic Azad University, Ahar, Iran
| |
Collapse
|
|
39
|
Xu Z, Xie Y, Wu L, Chen M, Shi Z, Cui Y, Han C, Lin H, Liu Y, Li P, Chen X, Ding Y, Liu Z. Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI Characteristics. J Magn Reson Imaging 2023; 58:1580-1589. [PMID: 36797654 DOI: 10.1002/jmri.28647] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 02/01/2023] [Accepted: 02/02/2023] [Indexed: 02/18/2023] Open
Abstract
BACKGROUND Preoperative assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) is of high clinical relevance for treatment decision-making and prognosis. PURPOSE To investigate the associations of preoperative clinical and magnetic resonance imaging (MRI) characteristics with LVI and disease-free survival (DFS) by using machine learning methods in patients with IBC. STUDY TYPE Retrospective. POPULATION Five hundred and seventy-five women (range: 24-79 years) with IBC who underwent preoperative MRI examinations at two hospitals, divided into the training (N = 386) and validation datasets (N = 189). FIELD STRENGTH/SEQUENCE Axial fat-suppressed T2-weighted turbo spin-echo sequence and dynamic contrast-enhanced with fat-suppressed T1-weighted three-dimensional gradient echo imaging. ASSESSMENT MRI characteristics (clinical T stage, breast edema score, MRI axillary lymph node status, multicentricity or multifocality, enhancement pattern, adjacent vessel sign, and increased ipsilateral vascularity) were reviewed independently by three radiologists. Logistic regression (LR), eXtreme Gradient Boosting (XGBoost), k-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms were used to establish the models by combing preoperative clinical and MRI characteristics for assessing LVI status in the training dataset, and the methods were further applied in the validation dataset. The LVI score was calculated using the best-performing of the four models to analyze the association with DFS. STATISTICAL TESTS Chi-squared tests, variance inflation factors, receiver operating characteristics (ROC), Kaplan-Meier curve, log-rank, Cox regression, and intraclass correlation coefficient were performed. The area under the ROC curve (AUC) and hazard ratios (HR) were calculated. A P-value <0.05 was considered statistically significant. RESULTS The model established by the XGBoost algorithm had better performance than LR, SVM, and KNN models, achieving an AUC of 0.832 (95% confidence interval [CI]: 0.789, 0.876) in the training dataset and 0.838 (95% CI: 0.775, 0.901) in the validation dataset. The LVI score established by the XGBoost model was an independent indicator of DFS (adjusted HR: 2.66, 95% CI: 1.22-5.80). DATA CONCLUSION The XGBoost model based on preoperative clinical and MRI characteristics may help to investigate the LVI status and survival in patients with IBC. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Zeyan Xu
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Yu Xie
- Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming, China
| | - Lei Wu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Minglei Chen
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Shantou University Medical College, Shantou, China
| | - Zhenwei Shi
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Yanfen Cui
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Chu Han
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Huan Lin
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| | - Yu Liu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Pinxiong Li
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
| | - Xin Chen
- Department of Radiology, Guangzhou First People's Hospital, The Second Affiliated Hospital of South China University of Technology, Guangzhou, China
| | - Yingying Ding
- Department of Radiology, The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Yunnan Cancer Center, Kunming, China
| | - Zaiyi Liu
- School of Medicine, South China University of Technology, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
| |
Collapse
|
|
40
|
Badawy M, Balaha HM, Maklad AS, Almars AM, Elhosseini MA. Revolutionizing Oral Cancer Detection: An Approach Using Aquila and Gorilla Algorithms Optimized Transfer Learning-Based CNNs. Biomimetics (Basel) 2023; 8:499. [PMID: 37887629 PMCID: PMC10604828 DOI: 10.3390/biomimetics8060499] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Revised: 10/11/2023] [Accepted: 10/17/2023] [Indexed: 10/28/2023] Open
Abstract
The early detection of oral cancer is pivotal for improving patient survival rates. However, the high cost of manual initial screenings poses a challenge, especially in resource-limited settings. Deep learning offers an enticing solution by enabling automated and cost-effective screening. This study introduces a groundbreaking empirical framework designed to revolutionize the accurate and automatic classification of oral cancer using microscopic histopathology slide images. This innovative system capitalizes on the power of convolutional neural networks (CNNs), strengthened by the synergy of transfer learning (TL), and further fine-tuned using the novel Aquila Optimizer (AO) and Gorilla Troops Optimizer (GTO), two cutting-edge metaheuristic optimization algorithms. This integration is a novel approach, addressing bias and unpredictability issues commonly encountered in the preprocessing and optimization phases. In the experiments, the capabilities of well-established pre-trained TL models, including VGG19, VGG16, MobileNet, MobileNetV3Small, MobileNetV2, MobileNetV3Large, NASNetMobile, and DenseNet201, all initialized with 'ImageNet' weights, were harnessed. The experimental dataset consisted of the Histopathologic Oral Cancer Detection dataset, which includes a 'normal' class with 2494 images and an 'OSCC' (oral squamous cell carcinoma) class with 2698 images. The results reveal a remarkable performance distinction between the AO and GTO, with the AO consistently outperforming the GTO across all models except for the Xception model. The DenseNet201 model stands out as the most accurate, achieving an astounding average accuracy rate of 99.25% with the AO and 97.27% with the GTO. This innovative framework signifies a significant leap forward in automating oral cancer detection, showcasing the tremendous potential of applying optimized deep learning models in the realm of healthcare diagnostics. The integration of the AO and GTO in our CNN-based system not only pushes the boundaries of classification accuracy but also underscores the transformative impact of metaheuristic optimization techniques in the field of medical image analysis.
Collapse
Affiliation(s)
- Mahmoud Badawy
- Department of Computer Science and Informatics, Applied College, Taibah University, Al Madinah Al Munawwarah 41461, Saudi Arabia
- Department of Computers and Control Systems Engineering, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt (M.A.E.)
| | - Hossam Magdy Balaha
- Department of Computers and Control Systems Engineering, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt (M.A.E.)
- Department of Bioengineering, Speed School of Engineering, University of Louisville, Louisville, KY 40208, USA
| | - Ahmed S. Maklad
- College of Computer Science and Engineering, Taibah University, Yanbu 46421, Saudi Arabia; (A.S.M.); (A.M.A.)
- Information Systems Department, Faculty of Computers and Artificial Intelligence, Beni-Suef University, Beni-Suif 62521, Egypt
| | - Abdulqader M. Almars
- College of Computer Science and Engineering, Taibah University, Yanbu 46421, Saudi Arabia; (A.S.M.); (A.M.A.)
| | - Mostafa A. Elhosseini
- Department of Computers and Control Systems Engineering, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt (M.A.E.)
- College of Computer Science and Engineering, Taibah University, Yanbu 46421, Saudi Arabia; (A.S.M.); (A.M.A.)
| |
Collapse
|
|
41
|
Altuhaifa FA, Win KT, Su G. Predicting lung cancer survival based on clinical data using machine learning: A review. Comput Biol Med 2023; 165:107338. [PMID: 37625260 DOI: 10.1016/j.compbiomed.2023.107338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 07/31/2023] [Accepted: 08/07/2023] [Indexed: 08/27/2023]
Abstract
Machine learning has gained popularity in predicting survival time in the medical field. This review examines studies utilizing machine learning and data-mining techniques to predict lung cancer survival using clinical data. A systematic literature review searched MEDLINE, Scopus, and Google Scholar databases, following reporting guidelines and using the COVIDENCE system. Studies published from 2000 to 2023 employing machine learning for lung cancer survival prediction were included. Risk of bias assessment used the prediction model risk of bias assessment tool. Thirty studies were reviewed, with 13 (43.3%) using the surveillance, epidemiology, and end results database. Missing data handling was addressed in 12 (40%) studies, primarily through data transformation and conversion. Feature selection algorithms were used in 19 (63.3%) studies, with age, sex, and N stage being the most chosen features. Random forest was the predominant machine learning model, used in 17 (56.6%) studies. While the number of lung cancer survival prediction studies is limited, the use of machine learning models based on clinical data has grown since 2012. Consideration of diverse patient cohorts and data pre-processing are crucial. Notably, most studies did not account for missing data, normalization, scaling, or standardized data, potentially introducing bias. Therefore, a comprehensive study on lung cancer survival prediction using clinical data is needed, addressing these challenges.
Collapse
Affiliation(s)
- Fatimah Abdulazim Altuhaifa
- School of Computing and Information Technology, University of Wollongong, NSW, 2500, Australia; Saudi Arabia Ministry of Higher Education, Riyadh, Saudi Arabia.
| | - Khin Than Win
- School of Computing and Information Technology, University of Wollongong, NSW, 2500, Australia
| | - Guoxin Su
- School of Computing and Information Technology, University of Wollongong, NSW, 2500, Australia
| |
Collapse
|
|
42
|
Jian C, Chen S, Wang Z, Zhou Y, Zhang Y, Li Z, Jian J, Wang T, Xiang T, Wang X, Jia Y, Wang H, Gong J. Predicting delayed methotrexate elimination in pediatric acute lymphoblastic leukemia patients: an innovative web-based machine learning tool developed through a multicenter, retrospective analysis. BMC Med Inform Decis Mak 2023; 23:148. [PMID: 37537590 PMCID: PMC10398990 DOI: 10.1186/s12911-023-02248-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Accepted: 07/26/2023] [Indexed: 08/05/2023] Open
Abstract
BACKGROUND High-dose methotrexate (HD-MTX) is a potent chemotherapeutic agent used to treat pediatric acute lymphoblastic leukemia (ALL). HD-MTX is known for cause delayed elimination and drug-related adverse events. Therefore, close monitoring of delayed MTX elimination in ALL patients is essential. OBJECTIVE This study aimed to identify the risk factors associated with delayed MTX elimination and to develop a predictive tool for its occurrence. METHODS Patients who received MTX chemotherapy during hospitalization were selected for inclusion in our study. Univariate and least absolute shrinkage and selection operator (LASSO) methods were used to screen for relevant features. Then four machine learning (ML) algorithms were used to construct prediction model in different sampling method. Furthermore, the performance of the model was evaluated using several indicators. Finally, the optimal model was deployed on a web page to create a visual prediction tool. RESULTS The study included 329 patients with delayed MTX elimination and 1400 patients without delayed MTX elimination who met the inclusion criteria. Univariate and LASSO regression analysis identified eleven predictors, including age, weight, creatinine, uric acid, total bilirubin, albumin, white blood cell count, hemoglobin, prothrombin time, immunological classification, and co-medication with omeprazole. The XGBoost algorithm with SMOTE exhibited AUROC of 0.897, AUPR of 0.729, sensitivity of 0.808, specificity of 0.847, outperforming the other models. And had AUROC of 0.788 in external validation. CONCLUSION The XGBoost algorithm provides superior performance in predicting the delayed elimination of MTX. We have created a prediction tool to assist medical professionals in predicting MTX metabolic delay.
Collapse
Affiliation(s)
- Chang Jian
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Siqi Chen
- College of Pharmacy, Chongqing Medical University, Chongqing, China
| | - Zhuangcheng Wang
- Big Data Engineering Center, Children's Hospital of Chongqing Medical University, Chongqing, China
| | - Yang Zhou
- Department of Medicine, Affiliated Hospital of Nantong University, Jiangsu, China
| | - Yang Zhang
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Ziyu Li
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Jie Jian
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Tingting Wang
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Tianyu Xiang
- Department of Pharmacy, Children's Hospital of Chongqing Medical University, Chongqing, China
| | - Xiao Wang
- College of Medical Informatics, Chongqing Medical University, Chongqing, China
| | - Yuntao Jia
- Department of Pharmacy, Children's Hospital of Chongqing Medical University, Chongqing, China
| | - Huilai Wang
- Department of Information Center, University-Town Hospital of Chongqing Medical University, Chongqing, China.
| | - Jun Gong
- Department of Information Center, University-Town Hospital of Chongqing Medical University, Chongqing, China.
| |
Collapse
|
|
43
|
Park D, Son SI, Kim MS, Kim TY, Choi JH, Lee SE, Hong D, Kim MC. Machine learning predictive model for aspiration screening in hospitalized patients with acute stroke. Sci Rep 2023; 13:7835. [PMID: 37188793 PMCID: PMC10185509 DOI: 10.1038/s41598-023-34999-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Accepted: 05/11/2023] [Indexed: 05/17/2023] Open
Abstract
Dysphagia is a fatal condition after acute stroke. We established machine learning (ML) models for screening aspiration in patients with acute stroke. This retrospective study enrolled patients with acute stroke admitted to a cerebrovascular specialty hospital between January 2016 and June 2022. A videofluoroscopic swallowing study (VFSS) confirmed aspiration. We evaluated the Gugging Swallowing Screen (GUSS), an early assessment tool for dysphagia, in all patients and compared its predictive value with ML models. Following ML algorithms were applied: regularized logistic regressions (ridge, lasso, and elastic net), random forest, extreme gradient boosting, support vector machines, k-nearest neighbors, and naïve Bayes. We finally analyzed data from 3408 patients, and 448 of them had aspiration on VFSS. The GUSS showed an area under the receiver operating characteristics curve (AUROC) of 0.79 (0.77-0.81). The ridge regression model was the best model among all ML models, with an AUROC of 0.81 (0.76-0.86), an F1 measure of 0.45. Regularized logistic regression models exhibited higher sensitivity (0.66-0.72) than the GUSS (0.64). Feature importance analyses revealed that the modified Rankin scale was the most important feature of ML performance. The proposed ML prediction models are valid and practical for screening aspiration in patients with acute stroke.
Collapse
Affiliation(s)
- Dougho Park
- Department of Medical Science and Engineering, School of Convergence Science and Technology, Pohang University of Science and Technology, Pohang, Republic of Korea.
- Department of Rehabilitation Medicine, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea.
| | - Seok Il Son
- Occupational Therapy Department of Rehabilitation Center, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Min Sol Kim
- Occupational Therapy Department of Rehabilitation Center, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Tae Yeon Kim
- Speech-Language Therapy Department of Rehabilitation Center, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Jun Hwa Choi
- Department of Quality Improvement, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Sang-Eok Lee
- Department of Rehabilitation Medicine, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Daeyoung Hong
- Department of Neurosurgery, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| | - Mun-Chul Kim
- Department of Neurosurgery, Pohang Stroke and Spine Hospital, Pohang, Republic of Korea
| |
Collapse
|
|
44
|
Chen Z, Li T, Guo S, Zeng D, Wang K. Machine learning-based in-hospital mortality risk prediction tool for intensive care unit patients with heart failure. Front Cardiovasc Med 2023; 10:1119699. [PMID: 37077747 PMCID: PMC10106627 DOI: 10.3389/fcvm.2023.1119699] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Accepted: 03/21/2023] [Indexed: 04/05/2023] Open
Abstract
OBJECTIVE Risk stratification of patients with congestive heart failure (HF) is vital in clinical practice. The aim of this study was to construct a machine learning model to predict the in-hospital all-cause mortality for intensive care unit (ICU) patients with HF. METHODS eXtreme Gradient Boosting algorithm (XGBoost) was used to construct a new prediction model (XGBoost model) from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (training set). The eICU Collaborative Research Database dataset (eICU-CRD) was used for the external validation (test set). The XGBoost model performance was compared with a logistic regression model and an existing model (Get with the guideline-Heart Failure model) for mortality in the test set. Area under the receiver operating characteristic cure and Brier score were employed to evaluate the discrimination and the calibration of the three models. The SHapley Additive exPlanations (SHAP) value was applied to explain XGBoost model and calculate the importance of its features. RESULTS The total of 11,156 and 9,837 patients with congestive HF from the training set and test set, respectively, were included in the study. In-hospital all-cause mortality occurred in 13.3% (1,484/11,156) and 13.4% (1,319/9,837) of patients, respectively. In the training set, of 17 features with the highest predictive value were selected into the models with LASSO regression. Acute Physiology Score III (APS III), age and Sequential Organ Failure Assessment (SOFA) were strongest predictors in SHAP. In the external validation, the XGBoost model performance was superior to that of conventional risk predictive methods, with an area under the curve of 0.771 (95% confidence interval, 0.757-0.784) and a Brier score of 0.100. In the evaluation of clinical effectiveness, the machine learning model brought a positive net benefit in the threshold probability of 0%-90%, prompting evident competitiveness compare to the other two models. This model has been translated into an online calculator which is accessible freely to the public (https://nkuwangkai-app-for-mortality-prediction-app-a8mhkf.streamlit.app). CONCLUSION This study developed a valuable machine learning risk stratification tool to accurately assess and stratify the risk of in-hospital all-cause mortality in ICU patients with congestive HF. This model was translated into a web-based calculator which access freely.
Collapse
Affiliation(s)
- Zijun Chen
- Department of Cardiology, The Yongchuan Hospital of Chongqing Medical University, Chongqing, China
- Department of Cardiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Tingming Li
- Department of Cardiology, The Yongchuan Hospital of Chongqing Medical University, Chongqing, China
| | - Sheng Guo
- Department of Cardiology, The People’s Hospital of Rongchang District, Chongqing, China
| | - Deli Zeng
- Department of Cardiology, The Yongchuan Hospital of Chongqing Medical University, Chongqing, China
| | - Kai Wang
- Department of Cardiology, The Yongchuan Hospital of Chongqing Medical University, Chongqing, China
| |
Collapse
|
|
45
|
Weng S, Hu D, Chen J, Yang Y, Peng D. Prediction of Fatty Liver Disease in a Chinese Population Using Machine-Learning Algorithms. Diagnostics (Basel) 2023; 13:diagnostics13061168. [PMID: 36980476 PMCID: PMC10047083 DOI: 10.3390/diagnostics13061168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Revised: 03/13/2023] [Accepted: 03/16/2023] [Indexed: 03/30/2023] Open
Abstract
BACKGROUND Fatty liver disease (FLD) is an important risk factor for liver cancer and cardiovascular disease and can lead to significant social and economic burden. However, there is currently no nationwide epidemiological survey for FLD in China, making early FLD screening crucial for the Chinese population. Unfortunately, liver biopsy and abdominal ultrasound, the preferred methods for FLD diagnosis, are not practical for primary medical institutions. Therefore, the aim of this study was to develop machine learning (ML) models for screening individuals at high risk of FLD, and to provide a new perspective on early FLD diagnosis. METHODS This study included a total of 30,574 individuals between the ages of 18 and 70 who completed abdominal ultrasound and the related clinical examinations. Among them, 3474 individuals were diagnosed with FLD by abdominal ultrasound. We used 11 indicators to build eight classification models to predict FLD. The model prediction ability was evaluated by the area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, and kappa value. Feature importance analysis was assessed by Shapley value or root mean square error loss after permutations. RESULTS Among the eight ML models, the prediction accuracy of the extreme gradient boosting (XGBoost) model was highest at 89.77%. By feature importance analysis, we found that the body mass index, triglyceride, and alanine aminotransferase play important roles in FLD prediction. CONCLUSION XGBoost improves the efficiency and cost of large-scale FLD screening.
Collapse
Affiliation(s)
- Shuwei Weng
- Department of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha 410011, China
- Research Institute of Blood Lipid and Atherosclerosis, Central South University, Changsha 410011, China
| | - Die Hu
- Department of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha 410011, China
- Research Institute of Blood Lipid and Atherosclerosis, Central South University, Changsha 410011, China
| | - Jin Chen
- Department of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha 410011, China
- Research Institute of Blood Lipid and Atherosclerosis, Central South University, Changsha 410011, China
| | - Yanyi Yang
- Health Management Center, The Second Xiangya Hospital, Central South University, Changsha 410011, China
| | - Daoquan Peng
- Department of Cardiovascular Medicine, The Second Xiangya Hospital, Central South University, Changsha 410011, China
- Research Institute of Blood Lipid and Atherosclerosis, Central South University, Changsha 410011, China
| |
Collapse
|
|
46
|
Wang S, Zhou Y, You X, Wang B, Du L. Quantification of the antagonistic and synergistic effects of Pb 2+, Cu 2+, and Zn 2+ bioaccumulation by living Bacillus subtilis biomass using XGBoost and SHAP. JOURNAL OF HAZARDOUS MATERIALS 2023; 446:130635. [PMID: 36584648 DOI: 10.1016/j.jhazmat.2022.130635] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2022] [Revised: 11/25/2022] [Accepted: 12/17/2022] [Indexed: 06/17/2023]
Abstract
Bioaccumulation and adsorption are efficient methods for removing heavy metal ions (HMIs) from aqueous environments. However, methods to quantifiably characterize the removal selectivity for co-existing HMIs are limited. In this study, we applied Shapley additive explanations (SHAP) following extreme gradient boosting (XGBoost) modeling, to generate SHAP values. We used these values to create an affinity interference index (AII) that quantitatively represented the interference between metal ions in a multi-metal bioaccumulation system. The selectivity for simultaneous bioaccumulation of Pb2+, Cu2+, and Zn2+ by living Bacillus subtilis biomass was then characterized as a proof of concept. The AII indicated that the bioaccumulation of Zn2+ was more strongly inhibited by Pb2+/Cu2+ (AII = 1) than that of Pb2+/Cu2+ by Zn2+. Moreover, the presence of Zn2+ promoted the bioaccumulation of Pb2+ (AII = 0.39), which was confirmed in further experiments where the bioaccumulation of Pb2+ (300 μM) was increased by 38% with Zn2+ (300 μM). This study demonstrated that the combination of XGBoost and SHAP is effective in the quantifiable characterization of the antagonistic and synergistic effects in a multi-metal simultaneous bioaccumulation system. This method could also be generalized to similar tasks for analyzing the selectivity effects in a multi-component system.
Collapse
Affiliation(s)
- Sheng Wang
- Institute of Eco-Environmental Sciences, Wenzhou Academy of Agricultural Sciences, Wenzhou 325006, Zhejiang, PR China.
| | - Ying Zhou
- Institute of Eco-Environmental Sciences, Wenzhou Academy of Agricultural Sciences, Wenzhou 325006, Zhejiang, PR China
| | - Xinxin You
- Institute of Eco-Environmental Sciences, Wenzhou Academy of Agricultural Sciences, Wenzhou 325006, Zhejiang, PR China
| | - Bing Wang
- Hangzhou Center for Disease Control and Prevention, Hangzhou 310021, Zhejiang, PR China
| | - Linna Du
- College of Advanced Materials Engineering, Jiaxing Nanhu Univerisity, Jiaxing 314001, Zhejiang, PR China.
| |
Collapse
|
|
47
|
Xuan A, Chen H, Chen T, Li J, Lu S, Fan T, Zeng D, Wen Z, Ma J, Hunter D, Ding C, Zhu Z. The application of machine learning in early diagnosis of osteoarthritis: a narrative review. Ther Adv Musculoskelet Dis 2023; 15:1759720X231158198. [PMID: 36937823 PMCID: PMC10017946 DOI: 10.1177/1759720x231158198] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 02/01/2023] [Indexed: 03/16/2023] Open
Abstract
Osteoarthritis (OA) is the commonest musculoskeletal disease worldwide, with an increasing prevalence due to aging. It causes joint pain and disability, decreased quality of life, and a huge burden on healthcare services for society. However, the current main diagnostic methods are not suitable for early diagnosing patients of OA. The use of machine learning (ML) in OA diagnosis has increased dramatically in the past few years. Hence, in this review article, we describe the research progress in the application of ML in the early diagnosis of OA, discuss the current trends and limitations of ML approaches, and propose future research priorities to apply the tools in the field of OA. Accurate ML-based predictive models with imaging techniques that are sensitive to early changes in OA ahead of the emergence of clinical features are expected to address the current dilemma. The diagnostic ability of the fusion model that combines multidimensional information makes patient-specific early diagnosis and prognosis estimation of OA possible in the future.
Collapse
Affiliation(s)
- Anran Xuan
- The Second Clinical Medical School, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Haowei Chen
- The Second Clinical Medical School, Zhujiang Hospital, Southern Medical University, Guangzhou, China
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Tianyu Chen
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Jia Li
- Division of Orthopaedic Surgery, Department of Orthopaedics, Nafang Hospital, Southern Medical University, Guangzhou, China
| | - Shilong Lu
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Tianxiang Fan
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Dong Zeng
- College of Automation Science and Engineering, South China University of Technology, Guangzhou, China
| | - Zhibo Wen
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Jianhua Ma
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - David Hunter
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
- Department of Rheumatology, Royal North Shore Hospital and Institute of Bone and Joint Research, Kolling Institute, University of Sydney, Sydney, NSW, Australia
| | - Changhai Ding
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, 261 Industry Road, Guangzhou, 510280, China
- Department of Rheumatology, Guangzhou First People’s Hospital, School of Medicine, South China University of Technology, Guangzhou, China
- Department of Orthopaedics, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, China
- Menzies Institute for Medical Research, University of Tasmania, Hobart, TAS, Australia
| | - Zhaohua Zhu
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou 510280, China
| |
Collapse
|
|
48
|
Nwanosike EM, Sunter W, Ansari MA, Merchant HA, Conway B, Hasan SS. A Real-World Exploration into Clinical Outcomes of Direct Oral Anticoagulant Dosing Regimens in Morbidly Obese Patients Using Data-Driven Approaches. Am J Cardiovasc Drugs 2023; 23:287-299. [PMID: 36872389 DOI: 10.1007/s40256-023-00569-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/27/2022] [Indexed: 03/07/2023]
Abstract
INTRODUCTION The clinical outcomes of direct oral anticoagulant (DOAC) dosage regimens in morbid obesity are uncertain due to limited clinical evidence. This study seeks to bridge this evidence gap by identifying the factors associated with clinical outcomes following the dosing of DOACs in morbidly obese patients. METHOD A data-driven observational study was carried out using supervised machine learning (ML) models with a dataset extracted from electronic health records and preprocessed. Following 70%:30% partitioning of the overall dataset via stratified sampling, the selected ML classifiers (e.g., random forest, decision trees, bootstrap aggregation) were applied to the training dataset (70%). The outcomes of the models were evaluated against the test dataset (30%). Multivariate regression analysis explored the association between DOAC regimens and clinical outcomes. RESULTS A sample of 4,275 morbidly obese patients was extracted and analysed. The decision trees, random forest, and bootstrap aggregation classifiers achieved acceptable (excellent) values of precision, recall, and F1 scores in terms of their contribution to clinical outcomes. The length of stay, treatment days, and age were ranked highest for relevance to mortality and stroke. Among DOAC regimens, apixaban 2.5 mg twice daily ranked highest for its association with mortality, increasing the mortality risk by 43% (odds ratio [OR] 1.430, 95% confidence interval [CI] 1.181-1.732, p = 0.001). On the other hand, apixaban 5 mg twice daily reduced the odds of mortality by 25% (OR 0.751, 95% CI 0.632-0.905, p = 0.003) but increased the odds of stroke events. No clinically relevant non-major bleeding events occurred in this group. CONCLUSION Data-driven approaches can identify key factors associated with clinical outcomes following the dosing of DOACs in morbidly obese patients. This will help design further studies to explore well tolerated and effective DOAC doses for morbidly obese patients.
Collapse
Affiliation(s)
- Ezekwesiri Michael Nwanosike
- Department of Pharmacy, School of Applied Sciences, University of Huddersfield, Queensgate, HD1 3DH, Huddersfield, UK
| | - Wendy Sunter
- Anticoagulant Services, Calderdale and Huddersfield NHS Foundation Trust Hospital, Lindley, HD3 3EA, Huddersfield, UK
| | - Muhammad Ayub Ansari
- School of Computing and Engineering, University of Huddersfield, Queensgate, Huddersfield, HD1 3DH, West Yorkshire, UK
| | - Hamid A Merchant
- Department of Pharmacy, School of Applied Sciences, University of Huddersfield, Queensgate, HD1 3DH, Huddersfield, UK
| | - Barbara Conway
- Department of Pharmacy, School of Applied Sciences, University of Huddersfield, Queensgate, HD1 3DH, Huddersfield, UK
| | - Syed Shahzad Hasan
- Department of Pharmacy, School of Applied Sciences, University of Huddersfield, Queensgate, HD1 3DH, Huddersfield, UK.
| |
Collapse
|
|
49
|
Cai Y, Zhou T, Chen J, Cai X, Fu Y. Uncovering the role of transient receptor potential channels in pterygium: a machine learning approach. Inflamm Res 2023; 72:589-602. [PMID: 36692516 DOI: 10.1007/s00011-023-01693-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Revised: 01/04/2023] [Accepted: 01/11/2023] [Indexed: 01/25/2023] Open
Abstract
OBJECTIVES We aimed at identifying the role of transient receptor potential (TRP) channels in pterygium. METHODS Based on microarray data GSE83627 and GSE2513, differentially expressed genes (DEGs) were screened and 20 hub genes were selected. After gene correlation analysis, 5 TRP-related genes were obtained and functional analyses of gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) were performed. Multifactor regulatory network including mRNA, microRNAs (miRNAs) and transcription factors (TFs) was constructed. The 5 gene TRP signature for pterygium was validated by multiple machine learning (ML) programs including support vector classifiers (SVC), random forest (RF), and k-nearest neighbors (KNN). Additionally, we outlined the immune microenvironment and analyzed the candidate drugs. Finally, in vitro experiments were performed using human conjunctival epithelial cells (CjECs) to confirm the bioinformatics results. RESULTS Five TRP-related genes (MCOLN1, MCOLN3, TRPM3, TRPM6, and TRPM8) were validated by ML algorithms. Functional analyses revealed the participation of lysosome and TRP-regulated inflammatory pathways. A comprehensive immune infiltration landscape and TFs-miRNAs-mRNAs network was studied, which indicated several therapeutic targets (LEF1 and hsa-miR-455-3p). Through correlation analysis, MCOLN3 was proposed as the most promising immune-related biomarker. In vitro experiments further verified the reliability of our in silico results and demonstrated that the 5 TRP-related genes could influence the proliferation and proinflammatory signaling in conjunctival tissue contributing to the pathogenesis of pterygium. CONCLUSIONS Our study suggested that TRP channels played an essential role in the pathogenesis of pterygium. The identified pivotal biomarkers (especially MCOLN3) and pathways provide novel directions for future mechanistic and therapeutic studies for pterygium.
Collapse
Affiliation(s)
- Yuchen Cai
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, 639 Zhi-Zao-Ju Road, Huangpu District, Shanghai, 200011, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Tianyi Zhou
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, 639 Zhi-Zao-Ju Road, Huangpu District, Shanghai, 200011, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Jin Chen
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, 639 Zhi-Zao-Ju Road, Huangpu District, Shanghai, 200011, China
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
| | - Xueyao Cai
- Department of Plastic and Reconstructive Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, 639 Zhi-Zao-Ju Road, Huangpu District, Shanghai, 200011, China.
| | - Yao Fu
- Department of Ophthalmology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, 639 Zhi-Zao-Ju Road, Huangpu District, Shanghai, 200011, China.
- Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China.
| |
Collapse
|
|
50
|
Leung T, Harjai B, Simpson S, Du AL, Tully JL, George O, Waterman R. An Ensemble Learning Approach to Improving Prediction of Case Duration for Spine Surgery: Algorithm Development and Validation. JMIR Perioper Med 2023; 6:e39650. [PMID: 36701181 PMCID: PMC9912154 DOI: 10.2196/39650] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2022] [Revised: 11/29/2022] [Accepted: 12/25/2022] [Indexed: 12/26/2022] Open
Abstract
BACKGROUND Estimating surgical case duration accurately is an important operating room efficiency metric. Current predictive techniques in spine surgery include less sophisticated approaches such as classical multivariable statistical models. Machine learning approaches have been used to predict outcomes such as length of stay and time returning to normal work, but have not been focused on case duration. OBJECTIVE The primary objective of this 4-year, single-academic-center, retrospective study was to use an ensemble learning approach that may improve the accuracy of scheduled case duration for spine surgery. The primary outcome measure was case duration. METHODS We compared machine learning models using surgical and patient features to our institutional method, which used historic averages and surgeon adjustments as needed. We implemented multivariable linear regression, random forest, bagging, and XGBoost (Extreme Gradient Boosting) and calculated the average R2, root-mean-square error (RMSE), explained variance, and mean absolute error (MAE) using k-fold cross-validation. We then used the SHAP (Shapley Additive Explanations) explainer model to determine feature importance. RESULTS A total of 3189 patients who underwent spine surgery were included. The institution's current method of predicting case times has a very poor coefficient of determination with actual times (R2=0.213). On k-fold cross-validation, the linear regression model had an explained variance score of 0.345, an R2 of 0.34, an RMSE of 162.84 minutes, and an MAE of 127.22 minutes. Among all models, the XGBoost regressor performed the best with an explained variance score of 0.778, an R2 of 0.770, an RMSE of 92.95 minutes, and an MAE of 44.31 minutes. Based on SHAP analysis of the XGBoost regression, body mass index, spinal fusions, surgical procedure, and number of spine levels involved were the features with the most impact on the model. CONCLUSIONS Using ensemble learning-based predictive models, specifically XGBoost regression, can improve the accuracy of the estimation of spine surgery times.
Collapse
Affiliation(s)
| | - Bhavya Harjai
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, San Diego, CA, United States
| | - Sierra Simpson
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, San Diego, CA, United States
| | - Austin Liu Du
- School of Medicine, University of California, San Diego, San Diego, CA, United States
| | - Jeffrey Logan Tully
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, San Diego, CA, United States
| | - Olivier George
- Department of Psychiatry, University of California, San Diego, San Diego, CA, United States
| | - Ruth Waterman
- Department of Anesthesiology, University of California, San Diego, San Diego, CA, United States
| |
Collapse
|