1
|
Escudero-Arnanz Ó, Martínez-Agüero S, Martín-Palomeque P, G. Marques A, Mora-Jiménez I, Álvarez-Rodríguez J, Soguero-Ruiz C. Multimodal interpretable data-driven models for early prediction of multidrug resistance using multivariate time series. Health Inf Sci Syst 2025; 13:35. [PMID: 40352427 PMCID: PMC12058612 DOI: 10.1007/s13755-025-00351-9] [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: 11/24/2024] [Accepted: 04/16/2025] [Indexed: 05/14/2025] Open
Abstract
Electronic Health Records (EHRs) serve as a comprehensive repository of multimodal patient health data, combining static demographic attributes with dynamic, irregular Multivariate Time Series (MTS), characterized by varying lengths. While MTS provide critical insights for clinical predictions, their integration with static features enables a more nuanced understanding of patient health trajectories and enhances predictive accuracy. Deep Neural Networks (DNNs) have proven highly effective in capturing complex patterns in healthcare data, offering a framework for multimodal data fusion. However, their adoption in clinical practice is limited by a lack of interpretability, as transparency and explainability are essential for supporting informed medical decisions. This study presents interpretable multimodal DNN architectures for predicting and understanding the emergence of Multidrug Resistance (MDR) in Intensive Care Units (ICUs). The proposed models integrate static demographic data with temporal variables, providing a holistic view of baseline patient characteristics and health progression. To address predictive performance and interpretability challenges, we introduce a novel methodology combining feature selection techniques with attention mechanisms and post-hoc explainability tools. This approach not only reduces feature redundancy but also highlights key risk factors, thereby improving model accuracy and robustness. Experimental results demonstrate the effectiveness of the proposed framework, achieving a Receiver Operating Characteristic Area Under the Curve of 76.90 ± 3.10, a significant improvement over baseline models. Beyond MDR prediction, this methodology offers a scalable and interpretable framework for addressing various clinical challenges involving EHR data. By integrating predictive accuracy with explanatory insights-such as the identification of key risk factors-this work supports timely, evidence-based interventions to improve patient outcomes in ICU settings.
Collapse
Affiliation(s)
- Óscar Escudero-Arnanz
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| | - Sergio Martínez-Agüero
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| | - Paula Martín-Palomeque
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| | - Antonio G. Marques
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| | - Inmaculada Mora-Jiménez
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| | | | - Cristina Soguero-Ruiz
- Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain
| |
Collapse
|
2
|
Piao C, Zhu T, Baldeweg SE, Taylor P, Georgiou P, Sun J, Wang J, Li K. GARNN: An interpretable graph attentive recurrent neural network for predicting blood glucose levels via multivariate time series. Neural Netw 2025; 185:107229. [PMID: 39929068 DOI: 10.1016/j.neunet.2025.107229] [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: 02/22/2024] [Revised: 01/20/2025] [Accepted: 01/27/2025] [Indexed: 03/09/2025]
Abstract
Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with type 1 or 2 diabetes, thereby reducing complications and improving quality of life. The state of the art of BG prediction has been achieved by leveraging advanced deep learning methods to model multimodal data, i.e., sensor data and self-reported event data, organized as multi-variate time series (MTS). However, these methods are mostly regarded as "black boxes" and not entirely trusted by clinicians and patients. In this paper, we propose interpretable graph attentive recurrent neural networks (GARNNs) to model MTS, explaining variable contributions via summarizing variable importance and generating feature maps by graph attention mechanisms instead of post-hoc analysis. We evaluate GARNNs on four datasets, representing diverse clinical scenarios. Upon comparison with fifteen well-established baseline methods, GARNNs not only achieve the best prediction accuracy but also provide high-quality temporal interpretability, in particular for postprandial glucose levels as a result of corresponding meal intake and insulin injection. These findings underline the potential of GARNN as a robust tool for improving diabetes care, bridging the gap between deep learning technology and real-world healthcare solutions.
Collapse
Affiliation(s)
- Chengzhe Piao
- Institute of Health Informatics, University College London, London, NW1 2DA, UK.
| | - Taiyu Zhu
- Department of Psychiatry, University of Oxford, Oxford, OX3 7JX, UK.
| | - Stephanie E Baldeweg
- Department of Diabetes & Endocrinology, University College London Hospitals, London, NW1 2PG, UK; Centre for Obesity & Metabolism, Department of Experimental & Translational Medicine, University College London, London, WC1E 6JF, UK.
| | - Paul Taylor
- Institute of Health Informatics, University College London, London, NW1 2DA, UK.
| | - Pantelis Georgiou
- Centre for Bio-Inspired Technology, Department of Electrical and Electronic Engineering, Imperial College London, London, SW7 2AZ, UK.
| | | | - Jun Wang
- Department of Computer Science, University College London, London, WC1E 6EA, UK.
| | - Kezhi Li
- Institute of Health Informatics, University College London, London, NW1 2DA, UK.
| |
Collapse
|
3
|
Marelli C, Giacobbe DR, Limongelli A, Guastavino S, Campi C, Piana M, Bassetti M. Neural networks for the prediction of bacterial and fungal infections: current evidence and implications. J Chemother 2025:1-28. [PMID: 40285636 DOI: 10.1080/1120009x.2025.2492960] [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: 11/25/2024] [Revised: 02/26/2025] [Accepted: 03/21/2025] [Indexed: 04/29/2025]
Abstract
In the present narrative review, we discuss the use of artificial neural networks (ANNs) for predicting bacterial and fungal infections based on commonly available clinical and laboratory data, focusing on promises and challenges of these machine learning models. For predicting different bacterial or fungal infections from data commonly found in electronical medical records, ANN models may reach, based on current literature, an acceptable performance for discriminating between infected and non-infected patients, and outperformed other machine learning (ML)-based models in 38.3% of the retrieved studies evaluating at least another ML approach. In the near future, as for other ML models, the use of ANNs could be leveraged to provide real-time support to clinicians in clinical decision-making processes, although further research is needed in terms of quality of data and explainability of ANN model predictions to better understand whether and how these techniques can be safely adopted in everyday clinical practice.
Collapse
Affiliation(s)
- Cristina Marelli
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Daniele Roberto Giacobbe
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Alessandro Limongelli
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | | | - Cristina Campi
- Department of Mathematics (DIMA), University of Genoa, Genoa, Italy
- Life Science Computational Laboratory (LISCOMP), IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Michele Piana
- Department of Mathematics (DIMA), University of Genoa, Genoa, Italy
- Life Science Computational Laboratory (LISCOMP), IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Matteo Bassetti
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| |
Collapse
|
4
|
Huang X, Qin M, Fang M, Wang Z, Hu C, Zhao T, Qin Z, Zhu H, Wu L, Yu G, De Cobelli F, Xie X, Palumbo D, Tian J, Dong D. The application of artificial intelligence in upper gastrointestinal cancers. JOURNAL OF THE NATIONAL CANCER CENTER 2025; 5:113-131. [PMID: 40265096 PMCID: PMC12010392 DOI: 10.1016/j.jncc.2024.12.006] [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: 06/13/2024] [Revised: 09/17/2024] [Accepted: 12/20/2024] [Indexed: 04/24/2025] Open
Abstract
Upper gastrointestinal cancers, mainly comprising esophageal and gastric cancers, are among the most prevalent cancers worldwide. There are many new cases of upper gastrointestinal cancers annually, and the survival rate tends to be low. Therefore, timely screening, precise diagnosis, appropriate treatment strategies, and effective prognosis are crucial for patients with upper gastrointestinal cancers. In recent years, an increasing number of studies suggest that artificial intelligence (AI) technology can effectively address clinical tasks related to upper gastrointestinal cancers. These studies mainly focus on four aspects: screening, diagnosis, treatment, and prognosis. In this review, we focus on the application of AI technology in clinical tasks related to upper gastrointestinal cancers. Firstly, the basic application pipelines of radiomics and deep learning in medical image analysis were introduced. Furthermore, we separately reviewed the application of AI technology in the aforementioned aspects for both esophageal and gastric cancers. Finally, the current limitations and challenges faced in the field of upper gastrointestinal cancers were summarized, and explorations were conducted on the selection of AI algorithms in various scenarios, the popularization of early screening, the clinical applications of AI, and large multimodal models.
Collapse
Affiliation(s)
- Xiaoying Huang
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Minghao Qin
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
- University of Science and Technology Beijing, Beijing, China
| | - Mengjie Fang
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Zipei Wang
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Chaoen Hu
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| | - Tongyu Zhao
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
- University of Science and Technology of China, Hefei, China
| | - Zhuyuan Qin
- Beijing Institute of Genomics, Chinese Academy of Sciences, Beijing, China
- Beijing University of Chinese Medicine, Beijing, China
| | | | - Ling Wu
- KiangWu Hospital, Macau, China
| | | | | | | | - Diego Palumbo
- Department of Radiology, IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Jie Tian
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, China
- Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology, Beijing, China
| | - Di Dong
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
| |
Collapse
|
5
|
Thiele D, Rodseth R, Friedland R, Berger F, Mathew C, Maslo C, Moll V, Leithner C, Storm C, Krannich A, Nee J. Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units-A Novel Approach to the Early Identification of High-Risk Patients. J Clin Med 2025; 14:350. [PMID: 39860355 PMCID: PMC11766095 DOI: 10.3390/jcm14020350] [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: 10/18/2024] [Revised: 11/12/2024] [Accepted: 12/20/2024] [Indexed: 01/27/2025] Open
Abstract
Background Predictive machine learning models have made use of a variety of scoring systems to identify clinical deterioration in ICU patients. However, most of these scores include variables that are dependent on medical staff examining the patient. We present the development of a real-time prediction model using clinical variables that are digital and automatically generated for the early detection of patients at risk of deterioration. Methods Routine monitoring data were used in this analysis. ICU patients with at least 24 h of vital sign recordings were included. Deterioration was defined as qSOFA ≥ 2. Model development and validation were performed internally by splitting the cohort into training and test datasets and validating the results on the test dataset. Five different models were trained, tested, and compared against each other. The models were an artificial neural network (ANN), a random forest (RF), a support vector machine (SVM), a linear discriminant analysis (LDA), and a logistic regression (LR). Results In total, 7156 ICU patients were screened for inclusion in the study, which resulted in models trained from a total of 28,348 longitudinal measurements. The artificial neural network showed a superior predictive performance for deterioration, with an area under the curve of 0.81 over 0.78 (RF), 0.78 (SVM), 0.77 (LDA), and 0.76 (LR), by using only four vital parameters. The sensitivity was higher than the specificity for the artificial neural network. Conclusions The artificial neural network, only using four automatically recorded vital signs, was best able to predict deterioration, 10 h before documentation in clinical records. This real-time prediction model has the potential to flag at-risk patients to the healthcare providers treating them, for closer monitoring and further investigation.
Collapse
Affiliation(s)
- Dominik Thiele
- Department of Neurology and Experimental Neurology, Charité—Universitätsmedizin Berlin, 10117 Berlin, Germany
- TCC Analytics, Telehealth Competence Center (TCC) GmbH, 22083 Hamburg, Germany
| | - Reitze Rodseth
- Netcare Limited, Johannesburg 2196, South Africa
- Department of Anaesthesiology and Critical Care, University of KwaZulu-Natal, Durban 4001, South Africa
| | | | | | - Chris Mathew
- Netcare Limited, Johannesburg 2196, South Africa
| | | | - Vanessa Moll
- Department of Anesthesiology, Division of Critical Care Medicine, University of Minnesota School of Medicine, Minneapolis, MN 55455, USA
- Department of Anesthesiology, Division of Critical Care Medicine, Emory University School of Medicine, Atlanta, GA 30322, USA
| | - Christoph Leithner
- Department of Neurology and Experimental Neurology, Charité—Universitätsmedizin Berlin, 10117 Berlin, Germany
| | - Christian Storm
- TCC Analytics, Telehealth Competence Center (TCC) GmbH, 22083 Hamburg, Germany
- Department of Nephrology and Medical Intensive Care, Charité—Universitätsmedizin Berlin, 22083 Berlin, Germany
| | - Alexander Krannich
- TCC Analytics, Telehealth Competence Center (TCC) GmbH, 22083 Hamburg, Germany
- Experimental and Clinical Research Center (ECRC), Charité—Universitätsmedizin Berlin, 22083 Berlin, Germany
| | - Jens Nee
- Department of Nephrology and Medical Intensive Care, Charité—Universitätsmedizin Berlin, 22083 Berlin, Germany
| |
Collapse
|
6
|
Qureshi M, Ishaq K, Daniyal M, Iftikhar H, Rehman MZ, Salar SAA. Forecasting cardiovascular disease mortality using artificial neural networks in Sindh, Pakistan. BMC Public Health 2025; 25:34. [PMID: 39754102 PMCID: PMC11699765 DOI: 10.1186/s12889-024-21187-0] [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: 05/10/2024] [Accepted: 12/23/2024] [Indexed: 01/06/2025] Open
Abstract
Cardiovascular disease (CVD) is a leading cause of death and disability worldwide, and its incidence and prevalence are increasing in many countries. Modeling of CVD plays a crucial role in understanding the trend of CVD death cases, evaluating the effectiveness of interventions, and predicting future disease trends. This study aims to investigate the modeling and forecasting of CVD mortality, specifically in the Sindh province of Pakistan. The civil hospital in the Nawabshah area of Sindh province, Pakistan, provided the data set used in this study. It is a time series dataset with actual cardiovascular disease (CVD) mortality cases from 1999 to 2021 included. This study analyzes and forecasts the CVD deaths in the Sindh province of Pakistan using classical time series models, including Naïve, Holt-Winters, and Simple Exponential Smoothing (SES), which have been adopted and compared with a machine learning approach called the Artificial Neural Network Auto-Regressive (ANNAR) model. The performance of both the classical time series models and the ANNAR model has been evaluated using key performance indicators such as Root Mean Square Deviation Error, Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). After comparing the results, it was found that the ANNAR model outperformed all the selected models, demonstrating its effectiveness in predicting CVD mortality and quantifying future disease burden in the Sindh province of Pakistan. The study concludes that the ANNAR model is the best-selected model among the competing models for predicting CVD mortality in the Sindh province. This model provides valuable insights into the impact of interventions aimed at reducing CVD and can assist in formulating health policies and allocating economic resources. By accurately forecasting CVD mortality, policymakers can make informed decisions to address this public health issue effectively.
Collapse
Affiliation(s)
- Moiz Qureshi
- Govt Degree College TangoJam, Hyderabad 70060, Sindh, Pakistan
- Department of Statistics, Quaid-i-Azam University, 45320, Islamabad, Pakistan
| | - Khushboo Ishaq
- Ibn-e-Sina Medical University Mirpurkhas, Sindh, Pakistan
| | - Muhammad Daniyal
- Department of Statistics, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, Pakistan
| | - Hasnain Iftikhar
- Department of Statistics, Quaid-i-Azam University, 45320, Islamabad, Pakistan.
- Al-Barkaat Institute of Management Studies, Aligarh 202122, Dr. A. P. J. Abdul Kalam Technical University, Lucknow 226010, India.
| | - Mohd Ziaur Rehman
- Department of Finance, College of Business Administration, King Saud University, P.O. Box 71115, Riyadh, 11587, Saudi Arabia
| | - S A Atif Salar
- Al-Barkaat Institute of Management Studies, Aligarh 202122, Dr. A. P. J. Abdul Kalam Technical University, Lucknow 226010, India
| |
Collapse
|
7
|
Song Q, Sun S, Song Q, Wang B, Liu Z, Jiang H. A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition. Sci Rep 2025; 15:101. [PMID: 39747222 PMCID: PMC11697173 DOI: 10.1038/s41598-024-83604-z] [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: 10/30/2024] [Accepted: 12/16/2024] [Indexed: 01/04/2025] Open
Abstract
Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that make it difficult to meet the needs of industrial applications. To realize accurate recognition of coal-gangue in noisy environments, this paper proposes an end-to-end multi-scale feature fusion convolutional neural network (MCNN-BILSTM) based gangue recognition method, which can automatically learn and fuse complementary information from multiple signal components of vibration signals. It combines traditional filtering methods and the idea of multi-scale learning, which can expand the breadth and depth of the feature learning process. the breadth and depth of the feature learning process. Moreover, to strengthen the expression of key features, a feature weighting method based on the attention mechanism is combined to give adaptive weights to different features. Finally, the experimental platform of a tail beam of coal-gangue impact hydraulic support is built, and several comparative experiments are carried out. The comprehensive comparison experiments show that the method shows strong adaptability, robustness, and noise resistance under various complex noise environments, and is suitable for complex practical industrial sites.
Collapse
Affiliation(s)
- Qingjun Song
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China
| | - Shirong Sun
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China
| | - Qinghui Song
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China
| | - Bingrui Wang
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China
| | - Zihao Liu
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China
| | - Haiyan Jiang
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, 271000, Shandong, China.
| |
Collapse
|
8
|
Ruiz‐Mateos Serrano R, Farina D, Malliaras GG. Body Surface Potential Mapping: A Perspective on High-Density Cutaneous Electrophysiology. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2025; 12:e2411087. [PMID: 39679757 PMCID: PMC11775574 DOI: 10.1002/advs.202411087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/10/2024] [Revised: 10/28/2024] [Indexed: 12/17/2024]
Abstract
The electrophysiological signals recorded by cutaneous electrodes, known as body surface potentials (BSPs), are widely employed biomarkers in medical diagnosis. Despite their widespread application and success in detecting various conditions, the poor spatial resolution of traditional BSP measurements poses a limit to their diagnostic potential. Advancements in the field of bioelectronics have facilitated the creation of compact, high-quality, high-density recording arrays for cutaneous electrophysiology, allowing detailed spatial information acquisition as BSP maps (BSPMs). Currently, the design of electrode arrays for BSP mapping lacks a standardized framework, leading to customizations for each clinical study, limiting comparability, reproducibility, and transferability. This perspective proposes preliminary design guidelines, drawn from existing literature, rooted solely in the physical properties of electrophysiological signals and mathematical principles of signal processing. These guidelines aim to simplify and generalize the optimization process for electrode array design, fostering more effective and applicable clinical research. Moreover, the increased spatial information obtained from BSPMs introduces interpretation challenges. To mitigate this, two strategies are outlined: observational transformations that reconstruct signal sources for intuitive comprehension, and machine learning-driven diagnostics. BSP mapping offers significant advantages in cutaneous electrophysiology with respect to classic electrophysiological recordings and is expected to expand into broader clinical domains in the future.
Collapse
Affiliation(s)
| | - Dario Farina
- Department of BioengineeringFaculty of Engineering, Imperial College LondonLondonW12 7TAUK
| | - George G. Malliaras
- Electrical Engineering Division, Department of EngineeringUniversity of CambridgeCambridgeCB3 0FAUK
| |
Collapse
|
9
|
Prithula J, Islam KR, Kumar J, Tan TL, Reaz MBI, Rahman T, Zughaier SM, Khan MS, Murugappan M, Chowdhury MEH. A novel classical machine learning framework for early sepsis prediction using electronic health record data from ICU patients. Comput Biol Med 2025; 184:109284. [PMID: 39579661 DOI: 10.1016/j.compbiomed.2024.109284] [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: 04/26/2024] [Revised: 10/01/2024] [Accepted: 10/14/2024] [Indexed: 11/25/2024]
Abstract
Sepsis, a life-threatening condition triggered by the body's response to infection, remains a significant global health challenge, annually affecting millions in the United States alone with substantial mortality and healthcare costs. Early prediction of sepsis is critical for timely intervention and improved patient outcomes. This study introduces an innovative predictive model leveraging machine learning techniques and a specific data-splitting approach on highly imbalanced electronic health records (EHRs). Using PhysioNet/CinC Challenge 2019 data from 40,336 patients, including vital signs, lab values, and demographics. Preliminary assessments using classical and stacked ML models with Synthetic Minority Oversampling Technique (SMOTE) augmentation were conducted, showing improved performance. It is found that stacking ML models enhances overall accuracy but faces limitations in precision, recall, and F1 score for positive class prediction. A novel data-splitting approach with 5-fold cross-validation and SMOTE and COPULA augmentation techniques demonstrated promise, with F1 scores ranging from 93 % to 94 % using the COPULA technique. COPULA excelled at predictions for different hours' onsets compared to the SMOTE technique. The proposed model outperformed existing studies, suggesting clinical viability for early sepsis prediction.
Collapse
Affiliation(s)
- Johayra Prithula
- Department of Electrical and Electronics Engineering, University of Dhaka, Dhaka, 1000, Bangladesh
| | - Khandaker Reajul Islam
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur, 56000, Malaysia
| | - Jaya Kumar
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur, 56000, Malaysia
| | - Toh Leong Tan
- Department of Emergency Medicine, Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur, 56000, Malaysia
| | - Mamun Bin Ibne Reaz
- Department of Electrical and Electronic Engineering, Independent University, Bangladesh, Bashundhara, Dhaka, Bangladesh
| | - Tawsifur Rahman
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Susu M Zughaier
- Department of Basic Medical Sciences, College of Medicine, QU Health, Qatar University, Doha, 2713, Qatar
| | | | - M Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha, Kuwait; Department of Electronics and Communication Engineering, Vels Institute of Sciences, Technology, and Advanced Studies, Chennai, Tamilnadu, India.
| | | |
Collapse
|
10
|
Fang S, Jin H, Zhang J, Wang Y, Nan W, Feng Y, Su W, Jiang X. Machine learning for predicting acute myocardial infarction in patients with sepsis. Sci Rep 2024; 14:30629. [PMID: 39719483 DOI: 10.1038/s41598-024-80575-z] [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: 06/03/2024] [Accepted: 11/19/2024] [Indexed: 12/26/2024] Open
Abstract
Acute myocardial infarction (AMI) and sepsis are the leading causes of high mortality rates in intensive care units. While sepsis frequently affects the cardiovascular system, distinguishing between sepsis-induced cardiomyopathy and AMI remains challenging due to overlapping biomarkers. Misdiagnosis can hinder timely treatment and increase risk of complications. This study used multidimensional clinical data and machine learning techniques to develop and validate a novel predictive model for identifying AMI in critically ill patients with sepsis. Data from patients with sepsis were extracted from the Medical Information Mart for Intensive Care-IV database. Six machine learning algorithms were employed for model construction. Additionally, the machine learning-based models were compared with traditional scoring systems. Model performance was evaluated in terms of discrimination, calibration, and clinical applicability. In total, 2,103 critically ill patients with sepsis were included, 459 (21.8%) of whom experienced AMI during hospitalization. A total of 26 variables were selected for model construction. Among all models, the Gradient Boosting Classifier model demonstrated the best predictive performance in terms of discrimination, calibration, and clinical applicability. Machine learning models have the potential to serve as tools for predicting AMI in patients with sepsis. The Gradient Boosting Classifier model developed herein demonstrated promising predictive performance, supporting clinicians in identifying patients at high-risk of sepsis and implementing early interventions to reduce mortality rates.
Collapse
Affiliation(s)
- Shusheng Fang
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Hongjin Jin
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Jiayu Zhang
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Yali Wang
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Wenyu Nan
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Yanhao Feng
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Wen Su
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China
| | - Xiaodong Jiang
- Department of Critical Care Medicine, The Second Hospital of Dalian Medical University, Dalian Medical University, Dalian, 116000, Liaoning, China.
| |
Collapse
|
11
|
Li Q, Li D, Jiao H, Wu Z, Nie W. CISepsis: a causal inference framework for early sepsis detection. Front Cell Infect Microbiol 2024; 14:1488130. [PMID: 39679198 PMCID: PMC11638194 DOI: 10.3389/fcimb.2024.1488130] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2024] [Accepted: 10/28/2024] [Indexed: 12/17/2024] Open
Abstract
Introduction The early prediction of sepsis based on machine learning or deep learning has achieved good results.Most of the methods use structured data stored in electronic medical records, but the pathological characteristics of sepsis involve complex interactions between multiple physiological systems and signaling pathways, resulting in mixed structured data. Some researchers will introduce unstructured data when also introduce confounders. These confounders mask the direct causality of sepsis, leading the model to learn misleading correlations. Finally, it affects the generalization ability, robustness, and interpretability of the model. Methods To address this challenge, we propose an early sepsis prediction approach based on causal inference which can remove confounding effects and capture causal relationships. First, we analyze the relationship between each type of observation, confounder, and label to create a causal structure diagram. To eliminate the effects of different confounders separately, the methods of back-door adjustment and instrumental variable are used. Specifically, we learn the confounder and an instrumental variable based on mutual information from various observed data and eliminate the influence of the confounder by optimizing mutual information. We use back-door adjustment to eliminate the influence of confounders in clinical notes and static indicators on the true causal effect. Results Our method, named CISepsis, was validated on the MIMIC-IV dataset. Compared to existing state-of-the-art early sepsis prediction models such as XGBoost, LSTM, and MGP-AttTCN, our method demonstrated a significant improvement in AUC. Specifically, our model achieved AUC values of 0.921, 0.920, 0.919, 0.923, 0.924, 0.926, and 0.926 at the 6, 5, 4, 3, 2, 1, and 0 time points, respectively. Furthermore, the effectiveness of our method was confirmed through ablation experiments. Discussion Our method, based on causal inference, effectively removes the influence of confounding factors, significantly improving the predictive accuracy of the model. Compared to traditional methods, this adjustment allows for a more accurate capture of the true causal effects of sepsis, thereby enhancing the model's generalizability, robustness, and interpretability. Future research will explore the impact of specific indicators or treatment interventions on sepsis using counterfactual adjustments in causal inference, as well as investigate the potential clinical application of our method.
Collapse
Affiliation(s)
- Qiang Li
- School of Microelectronics, Tianjin University, Tianjin, China
| | - Dongchen Li
- School of Microelectronics, Tianjin University, Tianjin, China
| | - He Jiao
- School of Pharmaceutical Science and Technology, Tianjin University, Tianjin, China
| | - Zhenhua Wu
- Department of Cardiovascular Surgery Intensive Care Unit, Tianjin Chest Hospital, Tianjin, China
| | - Weizhi Nie
- School of Electrical and Information Engineering, Tianjin University, Tianjin, China
| |
Collapse
|
12
|
Akabane S, Asamoto M, Azuma S, Otsuji M, Uchida K. Assessment of the relationship between central venous pressure waveform and the severity of tricuspid valve regurgitation using data science. Sci Rep 2024; 14:24839. [PMID: 39438502 PMCID: PMC11496678 DOI: 10.1038/s41598-024-74890-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2024] [Accepted: 09/30/2024] [Indexed: 10/25/2024] Open
Abstract
Purpose The relationship between the height of the V wave in the central venous pressure (CVP) waveform and the severity of tricuspid regurgitation (TR) is well known. Their diagnostic ability is unconfirmed. This study explored CVP waveform variations with TR. Methods All patients who underwent preoperative echocardiography and CVP waveform measurements before surgery at our institution were included. Indices were created to capture each feature of the CVP waveform. The median value for each case was obtained and statistically analyzed according to the severity of TR. A deep learning technique, Transformer, was used to handle the complex features of CVP waveforms. Results This study included 436 cases. The values for C wave - Y descent, X descent - Y descent, and V wave - Y descent differed significantly in the Jonckheere-Terpstra test (p = 0.0018, 0.027, and 0.077, respectively). The area under the receiver operating characteristic (ROC) curve (AUC) for X descent - Y descent in two groups, none to moderate TR and severe TR, was 0.83 (95% confidence interval (CI) [0.68, 0.98]). For Transformer, the accuracy of the validation dataset was 0.97. Conclusions The shape of the CVP waveform varied with the severity of TR in a large dataset.
Collapse
Affiliation(s)
- Shinichi Akabane
- Department of Anesthesiology and Pain Relief Center, The University of Tokyo Hospital, Tokyo, Japan
| | - Masaaki Asamoto
- Department of Anesthesiology and Pain Relief Center, The University of Tokyo Hospital, Tokyo, Japan.
| | - Seiichi Azuma
- Department of Anesthesiology and Pain Relief Center, The University of Tokyo Hospital, Tokyo, Japan
| | - Mikiya Otsuji
- Department of Anesthesiology, Tokyo Teishin Hospital, Tokyo, Japan
| | - Kanji Uchida
- Department of Anesthesiology and Pain Relief Center, The University of Tokyo Hospital, Tokyo, Japan
| |
Collapse
|
13
|
Yadgarov MY, Landoni G, Berikashvili LB, Polyakov PA, Kadantseva KK, Smirnova AV, Kuznetsov IV, Shemetova MM, Yakovlev AA, Likhvantsev VV. Early detection of sepsis using machine learning algorithms: a systematic review and network meta-analysis. Front Med (Lausanne) 2024; 11:1491358. [PMID: 39478824 PMCID: PMC11523135 DOI: 10.3389/fmed.2024.1491358] [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: 09/04/2024] [Accepted: 10/08/2024] [Indexed: 11/02/2024] Open
Abstract
Background With machine learning (ML) carving a niche in diverse medical disciplines, its role in sepsis prediction, a condition where the 'golden hour' is critical, is of paramount interest. This study assesses the factors influencing the efficacy of ML models in sepsis prediction, aiming to optimize their use in clinical practice. Methods We searched Medline, PubMed, Google Scholar, and CENTRAL for studies published from inception to October 2023. We focused on studies predicting sepsis in real-time settings in adult patients in any hospital settings without language limits. The primary outcome was area under the curve (AUC) of the receiver operating characteristic. This meta-analysis was conducted according to PRISMA-NMA guidelines and Cochrane Handbook recommendations. A Network Meta-Analysis using the CINeMA approach compared ML models against traditional scoring systems, with meta-regression identifying factors affecting model quality. Results From 3,953 studies, 73 articles encompassing 457,932 septic patients and 256 models were analyzed. The pooled AUC for ML models was 0.825 and it significantly outperformed traditional scoring systems. Neural Network and Decision Tree models demonstrated the highest AUC metrics. Significant factors influencing AUC included ML model type, dataset type, and prediction window. Conclusion This study establishes the superiority of ML models, especially Neural Network and Decision Tree types, in sepsis prediction. It highlights the importance of model type and dataset characteristics for prediction accuracy, emphasizing the necessity for standardized reporting and validation in ML healthcare applications. These findings call for broader clinical implementation to evaluate the effectiveness of these models in diverse patient groups. Systematic review registration https://inplasy.com/inplasy-2023-12-0062/, identifier, INPLASY2023120062.
Collapse
Affiliation(s)
- Mikhail Ya Yadgarov
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Giovanni Landoni
- Department of Anaesthesia and Intensive Care, IRCCS San Raffaele Scientific Institute, Milan, Italy
- Department of Anesthesiology, Vita-Salute San Raffaele University, Milan, Italy
| | - Levan B. Berikashvili
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Petr A. Polyakov
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Kristina K. Kadantseva
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Anastasia V. Smirnova
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Ivan V. Kuznetsov
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Maria M. Shemetova
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Alexey A. Yakovlev
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
| | - Valery V. Likhvantsev
- Federal Research and Clinical Centre of Intensive Care Medicine and Rehabilitology, Moscow, Russia
- Department of Anesthesiology, I.M. Sechenov First Moscow State Medical University, Moscow, Russia
| |
Collapse
|
14
|
Yang M, Peng Z, van Pul C, Andriessen P, Dong K, Silvertand D, Li J, Liu C, Long X. Continuous prediction and clinical alarm management of late-onset sepsis in preterm infants using vital signs from a patient monitor. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 255:108335. [PMID: 39047574 DOI: 10.1016/j.cmpb.2024.108335] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/11/2024] [Revised: 06/14/2024] [Accepted: 07/17/2024] [Indexed: 07/27/2024]
Abstract
BACKGROUND AND OBJECTIVE Continuous prediction of late-onset sepsis (LOS) could be helpful for improving clinical outcomes in neonatal intensive care units (NICU). This study aimed to develop an artificial intelligence (AI) model for assisting the bedside clinicians in successfully identifying infants at risk for LOS using non-invasive vital signs monitoring. METHODS In a retrospective study from the NICU of the Máxima Medical Center in Veldhoven, the Netherlands, a total of 492 preterm infants less than 32 weeks gestation were included between July 2016 and December 2018. Data on heart rate (HR), respiratory rate (RR), and oxygen saturation (SpO2) at 1 Hz were extracted from the patient monitor. We developed multiple AI models using 102 extracted features or raw time series to provide hourly LOS risk prediction. Shapley values were used to explain the model. For the best performing model, the effect of different vital signs and also the input type of signals on model performance was tested. To further assess the performance of applying the best performing model in a real-world clinical setting, we performed a simulation using four different alarm policies on continuous real-time predictions starting from three days after birth. RESULTS A total of 51 LOS patients and 68 controls were finally included according to the patient inclusion and exclusion criteria. When tested by seven-fold cross-validations, the mean (standard deviation) area under the receiver operating characteristic curve (AUC) six hours before CRASH was 0.875 (0.072) for the best performing model, compared to the other six models with AUC ranging from 0.782 (0.089) to 0.846 (0.083). The best performing model performed only slightly worse than the model learning from raw physiological waveforms (0.886 [0.068]), successfully detecting 96.1 % of LOS patients before CRASH. When setting the expected alarm window to 24 h and using a multi-threshold alarm policy, the sensitivity metric was 71.6 %, while the positive predictive value was 9.9 %, resulting in an average of 1.15 alarms per day per patient. CONCLUSIONS The proposed AI model, which learns from routinely collected vital signs, has the potential to assist clinicians in the early detection of LOS. Combined with interpretability and clinical alarm management, this model could be better translated into medical practice for future clinical implementation.
Collapse
Affiliation(s)
- Meicheng Yang
- State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China; Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Zheng Peng
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Department of Clinical Physics, Máxima Medical Centre, Veldhoven, the Netherlands
| | - Carola van Pul
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Department of Clinical Physics, Máxima Medical Centre, Veldhoven, the Netherlands; Department of Applied Physics, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Peter Andriessen
- Department of Applied Physics, Eindhoven University of Technology, Eindhoven, the Netherlands; Department of Pediatrics, Máxima Medical Centre, Veldhoven, the Netherlands
| | - Kejun Dong
- Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, United States of America
| | - Demi Silvertand
- Department of Pediatrics, Máxima Medical Centre, Veldhoven, the Netherlands
| | - Jianqing Li
- State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China; School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China
| | - Chengyu Liu
- State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China
| | - Xi Long
- Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
| |
Collapse
|
15
|
Gao C, Yin S, Wang H, Wang Z, Du Z, Li X. Medical-Knowledge-Based Graph Neural Network for Medication Combination Prediction. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:13246-13257. [PMID: 37141055 DOI: 10.1109/tnnls.2023.3266490] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
Medication combination prediction (MCP) can provide assistance for experts in the more thorough comprehension of complex mechanisms behind health and disease. Many recent studies focus on the patient representation from the historical medical records, but neglect the value of the medical knowledge, such as the prior knowledge and the medication knowledge. This article develops a medical-knowledge-based graph neural network (MK-GNN) model which incorporates the representation of patients and the medical knowledge into the neural network. More specifically, the features of patients are extracted from their medical records in different feature subspaces. Then these features are concatenated to obtain the feature representation of patients. The prior knowledge, which is calculated according to the mapping relationship between medications and diagnoses, provides heuristic medication features according to the diagnosis results. Such medication features can help the MK-GNN model learn optimal parameters. Moreover, the medication relationship in prescriptions is formulated as a drug network to integrate the medication knowledge into medication representation vectors. The results reveal the superior performance of the MK-GNN model compared with the state-of-the-art baselines on different evaluation metrics. The case study manifests the application potential of the MK-GNN model.
Collapse
|
16
|
Giacobbe DR, Marelli C, Guastavino S, Signori A, Mora S, Rosso N, Campi C, Piana M, Murgia Y, Giacomini M, Bassetti M. Artificial intelligence and prescription of antibiotic therapy: present and future. Expert Rev Anti Infect Ther 2024; 22:819-833. [PMID: 39155449 DOI: 10.1080/14787210.2024.2386669] [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: 05/20/2024] [Accepted: 07/28/2024] [Indexed: 08/20/2024]
Abstract
INTRODUCTION In the past few years, the use of artificial intelligence in healthcare has grown exponentially. Prescription of antibiotics is not exempt from its rapid diffusion, and various machine learning (ML) techniques, from logistic regression to deep neural networks and large language models, have been explored in the literature to support decisions regarding antibiotic prescription. AREAS COVERED In this narrative review, we discuss promises and challenges of the application of ML-based clinical decision support systems (ML-CDSSs) for antibiotic prescription. A search was conducted in PubMed up to April 2024. EXPERT OPINION Prescribing antibiotics is a complex process involving various dynamic phases. In each of these phases, the support of ML-CDSSs has shown the potential, and also the actual ability in some studies, to favorably impacting relevant clinical outcomes. Nonetheless, before widely exploiting this massive potential, there are still crucial challenges ahead that are being intensively investigated, pertaining to the transparency of training data, the definition of the sufficient degree of prediction explanations when predictions are obtained through black box models, and the legal and ethical framework for decision responsibility whenever an antibiotic prescription is supported by ML-CDSSs.
Collapse
Affiliation(s)
- Daniele Roberto Giacobbe
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Cristina Marelli
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | | | - Alessio Signori
- Section of Biostatistics, Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
| | - Sara Mora
- UO Information and Communication Technologies, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Nicola Rosso
- UO Information and Communication Technologies, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Cristina Campi
- Department of Mathematics (DIMA), University of Genoa, Genoa, Italy
- Life Science Computational Laboratory (LISCOMP), IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Michele Piana
- Department of Mathematics (DIMA), University of Genoa, Genoa, Italy
- Life Science Computational Laboratory (LISCOMP), IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Ylenia Murgia
- Department of Informatics, Bioengineering, Robotics and System Engineering (DIBRIS), University of Genoa, Genoa, Italy
| | - Mauro Giacomini
- Department of Informatics, Bioengineering, Robotics and System Engineering (DIBRIS), University of Genoa, Genoa, Italy
| | - Matteo Bassetti
- Department of Health Sciences (DISSAL), University of Genoa, Genoa, Italy
- UO Clinica Malattie Infettive, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| |
Collapse
|
17
|
Chiu CC, Wu CM, Chien TN, Kao LJ, Li C. Predicting ICU Readmission from Electronic Health Records via BERTopic with Long Short Term Memory Network Approach. J Clin Med 2024; 13:5503. [PMID: 39336990 PMCID: PMC11432694 DOI: 10.3390/jcm13185503] [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: 07/25/2024] [Revised: 09/04/2024] [Accepted: 09/10/2024] [Indexed: 09/30/2024] Open
Abstract
Background: The increasing rate of intensive care unit (ICU) readmissions poses significant challenges in healthcare, impacting both costs and patient outcomes. Predicting patient readmission after discharge is crucial for improving medical quality and reducing expenses. Traditional analyses of electronic health record (EHR) data have primarily focused on numerical data, often neglecting valuable text data. Methods: This study employs a hybrid model combining BERTopic and Long Short-Term Memory (LSTM) networks to predict ICU readmissions. Leveraging the MIMIC-III database, we utilize both quantitative and text data to enhance predictive capabilities. Our approach integrates the strengths of unsupervised topic modeling with supervised deep learning, extracting potential topics from patient records and transforming discharge summaries into topic vectors for more interpretable and personalized predictions. Results: Utilizing a comprehensive dataset of 36,232 ICU patient records, our model achieved an AUROC score of 0.80, thereby surpassing the performance of traditional machine learning models. The implementation of BERTopic facilitated effective utilization of unstructured data, generating themes that effectively guide the selection of relevant predictive factors for patient readmission prognosis. This significantly enhanced the model's interpretative accuracy and predictive capability. Additionally, the integration of importance ranking methods into our machine learning framework allowed for an in-depth analysis of the significance of various variables. This approach provided crucial insights into how different input variables interact and impact predictions of patient readmission across various clinical contexts. Conclusions: The practical application of BERTopic technology in our hybrid model contributes to more efficient patient management and serves as a valuable tool for developing tailored treatment strategies and resource optimization. This study highlights the significance of integrating unstructured text data with traditional quantitative data to develop more accurate and interpretable predictive models in healthcare, emphasizing the importance of individualized care and cost-effective healthcare paradigms.
Collapse
Affiliation(s)
- Chih-Chou Chiu
- Department of Business Management, National Taipei University of Technology, Taipei 106, Taiwan; (C.-C.C.); (C.-M.W.); (L.-J.K.)
| | - Chung-Min Wu
- Department of Business Management, National Taipei University of Technology, Taipei 106, Taiwan; (C.-C.C.); (C.-M.W.); (L.-J.K.)
| | - Te-Nien Chien
- College of Management, National Taipei University of Technology, Taipei 106, Taiwan;
| | - Ling-Jing Kao
- Department of Business Management, National Taipei University of Technology, Taipei 106, Taiwan; (C.-C.C.); (C.-M.W.); (L.-J.K.)
| | - Chengcheng Li
- College of Management, National Taipei University of Technology, Taipei 106, Taiwan;
| |
Collapse
|
18
|
Marullo G, Ulrich L, Antonaci FG, Audisio A, Aprato A, Massè A, Vezzetti E. Classification of AO/OTA 31A/B femur fractures in X-ray images using YOLOv8 and advanced data augmentation techniques. Bone Rep 2024; 22:101801. [PMID: 39324016 PMCID: PMC11422035 DOI: 10.1016/j.bonr.2024.101801] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/26/2024] [Revised: 08/20/2024] [Accepted: 09/05/2024] [Indexed: 09/27/2024] Open
Abstract
Femur fractures are a significant worldwide public health concern that affects patients as well as their families because of their high frequency, morbidity, and mortality. When employing computer-aided diagnostic (CAD) technologies, promising results have been shown in the efficiency and accuracy of fracture classification, particularly with the growing use of Deep Learning (DL) approaches. Nevertheless, the complexity is further increased by the need to collect enough input data to train these algorithms and the challenge of interpreting the findings. By improving on the results of the most recent deep learning-based Arbeitsgemeinschaft für Osteosynthesefragen and Orthopaedic Trauma Association (AO/OTA) system classification of femur fractures, this study intends to support physicians in making correct and timely decisions regarding patient care. A state-of-the-art architecture, YOLOv8, was used and refined while paying close attention to the interpretability of the model. Furthermore, data augmentation techniques were involved during preprocessing, increasing the dataset samples through image processing alterations. The fine-tuned YOLOv8 model achieved remarkable results, with 0.9 accuracy, 0.85 precision, 0.85 recall, and 0.85 F1-score, computed by averaging the values among all the individual classes for each metric. This study shows the proposed architecture's effectiveness in enhancing the AO/OTA system's classification of femur fractures, assisting physicians in making prompt and accurate diagnoses.
Collapse
Affiliation(s)
- Giorgia Marullo
- Department of Management, Production, and Design, Politecnico di Torino, C.so Duca degli Abruzzi, 24, Torino 10129, Italy
| | - Luca Ulrich
- Department of Management, Production, and Design, Politecnico di Torino, C.so Duca degli Abruzzi, 24, Torino 10129, Italy
| | - Francesca Giada Antonaci
- Department of Management, Production, and Design, Politecnico di Torino, C.so Duca degli Abruzzi, 24, Torino 10129, Italy
| | - Andrea Audisio
- Pediatric Orthopaedics and Traumatology, Regina Margherita Children's Hospital, Torino 10126, Italy
| | - Alessandro Aprato
- Department of Surgical Sciences, University of Turin, Torino 10124, Italy
| | - Alessandro Massè
- Department of Surgical Sciences, University of Turin, Torino 10124, Italy
| | - Enrico Vezzetti
- Department of Management, Production, and Design, Politecnico di Torino, C.so Duca degli Abruzzi, 24, Torino 10129, Italy
| |
Collapse
|
19
|
Choi H, Kim Y, Kang H, Seo H, Kim M, Han J, Kee G, Park S, Ko S, Jung H, Kim B, Roh JH, Jun TJ, Kim YH. Time series forecasting of weight for diuretic dose adjustment using bidirectional long short-term memory. Sci Rep 2024; 14:17723. [PMID: 39085306 PMCID: PMC11292016 DOI: 10.1038/s41598-024-68663-6] [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: 06/14/2024] [Accepted: 07/26/2024] [Indexed: 08/02/2024] Open
Abstract
Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients.
Collapse
Affiliation(s)
- Heejung Choi
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Yunha Kim
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Heejun Kang
- Division of Cardiology, Asan Medical Center, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Hyeram Seo
- Department of Information Medicine, Asan Medical Center, 88, Olympicro 43GilSongpagu, 05505, Seoul, Republic of Korea
| | - Minkyoung Kim
- Department of Information Medicine, Asan Medical Center, 88, Olympicro 43GilSongpagu, 05505, Seoul, Republic of Korea
| | - JiYe Han
- Department of Information Medicine, Asan Medical Center, 88, Olympicro 43GilSongpagu, 05505, Seoul, Republic of Korea
| | - Gaeun Kee
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Seohyun Park
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Soyoung Ko
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - HyoJe Jung
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Byeolhee Kim
- Department of Medical ScienceAsan Medical Institute of Convergence Science and TechnologyAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43Gil, Songpagu, 05505, Seoul, Republic of Korea
| | - Jae-Hyung Roh
- Department of Internal Medicine, Chungnam National University College of Medicine, Chungnam National University Sejong Hospital, 20, Bodeum 7-Ro, Sejong-Si, 30099, Sejong, Republic of Korea
| | - Tae Joon Jun
- Big Data Research Center, Asan Institute for Life Sciences, AsanMedicalCenter, 88, Olympicro 43GilSongpagu, 05505, Seoul, Republic of Korea
| | - Young-Hak Kim
- Division of CardiologyDepartment of Information MedicineAsan Medical Center, University of Ulsan College of Medicine, 88, Olympicro 43GilSongpagu, 05505, Seoul, Republic of Korea.
| |
Collapse
|
20
|
Kiser AC, Shi J, Bucher BT. An explainable long short-term memory network for surgical site infection identification. Surgery 2024; 176:24-31. [PMID: 38616153 PMCID: PMC11162927 DOI: 10.1016/j.surg.2024.03.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 02/23/2024] [Accepted: 03/03/2024] [Indexed: 04/16/2024]
Abstract
BACKGROUND Currently, surgical site infection surveillance relies on labor-intensive manual chart review. Recently suggested solutions involve machine learning to identify surgical site infections directly from the medical record. Deep learning is a form of machine learning that has historically performed better than traditional methods while being harder to interpret. We propose a deep learning model, a long short-term memory network, for the identification of surgical site infection from the medical record with an attention layer for explainability. METHODS We retrieved structured data and clinical notes from the University of Utah Health System's electronic health care record for operative events randomly selected for manual chart review from January 2016 to June 2021. Surgical site infection occurring within 30 days of surgery was determined according to the National Surgical Quality Improvement Program definition. We trained the long short-term memory model along with traditional machine learning models for comparison. We calculated several performance metrics from a holdout test set and performed additional analyses to understand the performance of the long short-term memory, including an explainability analysis. RESULTS Surgical site infection was present in 4.7% of the total 9,185 operative events. The area under the receiver operating characteristic curve and sensitivity of the long short-term memory was higher (area under the receiver operating characteristic curve: 0.954, sensitivity: 0.920) compared to the top traditional model (area under the receiver operating characteristic curve: 0.937, sensitivity: 0.736). The top 5 features of the long short-term memory included 2 procedure codes and 3 laboratory values. CONCLUSION Surgical site infection surveillance is vital for the reduction of surgical site infection rates. Our explainable long short-term memory achieved a comparable area under the receiver operating characteristic curve and greater sensitivity when compared to traditional machine learning methods. With explainable deep learning, automated surgical site infection surveillance could replace burdensome manual chart review processes.
Collapse
Affiliation(s)
- Amber C Kiser
- Department of Biomedical Informatics, University of Utah School of Medicine, Salt Lake City, UT.
| | - Jianlin Shi
- Division of Epidemiology, Department of Medicine, University of Utah School of Medicine, Salt Lake City, UT
| | - Brian T Bucher
- Department of Biomedical Informatics, University of Utah School of Medicine, Salt Lake City, UT; Division of Pediatric Surgery, Department of Surgery, University of Utah School of Medicine, Salt Lake City, UT
| |
Collapse
|
21
|
Hodgman M, Wittrup E, Najarian K. Learning Physiological Mechanisms that Predict Adverse Cardiovascular Events in Intensive Care Patients with Chronic Heart Disease. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2024; 2024:1-4. [PMID: 40039950 DOI: 10.1109/embc53108.2024.10781773] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2025]
Abstract
Chronic heart disease is a burdensome, complex, and fatal condition. Learning the mechanisms driving the development of heart disease is key to early risk assessment and intervention. However, many current machine learning approaches lack sufficient interpretability. Using 2,737 patients with chronic heart disease from the MIMIC-III database, we trained an interpretable Tropical Geometry Fuzzy Neural Network to predict one-year occurrence of a severe cardiac procedure or mortality (AUROC=0.663). We present the 20 learned rules which explain the model predictions. We find that the rules are clinically valid and indicate underlying pathologies. We anticipate that with additional development and validation, these rules will aid clinicians in providing preventative care for chronic heart disease patients in intensive care units.
Collapse
|
22
|
Xu Z, Guo J, Qin L, Xie Y, Xiao Y, Lin X, Li Q, Li X. Predicting ICU Interventions: A Transparent Decision Support Model Based on Multivariate Time Series Graph Convolutional Neural Network. IEEE J Biomed Health Inform 2024; 28:3709-3720. [PMID: 38512747 DOI: 10.1109/jbhi.2024.3379998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/23/2024]
Abstract
In this study, we present a novel approach for predicting interventions for patients in the intensive care unit using a multivariate time series graph convolutional neural network. Our method addresses two critical challenges: the need for timely and accurate decisions based on changing physiological signals, drug administration information, and static characteristics; and the need for interpretability in the decision-making process. Drawing on real-world ICU records from the MIMIC-III dataset, we demonstrate that our approach significantly improves upon existing machine learning and deep learning methods for predicting two targeted interventions, mechanical ventilation and vasopressors. Our model achieved an accuracy improvement from 81.6% to 91.9% and a F1 score improvement from 0.524 to 0.606 for predicting mechanical ventilation interventions. For predicting vasopressor interventions, our model achieved an accuracy improvement from 76.3% to 82.7% and a F1 score improvement from 0.509 to 0.619. We also assessed the interpretability by performing an adjacency matrix importance analysis, which revealed that our model uses clinically meaningful and appropriate features for prediction. This critical aspect can help clinicians gain insights into the underlying mechanisms of interventions, allowing them to make more informed and precise clinical decisions. Overall, our study represents a significant step forward in the development of decision support systems for ICU patient care, providing a powerful tool for improving clinical outcomes and enhancing patient safety.
Collapse
|
23
|
Zilker S, Weinzierl S, Kraus M, Zschech P, Matzner M. A machine learning framework for interpretable predictions in patient pathways: The case of predicting ICU admission for patients with symptoms of sepsis. Health Care Manag Sci 2024; 27:136-167. [PMID: 38771522 PMCID: PMC11258202 DOI: 10.1007/s10729-024-09673-8] [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: 02/08/2023] [Accepted: 04/13/2024] [Indexed: 05/22/2024]
Abstract
Proactive analysis of patient pathways helps healthcare providers anticipate treatment-related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient's complete health history to make informed decisions about future events. However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for clinicians to apply such models. Our work introduces PatWay-Net, an ML framework designed for interpretable predictions of admission to the intensive care unit (ICU) for patients with symptoms of sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks. Our evaluation includes both predictive performance - where PatWay-Net outperforms standard models such as decision trees, random forests, and gradient-boosted decision trees - and clinical utility, validated through structured interviews with clinicians. By providing improved predictive accuracy along with interpretable and actionable insights, PatWay-Net serves as a valuable tool for healthcare decision support in the critical case of patients with symptoms of sepsis.
Collapse
Affiliation(s)
- Sandra Zilker
- Technische Hochschule Nürnberg Georg Simon Ohm, Professorship for Business Analytics, Hohfederstraße 40, 90489, Nuremberg, Germany.
- Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair of Digital Industrial Service Systems, Fürther Straße 248, 90429, Nuremberg, Germany.
| | - Sven Weinzierl
- Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair of Digital Industrial Service Systems, Fürther Straße 248, 90429, Nuremberg, Germany
| | - Mathias Kraus
- University of Regensburg, Chair for Explainable AI in Business Value Creation, Bajuwarenstraße 4, 93053, Regensburg, Germany
| | - Patrick Zschech
- Leipzig University, Professorship for Intelligent Information Systems and Processes, Grimmaische Straße 12, 04109, Leipzig, Germany
| | - Martin Matzner
- Friedrich-Alexander-Universität Erlangen-Nürnberg, Chair of Digital Industrial Service Systems, Fürther Straße 248, 90429, Nuremberg, Germany
| |
Collapse
|
24
|
Jin R, Ye Q, Wang J, Cao Z, Jiang D, Wang T, Kang Y, Xu W, Hsieh CY, Hou T. AttABseq: an attention-based deep learning prediction method for antigen-antibody binding affinity changes based on protein sequences. Brief Bioinform 2024; 25:bbae304. [PMID: 38960407 PMCID: PMC11221889 DOI: 10.1093/bib/bbae304] [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: 11/09/2023] [Revised: 04/15/2024] [Accepted: 06/11/2024] [Indexed: 07/05/2024] Open
Abstract
The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.
Collapse
Affiliation(s)
- Ruofan Jin
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
- College of Life Science, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Qing Ye
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Jike Wang
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Zheng Cao
- College of Computer Science and Technology, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Dejun Jiang
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Tianyue Wang
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Yu Kang
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Wanting Xu
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Chang-Yu Hsieh
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| | - Tingjun Hou
- College of Pharmaceutical Science, Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Zhejiang University, Yuhangtang Road 866, Hangzhou 310058, Zhejiang, China
| |
Collapse
|
25
|
Moroz H, Li Y, Marelli A. hART: Deep learning-informed lifespan heart failure risk trajectories. Int J Med Inform 2024; 185:105384. [PMID: 38395016 DOI: 10.1016/j.ijmedinf.2024.105384] [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: 10/27/2023] [Revised: 01/21/2024] [Accepted: 02/18/2024] [Indexed: 02/25/2024]
Abstract
BACKGROUND Heart failure (HF) results in persistent risk and long-term comorbidities. This is particularly true for patients with lifelong HF sequelae of cardiovascular disease such as patients with congenital heart disease (CHD). PURPOSE We developed hART (heart failure Attentive Risk Trajectory), a deep-learning model to predict HF trajectories in CHD patients. METHODS hART is designed to capture the contextual relationships between medical events within a patient's history. It is trained to predict future HF risk by using the masked self-attention mechanism that forces it to focus only on the most relevant segments of the past medical events. RESULTS To demonstrate the utility of hART, we used a large cohort containing healthcare administrative data from the Quebec CHD database (137,493 patients, 35-year follow-up). hART achieves an area under the precision-recall of 28% for HF risk prediction, which is 33% improvement over existing methods. Patients with severe CHD lesion showed a consistently elevated predicted HF risks throughout their lifespan, and patients with genetic syndromes exhibited elevated HF risks until the age of 50. The impact of the birth condition decreases on long-term HF risk. The timing of interventions such as arrhythmia surgery had varying impacts on the lifespan HF risk among the individuals. Arrhythmic surgery performed at a younger age had minimal long-term effects on HF risk, while surgeries during adulthood had a significant lasting impact. CONCLUSION Together, we show that hART can detect meaningful lifelong HF risk in CHD patients by capturing both long and short-range dependencies in their past medical events.
Collapse
Affiliation(s)
- Harry Moroz
- Department of Medicine, McGill University of Health Centre, Montreal, QC, Canada
| | - Yue Li
- School of Computer Science, McGill University, Montreal, QC, Canada.
| | - Ariane Marelli
- Department of Medicine, McGill University of Health Centre, Montreal, QC, Canada.
| |
Collapse
|
26
|
Xiang L, Gao Z, Wang A, Shim V, Fekete G, Gu Y, Fernandez J. Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors. Front Bioeng Biotechnol 2024; 12:1377383. [PMID: 38650752 PMCID: PMC11033368 DOI: 10.3389/fbioe.2024.1377383] [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: 01/27/2024] [Accepted: 03/22/2024] [Indexed: 04/25/2024] Open
Abstract
This study presents a comprehensive review of the correlation between tibial acceleration (TA), ground reaction forces (GRF), and tibial bone loading, emphasizing the critical role of wearable sensor technology in accurately measuring these biomechanical forces in the context of running. This systematic review and meta-analysis searched various electronic databases (PubMed, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect) to identify relevant studies. It critically evaluates existing research on GRF and tibial acceleration (TA) as indicators of running-related injuries, revealing mixed findings. Intriguingly, recent empirical data indicate only a marginal link between GRF, TA, and tibial bone stress, thus challenging the conventional understanding in this field. The study also highlights the limitations of current biomechanical models and methodologies, proposing a paradigm shift towards more holistic and integrated approaches. The study underscores wearable sensors' potential, enhanced by machine learning, in transforming the monitoring, prevention, and rehabilitation of running-related injuries.
Collapse
Affiliation(s)
- Liangliang Xiang
- Department of Radiology, Ningbo No. 2 Hospital, Ningbo, China
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Zixiang Gao
- Department of Radiology, Ningbo No. 2 Hospital, Ningbo, China
- Faculty of Engineering, University of Pannonia, Veszprém, Hungary
| | - Alan Wang
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
- Center for Medical Imaging, Faculty of Medical and Health Sciences, The University of Auckland, Auckland, New Zealand
| | - Vickie Shim
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Gusztáv Fekete
- Vehicle Industry Research Center, Széchenyi István University, Győr, Hungary
| | - Yaodong Gu
- Department of Radiology, Ningbo No. 2 Hospital, Ningbo, China
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
- Faculty of Sports Science, Ningbo University, Ningbo, China
| | - Justin Fernandez
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
- Department of Engineering Science, The University of Auckland, Auckland, New Zealand
| |
Collapse
|
27
|
Armoundas AA, Narayan SM, Arnett DK, Spector-Bagdady K, Bennett DA, Celi LA, Friedman PA, Gollob MH, Hall JL, Kwitek AE, Lett E, Menon BK, Sheehan KA, Al-Zaiti SS. Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association. Circulation 2024; 149:e1028-e1050. [PMID: 38415358 PMCID: PMC11042786 DOI: 10.1161/cir.0000000000001201] [Citation(s) in RCA: 50] [Impact Index Per Article: 50.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/29/2024]
Abstract
A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.
Collapse
|
28
|
Abrego L, Zaikin A, Marino IP, Krivonosov MI, Jacobs I, Menon U, Gentry‐Maharaj A, Blyuss O. Bayesian and deep-learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers. Cancer Med 2024; 13:e7163. [PMID: 38597129 PMCID: PMC11004913 DOI: 10.1002/cam4.7163] [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: 09/05/2023] [Revised: 03/16/2024] [Accepted: 03/26/2024] [Indexed: 04/11/2024] Open
Abstract
BACKGROUND Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best-performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models. METHODS Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change-point detection and recurrent neural networks. RESULTS We obtained a significantly higher performance for CA125-HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change-point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125-HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125. CONCLUSIONS Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer.
Collapse
Affiliation(s)
- Luis Abrego
- Department of Women's CancerEGA Institute for Women's Health, University College LondonLondonUK
- Department of MathematicsUniversity College LondonLondonUK
| | - Alexey Zaikin
- Department of Women's CancerEGA Institute for Women's Health, University College LondonLondonUK
- Department of MathematicsUniversity College LondonLondonUK
| | - Ines P. Marino
- Department of Biology and Geology, Physics and Inorganic ChemistryUniversidad Rey Juan CarlosMadridSpain
| | - Mikhail I. Krivonosov
- Research Center for Trusted Artificial IntelligenceIvannikov Institute for System Programming of the Russian Academy of SciencesMoscowRussia
- Institute of BiogerontologyLobachevsky State UniversityNizhny NovgorodRussia
| | - Ian Jacobs
- Department of Women's CancerEGA Institute for Women's Health, University College LondonLondonUK
| | - Usha Menon
- MRC Clinical Trials UnitUniversity College LondonLondonUK
| | - Aleksandra Gentry‐Maharaj
- Department of Women's CancerEGA Institute for Women's Health, University College LondonLondonUK
- MRC Clinical Trials UnitUniversity College LondonLondonUK
| | - Oleg Blyuss
- Department of Women's CancerEGA Institute for Women's Health, University College LondonLondonUK
- Wolfson Institute of Population HealthQueen Mary University of LondonLondonUK
- Department of Pediatrics and Pediatric Infectious Diseases, Institute of Child's HealthSechenov First Moscow State Medical University (Sechenov University)MoscowRussia
| |
Collapse
|
29
|
Zheng Y, Song Z, Cheng B, Peng X, Huang Y, Min M. Integrating Phenotypic Information of Obstructive Sleep Apnea and Deep Representation of Sleep-Event Sequences for Cardiovascular Risk Prediction. RESEARCH SQUARE 2024:rs.3.rs-4084889. [PMID: 38559110 PMCID: PMC10980103 DOI: 10.21203/rs.3.rs-4084889/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/04/2024]
Abstract
Background Advances in mobile, wearable and machine learning (ML) technologies for gathering and analyzing long-term health data have opened up new possibilities for predicting and preventing cardiovascular diseases (CVDs). Meanwhile, the association between obstructive sleep apnea (OSA) and CV risk has been well-recognized. This study seeks to explore effective strategies of incorporating OSA phenotypic information and overnight physiological information for precise CV risk prediction in the general population. Methods 1,874 participants without a history of CVDs from the MESA dataset were included for the 5-year CV risk prediction. Four OSA phenotypes were first identified by the K-mean clustering based on static polysomnographic (PSG) features. Then several phenotype-agnostic and phenotype-specific ML models, along with deep learning (DL) models that integrate deep representations of overnight sleep-event feature sequences, were built for CV risk prediction. Finally, feature importance analysis was conducted by calculating SHapley Additive exPlanations (SHAP) values for all features across the four phenotypes to provide model interpretability. Results All ML models showed improved performance after incorporating the OSA phenotypic information. The DL model trained with the proposed phenotype-contrastive training strategy performed the best, achieving an area under the Receiver Operating Characteristic (ROC) curve of 0.877. Moreover, PSG and FOOD FREQUENCY features were recognized as significant CV risk factors across all phenotypes, with each phenotype emphasizing unique features. Conclusion Models that are aware of OSA phenotypes are preferred, and lifestyle factors should be a greater focus for precise CV prevention and risk management in the general population.
Collapse
|
30
|
Yang M, Liu S, Hao T, Ma C, Chen H, Li Y, Wu C, Xie J, Qiu H, Li J, Yang Y, Liu C. Development and validation of a deep interpretable network for continuous acute kidney injury prediction in critically ill patients. Artif Intell Med 2024; 149:102785. [PMID: 38462285 DOI: 10.1016/j.artmed.2024.102785] [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: 09/19/2022] [Revised: 10/05/2023] [Accepted: 01/21/2024] [Indexed: 03/12/2024]
Abstract
Early detection of acute kidney injury (AKI) may provide a crucial window of opportunity to prevent further injury, which helps improve clinical outcomes. This study aimed to develop a deep interpretable network for continuously predicting the 24-hour AKI risk in real-time and evaluate its performance internally and externally in critically ill patients. A total of 21,163 patients' electronic health records sourced from Beth Israel Deaconess Medical Center (BIDMC) were first included in building the model. Two external validation populations included 3025 patients from the Philips eICU Research Institute and 2625 patients from Zhongda Hospital Southeast University. A total of 152 intelligently engineered predictors were extracted on an hourly basis. The prediction model referred to as DeepAKI was designed with the basic framework of squeeze-and-excitation networks with dilated causal convolution embedded. The integrated gradients method was utilized to explain the prediction model. When performed on the internal validation set (3175 [15 %] patients from BIDMC) and the two external validation sets, DeepAKI obtained the area under the curve of 0.799 (95 % CI 0.791-0.806), 0.763 (95 % CI 0.755-0.771) and 0.676 (95 % CI 0.668-0.684) for continuousAKI prediction, respectively. For model interpretability, clinically relevant important variables contributing to the model prediction were informed, and individual explanations along the timeline were explored to show how AKI risk arose. The potential threats to generalisability in deep learning-based models when deployed across health systems in real-world settings were analyzed.
Collapse
Affiliation(s)
- Meicheng Yang
- The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China
| | - Songqiao Liu
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China; Department of Critical Care Medicine, Nanjing Lishui People's Hospital, Zhongda Hospital Lishui Branch, Nanjing, China
| | - Tong Hao
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Caiyun Ma
- The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China
| | - Hui Chen
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Yuwen Li
- The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China
| | - Changde Wu
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Jianfeng Xie
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Haibo Qiu
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Jianqing Li
- The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China; School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
| | - Yi Yang
- Jiangsu Provincial Key Laboratory of Critical Care Medicine, Department of Critical Care Medicine, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China.
| | - Chengyu Liu
- The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China.
| |
Collapse
|
31
|
Xiang L, Gu Y, Gao Z, Yu P, Shim V, Wang A, Fernandez J. Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors. Comput Biol Med 2024; 170:108016. [PMID: 38277923 DOI: 10.1016/j.compbiomed.2024.108016] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 01/14/2024] [Accepted: 01/19/2024] [Indexed: 01/28/2024]
Abstract
The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.
Collapse
Affiliation(s)
- Liangliang Xiang
- Faculty of Sports Science, Ningbo University, Ningbo, China; Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Yaodong Gu
- Faculty of Sports Science, Ningbo University, Ningbo, China; Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand.
| | - Zixiang Gao
- Faculty of Sports Science, Ningbo University, Ningbo, China; Faculty of Engineering, University of Pannonia, Veszprém, Hungary
| | - Peimin Yu
- Faculty of Sports Science, Ningbo University, Ningbo, China; Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Vickie Shim
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand
| | - Alan Wang
- Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand; Center for Medical Imaging, Faculty of Medical and Health Sciences, The University of Auckland, Auckland, New Zealand
| | - Justin Fernandez
- Faculty of Sports Science, Ningbo University, Ningbo, China; Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand; Department of Engineering Science, The University of Auckland, Auckland, New Zealand
| |
Collapse
|
32
|
Tong L, Shi W, Isgut M, Zhong Y, Lais P, Gloster L, Sun J, Swain A, Giuste F, Wang MD. Integrating Multi-Omics Data With EHR for Precision Medicine Using Advanced Artificial Intelligence. IEEE Rev Biomed Eng 2024; 17:80-97. [PMID: 37824325 DOI: 10.1109/rbme.2023.3324264] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/14/2023]
Abstract
With the recent advancement of novel biomedical technologies such as high-throughput sequencing and wearable devices, multi-modal biomedical data ranging from multi-omics molecular data to real-time continuous bio-signals are generated at an unprecedented speed and scale every day. For the first time, these multi-modal biomedical data are able to make precision medicine close to a reality. However, due to data volume and the complexity, making good use of these multi-modal biomedical data requires major effort. Researchers and clinicians are actively developing artificial intelligence (AI) approaches for data-driven knowledge discovery and causal inference using a variety of biomedical data modalities. These AI-based approaches have demonstrated promising results in various biomedical and healthcare applications. In this review paper, we summarize the state-of-the-art AI models for integrating multi-omics data and electronic health records (EHRs) for precision medicine. We discuss the challenges and opportunities in integrating multi-omics data with EHRs and future directions. We hope this review can inspire future research and developing in integrating multi-omics data with EHRs for precision medicine.
Collapse
|
33
|
Dutta DJ, Sasaki J, Bansal A, Sugai K, Yamashita S, Li G, Lazarski C, Wang L, Sasaki T, Yamashita C, Carryl H, Suzuki R, Odawara M, Imamura Kawasawa Y, Rakic P, Torii M, Hashimoto-Torii K. Alternative splicing events as peripheral biomarkers for motor learning deficit caused by adverse prenatal environments. Proc Natl Acad Sci U S A 2023; 120:e2304074120. [PMID: 38051767 PMCID: PMC10723155 DOI: 10.1073/pnas.2304074120] [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: 03/13/2023] [Accepted: 10/25/2023] [Indexed: 12/07/2023] Open
Abstract
Severity of neurobehavioral deficits in children born from adverse pregnancies, such as maternal alcohol consumption and diabetes, does not always correlate with the adversity's duration and intensity. Therefore, biological signatures for accurate prediction of the severity of neurobehavioral deficits, and robust tools for reliable identification of such biomarkers, have an urgent clinical need. Here, we demonstrate that significant changes in the alternative splicing (AS) pattern of offspring lymphocyte RNA can function as accurate peripheral biomarkers for motor learning deficits in mouse models of prenatal alcohol exposure (PAE) and offspring of mother with diabetes (OMD). An aptly trained deep-learning model identified 29 AS events common to PAE and OMD as superior predictors of motor learning deficits than AS events specific to PAE or OMD. Shapley-value analysis, a game-theory algorithm, deciphered the trained deep-learning model's learnt associations between its input, AS events, and output, motor learning performance. Shapley values of the deep-learning model's input identified the relative contribution of the 29 common AS events to the motor learning deficit. Gene ontology and predictive structure-function analyses, using Alphafold2 algorithm, supported existing evidence on the critical roles of these molecules in early brain development and function. The direction of most AS events was opposite in PAE and OMD, potentially from differential expression of RNA binding proteins in PAE and OMD. Altogether, this study posits that AS of lymphocyte RNA is a rich resource, and deep-learning is an effective tool, for discovery of peripheral biomarkers of neurobehavioral deficits in children of diverse adverse pregnancies.
Collapse
Affiliation(s)
- Dipankar J. Dutta
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Junko Sasaki
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
- Department of Diabetes, Endocrinology and Metabolism, Tokyo Medical University, Tokyo160-8402, Japan
| | - Ankush Bansal
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Keiji Sugai
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
- Department of Diabetes, Endocrinology and Metabolism, Tokyo Medical University, Tokyo160-8402, Japan
| | - Satoshi Yamashita
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Guojiao Li
- Department of Diabetes, Endocrinology and Metabolism, Tokyo Medical University, Tokyo160-8402, Japan
| | - Christopher Lazarski
- Center for Cancer and Immunology Research, Children’s National Hospital, Washington, DC20010
| | - Li Wang
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Toru Sasaki
- Department of Obstetrics and Gynecology, Tokyo Medical University, Tokyo160-8402, Japan
| | - Chiho Yamashita
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Heather Carryl
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
| | - Ryo Suzuki
- Department of Diabetes, Endocrinology and Metabolism, Tokyo Medical University, Tokyo160-8402, Japan
| | - Masato Odawara
- Department of Diabetes, Endocrinology and Metabolism, Tokyo Medical University, Tokyo160-8402, Japan
| | - Yuka Imamura Kawasawa
- Department of Biochemistry and Molecular Biology, Pennsylvania State University College of Medicine, Hershey, PA17033
| | - Pasko Rakic
- Kavli Institute for Neuroscience, Yale School of Medicine, New Haven, CT06520
| | - Masaaki Torii
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
- Department of Pediatrics, Pharmacology and Physiology, George Washington University, Washington, DC20010
| | - Kazue Hashimoto-Torii
- Center for Neuroscience Research, Children’s National Hospital,Washington, DC20010
- Department of Pediatrics, Pharmacology and Physiology, George Washington University, Washington, DC20010
| |
Collapse
|
34
|
Wang Z, Liu J, Tian Y, Zhou T, Liu Q, Qiu Y, Li J. Integrating Medical Domain Knowledge for Early Diagnosis of Fever of Unknown Origin: An Interpretable Hierarchical Multimodal Neural Network Approach. IEEE J Biomed Health Inform 2023; 27:5237-5248. [PMID: 37590111 DOI: 10.1109/jbhi.2023.3306041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/19/2023]
Abstract
Accurate and interpretable differential diagnostic technologies are crucial for supporting clinicians in decision-making and treatment-planning for patients with fever of unknown origin (FUO). Existing solutions commonly address the diagnosis of FUO by transforming it into a multi-classification task. However, after the emergence of COVID-19 pandemic, clinicians have recognized the heightened significance of early diagnosis in patients with FUO, particularly for practical needs such as early triage. This has resulted in increased demands for identifying a wider range of etiologies, shorter observation windows, and better model interpretability. In this article, we propose an interpretable hierarchical multimodal neural network framework (iHMNNF) to facilitate early diagnosis of FUO by incorporating medical domain knowledge and leveraging multimodal clinical data. The iHMNNF comprises a top-down hierarchical reasoning framework (Td-HRF) built on the class hierarchy of FUO etiologies, five local attention-based multimodal neural networks (La-MNNs) trained for each parent node of the class hierarchy, and an interpretable module based on layer-wise relevance propagation (LRP) and attention mechanism. Experimental datasets were collected from electronic health records (EHRs) at a large-scale tertiary grade-A hospital in China, comprising 34,051 hospital admissions of 30,794 FUO patients from January 2011 to October 2020. Our proposed La-MNNs achieved area under the receiver operating characteristic curve (AUROC) values ranging from 0.7809 to 0.9035 across all five decomposed tasks, surpassing competing machine learning (ML) and single-modality deep learning (DL) methods while also providing enhanced interpretability. Furthermore, we explored the feasibility of identifying FUO etiologies using only the first N-hour time series data obtained after admission.
Collapse
|
35
|
Contreras M, Silva B, Shickel B, Bandyopadhyay S, Guan Z, Ren Y, Ozrazgat-Baslanti T, Khezeli K, Bihorac A, Rashidi P. Dynamic Delirium Prediction in the Intensive Care Unit using Machine Learning on Electronic Health Records. ... IEEE-EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS. IEEE-EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS 2023; 2023:10.1109/bhi58575.2023.10313445. [PMID: 38585187 PMCID: PMC10998264 DOI: 10.1109/bhi58575.2023.10313445] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/09/2024]
Abstract
Delirium is a syndrome of acute brain failure which is prevalent amongst older adults in the Intensive Care Unit (ICU). Incidence of delirium can significantly worsen prognosis and increase mortality, therefore necessitating its rapid and continual assessment in the ICU. Currently, the common approach for delirium assessment is manual and sporadic. Hence, there exists a critical need for a robust and automated system for predicting delirium in the ICU. In this work, we develop a machine learning (ML) system for real-time prediction of delirium using Electronic Health Record (EHR) data. Unlike prior approaches which provide one delirium prediction label per entire ICU stay, our approach provides predictions every 12 hours. We use the latest 12 hours of ICU data, along with patient demographic and medical history data, to predict delirium risk in the next 12-hour window. This enables delirium risk prediction as soon as 12 hours after ICU admission. We train and test four ML classification algorithms on longitudinal EHR data pertaining to 16,327 ICU stays of 13,395 patients covering a total of 56,297 12-hour windows in the ICU to predict the dynamic incidence of delirium. The best performing algorithm was Categorical Boosting which achieved an area under receiver operating characteristic curve (AUROC) of 0.87 (95% Confidence Interval; C.I, 0.86-0.87). The deployment of this ML system in ICUs can enable early identification of delirium, thereby reducing its deleterious impact on long-term adverse outcomes, such as ICU cost, length of stay and mortality.
Collapse
Affiliation(s)
- Miguel Contreras
- Department of Biomedical Engineering, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Brandon Silva
- Department of Biomedical Engineering, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Benjamin Shickel
- Department of Medicine, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Sabyasachi Bandyopadhyay
- Department of Biomedical Engineering, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Ziyuan Guan
- Department of Medicine, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Yuanfang Ren
- Department of Medicine, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Tezcan Ozrazgat-Baslanti
- Department of Medicine, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Kia Khezeli
- Department of Biomedical Engineering, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Azra Bihorac
- Department of Medicine, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| | - Parisa Rashidi
- Department of Biomedical Engineering, University of Florida, Gainesville, FL USA
- Intelligent Critical Care Center (IC3), University of Florida, Gainesville, FL USA
| |
Collapse
|
36
|
Sheikhalishahi S, Bhattacharyya A, Celi LA, Osmani V. An interpretable deep learning model for time-series electronic health records: Case study of delirium prediction in critical care. Artif Intell Med 2023; 144:102659. [PMID: 37783541 DOI: 10.1016/j.artmed.2023.102659] [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: 01/24/2022] [Revised: 07/19/2023] [Accepted: 09/04/2023] [Indexed: 10/04/2023]
Abstract
Deep Learning (DL) models have received increasing attention in the clinical setting, particularly in intensive care units (ICU). In this context, the interpretability of the outcomes estimated by the DL models is an essential step towards increasing adoption of DL models in clinical practice. To address this challenge, we propose an ante-hoc, interpretable neural network model. Our proposed model, named double self-attention architecture (DSA), uses two attention-based mechanisms, including self-attention and effective attention. It can capture the importance of input variables in general, as well as changes in importance along the time dimension for the outcome of interest. We evaluated our model using two real-world clinical datasets covering 22840 patients in predicting onset of delirium 12 h and 48 h in advance. Additionally, we compare the descriptive performance of our model with three post-hoc interpretable algorithms as well as with the opinion of clinicians based on the published literature and clinical experience. We find that our model covers the majority of the top-10 variables ranked by the other three post-hoc interpretable algorithms as well as the clinical opinion, with the advantage of taking into account both, the dependencies among variables as well as dependencies between varying time-steps. Finally, our results show that our model can improve descriptive performance without sacrificing predictive performance.
Collapse
Affiliation(s)
| | | | - Leo Anthony Celi
- Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA; Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Venet Osmani
- Fondazione Bruno Kessler Research Institute, Trento, Italy; Information School, University of Sheffield, UK.
| |
Collapse
|
37
|
Pungitore S, Subbian V. Assessment of Prediction Tasks and Time Window Selection in Temporal Modeling of Electronic Health Record Data: a Systematic Review. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2023; 7:313-331. [PMID: 37637723 PMCID: PMC10449760 DOI: 10.1007/s41666-023-00143-4] [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: 07/08/2022] [Revised: 04/12/2023] [Accepted: 07/28/2023] [Indexed: 08/29/2023]
Abstract
Temporal electronic health record (EHR) data are often preferred for clinical prediction tasks because they offer more complete representations of a patient's pathophysiology than static data. A challenge when working with temporal EHR data is problem formulation, which includes defining the time windows of interest and the prediction task. Our objective was to conduct a systematic review that assessed the definition and reporting of concepts relevant to temporal clinical prediction tasks. We searched PubMed® and IEEE Xplore® databases for studies from January 1, 2010 applying machine learning models to EHR data for patient outcome prediction. Publications applying time-series methods were selected for further review. We identified 92 studies and summarized them by clinical context and definition and reporting of the prediction problem. For the time windows of interest, 12 studies did not discuss window lengths, 57 used a single set of window lengths, and 23 evaluated the relationship between window length and model performance. We also found that 72 studies had appropriate reporting of the prediction task. However, evaluation of prediction problem formulation for temporal EHR data was complicated by heterogeneity in assessing and reporting of these concepts. Even among studies modeling similar clinical outcomes, there were variations in terminology used to describe the prediction problem, rationale for window lengths, and determination of the outcome of interest. As temporal modeling using EHR data expands, minimal reporting standards should include time-series specific concerns to promote rigor and reproducibility in future studies and facilitate model implementation in clinical settings. Supplementary Information The online version contains supplementary material available at 10.1007/s41666-023-00143-4.
Collapse
Affiliation(s)
- Sarah Pungitore
- Program in Applied Mathematics, Department of Mathematics, 617 N Santa Rita Ave, Tucson, AZ 85721 USA
| | - Vignesh Subbian
- Department of Biomedical Engineering, The University of Arizona, Tucson, AZ 85721-0020 USA
- Department of Systems and Industrial Engineering, The University of Arizona, Tucson, AZ 85721-0020 USA
| |
Collapse
|
38
|
Islam KR, Prithula J, Kumar J, Tan TL, Reaz MBI, Sumon MSI, Chowdhury MEH. Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review. J Clin Med 2023; 12:5658. [PMID: 37685724 PMCID: PMC10488449 DOI: 10.3390/jcm12175658] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Revised: 08/13/2023] [Accepted: 08/23/2023] [Indexed: 09/10/2023] Open
Abstract
BACKGROUND Sepsis, a life-threatening infection-induced inflammatory condition, has significant global health impacts. Timely detection is crucial for improving patient outcomes as sepsis can rapidly progress to severe forms. The application of machine learning (ML) and deep learning (DL) to predict sepsis using electronic health records (EHRs) has gained considerable attention for timely intervention. METHODS PubMed, IEEE Xplore, Google Scholar, and Scopus were searched for relevant studies. All studies that used ML/DL to detect or early-predict the onset of sepsis in the adult population using EHRs were considered. Data were extracted and analyzed from all studies that met the criteria and were also evaluated for their quality. RESULTS This systematic review examined 1942 articles, selecting 42 studies while adhering to strict criteria. The chosen studies were predominantly retrospective (n = 38) and spanned diverse geographic settings, with a focus on the United States. Different datasets, sepsis definitions, and prevalence rates were employed, necessitating data augmentation. Heterogeneous parameter utilization, diverse model distribution, and varying quality assessments were observed. Longitudinal data enabled early sepsis prediction, and quality criteria fulfillment varied, with inconsistent funding-article quality correlation. CONCLUSIONS This systematic review underscores the significance of ML/DL methods for sepsis detection and early prediction through EHR data.
Collapse
Affiliation(s)
- Khandaker Reajul Islam
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Johayra Prithula
- Department of Electrical and Electronics Engineering, University of Dhaka, Dhaka 1000, Bangladesh
| | - Jaya Kumar
- Department of Physiology, Faculty of Medicine, University Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Toh Leong Tan
- Department of Emergency Medicine, Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
| | - Mamun Bin Ibne Reaz
- Department of Electrical and Electronic Engineering, Independent University, Bangladesh Bashundhara, Dhaka 1229, Bangladesh
| | - Md. Shaheenur Islam Sumon
- Department of Biomedical Engineering, Military Institute of Science and Technology (MIST), Dhaka 1216, Bangladesh
| | | |
Collapse
|
39
|
Ahuja Y, Liang L, Zhou D, Huang S, Cai T. Semisupervised Calibration of Risk with Noisy Event Times (SCORNET) using electronic health record data. Biostatistics 2023; 24:760-775. [PMID: 35166342 PMCID: PMC10544799 DOI: 10.1093/biostatistics/kxac003] [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: 01/06/2021] [Revised: 01/18/2022] [Accepted: 01/24/2022] [Indexed: 01/19/2023] Open
Abstract
Leveraging large-scale electronic health record (EHR) data to estimate survival curves for clinical events can enable more powerful risk estimation and comparative effectiveness research. However, use of EHR data is hindered by a lack of direct event time observations. Occurrence times of relevant diagnostic codes or target disease mentions in clinical notes are at best a good approximation of the true disease onset time. On the other hand, extracting precise information on the exact event time requires laborious manual chart review and is sometimes altogether infeasible due to a lack of detailed documentation. Current status labels-binary indicators of phenotype status during follow-up-are significantly more efficient and feasible to compile, enabling more precise survival curve estimation given limited resources. Existing survival analysis methods using current status labels focus almost entirely on supervised estimation, and naive incorporation of unlabeled data into these methods may lead to biased estimates. In this article, we propose Semisupervised Calibration of Risk with Noisy Event Times (SCORNET), which yields a consistent and efficient survival function estimator by leveraging a small set of current status labels and a large set of informative features. In addition to providing theoretical justification of SCORNET, we demonstrate in both simulation and real-world EHR settings that SCORNET achieves efficiency akin to the parametric Weibull regression model, while also exhibiting semi-nonparametric flexibility and relatively low empirical bias in a variety of generative settings.
Collapse
Affiliation(s)
- Yuri Ahuja
- Department of Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115, USA
| | - Liang Liang
- Department of Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115, USA
| | - Doudou Zhou
- Department of Statistics, University of California Davis, 1 Shields Avenue, Davis, CA 05616, USA
| | - Sicong Huang
- Department of Rheumatology, Immunology, and Allergy, Brigham and Women’s Hospital, 75 Francis Street, Boston, MA 02115, USA
| | - Tianxi Cai
- Department of Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115, USA and Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Boston, MA 02115, USA
| |
Collapse
|
40
|
Prediction of Acid-Base and Potassium Imbalances in Intensive Care Patients Using Machine Learning Techniques. Diagnostics (Basel) 2023; 13:diagnostics13061171. [PMID: 36980479 PMCID: PMC10047445 DOI: 10.3390/diagnostics13061171] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Revised: 03/16/2023] [Accepted: 03/17/2023] [Indexed: 03/22/2023] Open
Abstract
Acid–base disorders occur when the body’s normal pH is out of balance. They can be caused by problems with kidney or respiratory function or by an excess of acids or bases that the body cannot properly eliminate. Acid–base and potassium imbalances are mechanistically linked because acid–base imbalances can alter the transport of potassium. Both acid–base and potassium imbalances are common in critically ill patients. This study investigated machine learning models for predicting the occurrence of acid–base and potassium imbalances in intensive care patients. We used an institutional dataset of 1089 patients with 87 variables, including vital signs, general appearance, and laboratory results. Gradient boosting (GB) was able to predict nine clinical conditions related to acid–base and potassium imbalances: mortality (AUROC = 0.9822), hypocapnia (AUROC = 0.7524), hypercapnia (AUROC = 0.8228), hypokalemia (AUROC = 0.9191), hyperkalemia (AUROC = 0.9565), respiratory acidosis (AUROC = 0.8125), respiratory alkalosis (AUROC = 0.7685), metabolic acidosis (AUROC = 0.8682), and metabolic alkalosis (AUROC = 0.8284). Some predictions remained relatively robust even when the prediction window was increased. Additionally, the decision-making process was made more interpretable and transparent through the use of SHAP analysis. Overall, the results suggest that machine learning could be a useful tool to gain insight into the condition of intensive care patients and assist in the management of acid–base and potassium imbalances.
Collapse
|
41
|
Khope SR, Elias S. Strategies of Predictive Schemes and Clinical Diagnosis for Prognosis Using MIMIC-III: A Systematic Review. Healthcare (Basel) 2023; 11:710. [PMID: 36900715 PMCID: PMC10001415 DOI: 10.3390/healthcare11050710] [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: 12/11/2022] [Revised: 02/18/2023] [Accepted: 02/21/2023] [Indexed: 03/05/2023] Open
Abstract
The prime purpose of the proposed study is to construct a novel predictive scheme for assisting in the prognosis of criticality using the MIMIC-III dataset. With the adoption of various analytics and advanced computing in the healthcare system, there is an increasing trend toward developing an effective prognostication mechanism. Predictive-based modeling is the best alternative to work in this direction. This paper discusses various scientific contributions using desk research methodology towards the Medical Information Mart for Intensive Care (MIMIC-III). This open-access dataset is meant to help predict patient trajectories for various purposes ranging from mortality forecasting to treatment planning. With a dominant machine learning approach in this perspective, there is a need to discover the effectiveness of existing predictive methods. The resultant outcome of this paper offers an inclusive discussion about various available predictive schemes and clinical diagnoses using MIMIC-III in order to contribute toward better information associated with its strengths and weaknesses. Therefore, the paper provides a clear visualization of existing schemes for clinical diagnosis using a systematic review approach.
Collapse
Affiliation(s)
| | - Susan Elias
- School of Electronics Engineering, Vellore Institute of Technology, Chennai 600127, Tamil Nadu, India
| |
Collapse
|
42
|
Deep-learning-based prognostic modeling for incident heart failure in patients with diabetes using electronic health records: A retrospective cohort study. PLoS One 2023; 18:e0281878. [PMID: 36809251 PMCID: PMC9943005 DOI: 10.1371/journal.pone.0281878] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Accepted: 02/02/2023] [Indexed: 02/23/2023] Open
Abstract
Patients with type 2 diabetes mellitus (T2DM) have more than twice the risk of developing heart failure (HF) compared to patients without diabetes. The present study is aimed to build an artificial intelligence (AI) prognostic model that takes in account a large and heterogeneous set of clinical factors and investigates the risk of developing HF in diabetic patients. We carried out an electronic health records- (EHR-) based retrospective cohort study that included patients with cardiological clinical evaluation and no previous diagnosis of HF. Information consists of features extracted from clinical and administrative data obtained as part of routine medical care. The primary endpoint was diagnosis of HF (during out-of-hospital clinical examination or hospitalization). We developed two prognostic models using (1) elastic net regularization for Cox proportional hazard model (COX) and (2) a deep neural network survival method (PHNN), in which a neural network was used to represent a non-linear hazard function and explainability strategies are applied to estimate the influence of predictors on the risk function. Over a median follow-up of 65 months, 17.3% of the 10,614 patients developed HF. The PHNN model outperformed COX both in terms of discrimination (c-index 0.768 vs 0.734) and calibration (2-year integrated calibration index 0.008 vs 0.018). The AI approach led to the identification of 20 predictors of different domains (age, body mass index, echocardiographic and electrocardiographic features, laboratory measurements, comorbidities, therapies) whose relationship with the predicted risk correspond to known trends in the clinical practice. Our results suggest that prognostic models for HF in diabetic patients may improve using EHRs in combination with AI techniques for survival analysis, which provide high flexibility and better performance with respect to standard approaches.
Collapse
|
43
|
Sushentsev N, Rundo L, Abrego L, Li Z, Nazarenko T, Warren AY, Gnanapragasam VJ, Sala E, Zaikin A, Barrett T, Blyuss O. Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance. Eur Radiol 2023; 33:3792-3800. [PMID: 36749370 PMCID: PMC10182165 DOI: 10.1007/s00330-023-09438-x] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 01/03/2023] [Accepted: 01/09/2023] [Indexed: 02/08/2023]
Abstract
Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78-0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64-0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76-0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation. KEY POINTS: •LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density. •Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework. •The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.
Collapse
Affiliation(s)
- Nikita Sushentsev
- Department of Radiology, School of Clinical Medicine, Addenbrooke's Hospital, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ, UK.
| | - Leonardo Rundo
- Department of Radiology, School of Clinical Medicine, Addenbrooke's Hospital, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ, UK
- Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Fisciano, SA, Italy
| | - Luis Abrego
- Department of Women's Cancer, Institute for Women's Health, University College London, London, UK
| | - Zonglun Li
- Department of Mathematics, University College London, London, UK
| | - Tatiana Nazarenko
- Department of Women's Cancer, Institute for Women's Health, University College London, London, UK
- Department of Mathematics, University College London, London, UK
| | - Anne Y Warren
- Department of Pathology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
| | - Vincent J Gnanapragasam
- Department of Urology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
- Cambridge Urology Translational Research and Clinical Trials Office, Addenbrooke's Hospital, Cambridge Biomedical Campus, Cambridge, UK
| | - Evis Sala
- Department of Radiology, School of Clinical Medicine, Addenbrooke's Hospital, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ, UK
- Cancer Research UK Cambridge Institute, University of Cambridge, Cambridge, UK
| | - Alexey Zaikin
- Department of Women's Cancer, Institute for Women's Health, University College London, London, UK
- Department of Mathematics, University College London, London, UK
| | - Tristan Barrett
- Department of Radiology, School of Clinical Medicine, Addenbrooke's Hospital, University of Cambridge, Cambridge Biomedical Campus, Box 218, Cambridge, CB2 0QQ, UK
| | - Oleg Blyuss
- Wolfson Institute of Population Health, Queen Mary University of London, London, UK
- Center of Photonics, Lobachevsky University, Nizhny Novgorod, Russian Federation
| |
Collapse
|
44
|
Xu Q, Xie W, Liao B, Hu C, Qin L, Yang Z, Xiong H, Lyu Y, Zhou Y, Luo A. Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review. JOURNAL OF HEALTHCARE ENGINEERING 2023; 2023:9919269. [PMID: 36776958 PMCID: PMC9918364 DOI: 10.1155/2023/9919269] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Revised: 05/05/2022] [Accepted: 11/24/2022] [Indexed: 02/05/2023]
Abstract
Background Artificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application. Objective This study is a review of the knowledge-based and data-based CDSS literature regarding interpretability in health care. It highlights the relevance of interpretability for CDSS and the area for improvement from technological and medical perspectives. Methods A systematic search was conducted on the interpretability-related literature published from 2011 to 2020 and indexed in the five databases: Web of Science, PubMed, ScienceDirect, Cochrane, and Scopus. Journal articles that focus on the interpretability of CDSS were included for analysis. Experienced researchers also participated in manually reviewing the selected articles for inclusion/exclusion and categorization. Results Based on the inclusion and exclusion criteria, 20 articles from 16 journals were finally selected for this review. Interpretability, which means a transparent structure of the model, a clear relationship between input and output, and explainability of artificial intelligence algorithms, is essential for CDSS application in the healthcare setting. Methods for improving the interpretability of CDSS include ante-hoc methods such as fuzzy logic, decision rules, logistic regression, decision trees for knowledge-based AI, and white box models, post hoc methods such as feature importance, sensitivity analysis, visualization, and activation maximization for black box models. A number of factors, such as data type, biomarkers, human-AI interaction, needs of clinicians, and patients, can affect the interpretability of CDSS. Conclusions The review explores the meaning of the interpretability of CDSS and summarizes the current methods for improving interpretability from technological and medical perspectives. The results contribute to the understanding of the interpretability of CDSS based on AI in health care. Future studies should focus on establishing formalism for defining interpretability, identifying the properties of interpretability, and developing an appropriate and objective metric for interpretability; in addition, the user's demand for interpretability and how to express and provide explanations are also the directions for future research.
Collapse
Affiliation(s)
- Qian Xu
- The Second Xiangya Hospital of Central South University, No. 139, Renmin Road Central, Changsha, Hunan, China
- School of Life Sciences, Central South University, Changsha, Hunan, China
- College of Computer Science and Engineering, Jishou University, Jishou, Hunan, China
- Key Laboratory of Medical Information Research, The Third Xiangya Hospital, Central South University, College of Hunan Province, Changsha, Hunan, China
- Clinical Research Center for Cardiovascular Intelligent Healthcare, Changsha, Hunan, China
| | - Wenzhao Xie
- Key Laboratory of Medical Information Research, The Third Xiangya Hospital, Central South University, College of Hunan Province, Changsha, Hunan, China
| | - Bolin Liao
- College of Computer Science and Engineering, Jishou University, Jishou, Hunan, China
| | - Chao Hu
- Big Data Institute, Central South University, Changsha 410083, China
| | - Lu Qin
- School of Life Sciences, Central South University, Changsha, Hunan, China
| | - Zhengzijin Yang
- School of Life Sciences, Central South University, Changsha, Hunan, China
| | - Huan Xiong
- School of Life Sciences, Central South University, Changsha, Hunan, China
| | - Yi Lyu
- School of Life Sciences, Central South University, Changsha, Hunan, China
| | - Yue Zhou
- School of Life Sciences, Central South University, Changsha, Hunan, China
| | - Aijing Luo
- The Second Xiangya Hospital of Central South University, No. 139, Renmin Road Central, Changsha, Hunan, China
- Key Laboratory of Medical Information Research, The Third Xiangya Hospital, Central South University, College of Hunan Province, Changsha, Hunan, China
- Clinical Research Center for Cardiovascular Intelligent Healthcare, Changsha, Hunan, China
| |
Collapse
|
45
|
Takkavatakarn K, Hofer IS. Artificial Intelligence and Machine Learning in Perioperative Acute Kidney Injury. ADVANCES IN KIDNEY DISEASE AND HEALTH 2023; 30:53-60. [PMID: 36723283 DOI: 10.1053/j.akdh.2022.10.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Revised: 09/30/2022] [Accepted: 10/28/2022] [Indexed: 12/24/2022]
Abstract
Acute kidney injury (AKI) is a common complication after a surgery, especially in cardiac and aortic procedures, and has a significant impact on morbidity and mortality. Early identification of high-risk patients and providing effective prevention and therapeutic approach are the main strategies for reducing the possibility of perioperative AKI. Consequently, several risk-prediction models and risk assessment scores have been developed for the prediction of perioperative AKI. However, a majority of these risk scores are only derived from preoperative data while the intraoperative time-series monitoring data such as heart rate and blood pressure were not included. Moreover, the complexity of the pathophysiology of AKI, as well as its nonlinear and heterogeneous nature, imposes limitations on the use of linear statistical techniques. The development of clinical medicine's digitization, the widespread availability of electronic medical records, and the increase in the use of continuous monitoring have generated vast quantities of data. Machine learning has recently shown promise as a method for automatically integrating large amounts of data in predicting the risk of perioperative outcomes. In this article, we discussed the development, limitations of existing work, and the potential future direction of models using machine learning techniques to predict AKI after a surgery.
Collapse
Affiliation(s)
- Kullaya Takkavatakarn
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY; Division of Nephrology, Department of Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Ira S Hofer
- Department of Anesthesiology, Pain and Perioperative Medicine, Icahn School of Medicine at Mount, Sinai, NY.
| |
Collapse
|
46
|
Wang Z, Samsten I, Kougia V, Papapetrou P. Style-transfer counterfactual explanations: An application to mortality prevention of ICU patients. Artif Intell Med 2023; 135:102457. [PMID: 36628793 DOI: 10.1016/j.artmed.2022.102457] [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: 01/31/2022] [Revised: 10/21/2022] [Accepted: 11/16/2022] [Indexed: 11/24/2022]
Abstract
In recent years, machine learning methods have been rapidly adopted in the medical domain. However, current state-of-the-art medical mining methods usually produce opaque, black-box models. To address the lack of model transparency, substantial attention has been given to developing interpretable machine learning models. In the medical domain, counterfactuals can provide example-based explanations for predictions, and show practitioners the modifications required to change a prediction from an undesired to a desired state. In this paper, we propose a counterfactual solution MedSeqCF for preventing the mortality of three cohorts of ICU patients, by representing their electronic health records as medical event sequences, and generating counterfactuals by adopting and employing a text style-transfer technique. We propose three model augmentations for MedSeqCF to integrate additional medical knowledge for generating more trustworthy counterfactuals. Experimental results on the MIMIC-III dataset strongly suggest that augmented style-transfer methods can be effectively adapted for the problem of counterfactual explanations in healthcare applications and can further improve the model performance in terms of validity, BLEU-4, local outlier factor, and edit distance. In addition, our qualitative analysis of the results by consultation with medical experts suggests that our style-transfer solutions can generate clinically relevant and actionable counterfactual explanations.
Collapse
Affiliation(s)
- Zhendong Wang
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden.
| | - Isak Samsten
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
| | - Vasiliki Kougia
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden; Faculty of Computer Science, University of Vienna, Vienna, Austria
| | - Panagiotis Papapetrou
- Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
| |
Collapse
|
47
|
D'Hondt E, Ashby TJ, Chakroun I, Koninckx T, Wuyts R. Identifying and evaluating barriers for the implementation of machine learning in the intensive care unit. COMMUNICATIONS MEDICINE 2022; 2:162. [PMID: 36543940 PMCID: PMC9768782 DOI: 10.1038/s43856-022-00225-1] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2021] [Accepted: 11/29/2022] [Indexed: 12/24/2022] Open
Abstract
BACKGROUND Despite apparent promise and the availability of numerous examples in the literature, machine learning models are rarely used in practice in ICU units. This mismatch suggests that there are poorly understood barriers preventing uptake, which we aim to identify. METHODS We begin with a qualitative study with 29 interviews of 40 Intensive Care Unit-, hospital- and MedTech company staff members. As a follow-up to the study, we attempt to quantify some of the technical issues raised. To perform experiments we selected two models based on criteria such as medical relevance. Using these models we measure the loss of performance in predictive models due to drift over time, change of available patient features, scarceness of data, and deploying a model in a different context to the one it was built in. RESULTS The qualitative study confirms our assumptions on the potential of AI-driven analytics for patient care, as well as showing the prevalence and type of technical blocking factors that are responsible for its slow uptake. The experiments confirm that each of these issues can cause important loss of predictive model performance, depending on the model and the issue. CONCLUSIONS Based on the qualitative study and quantitative experiments we conclude that more research on practical solutions to enable AI-driven innovation in Intensive Care Units is needed. Furthermore, the general poor situation with respect to public, usable implementations of predictive models would appear to limit the possibilities for both the scientific repeatability of the underlying research and the transfer of this research into practice.
Collapse
Affiliation(s)
| | | | | | | | - Roel Wuyts
- Exascience Life Lab, imec, Leuven, Belgium.
| |
Collapse
|
48
|
Hwang GJ, Chang PY, Tseng WY, Chou CA, Wu CH, Tu YF. Research Trends in Artificial Intelligence-Associated Nursing Activities Based on a Review of Academic Studies Published From 2001 to 2020. Comput Inform Nurs 2022; 40:814-824. [PMID: 36516032 DOI: 10.1097/cin.0000000000000897] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
The present study referred to the technology-based learning model to conduct a systematic review of the dimensions of nursing activities, research samples, research methods, roles of artificial intelligence, applied artificial intelligence algorithms, evaluation measure of algorithms, and research foci. Based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses procedure, this study obtained and analyzed a total of 102 high-quality artificial intelligence-associated nursing activities studies published from 2001 to 2020 in the Web of Science database. The results showed: (1) In terms of nursing activities, nursing management was explored the most, followed by nursing assessment; (2) quantitative methods were most frequently adopted in artificial intelligence-associated nursing activities studies to investigate issues related to patients, followed by nursing staff; (3) the most adopted roles of artificial intelligence in artificial intelligence-associated nursing activities studies were profiling and prediction, followed by assessment and evaluation; (4) artificial intelligence-associated nursing activities studies frequently mixed applied artificial intelligence algorithms and evaluation measure of algorithms; (5) in the dimension of research foci, most studies mainly paid attention to the design or evaluation of the artificial intelligence systems/instruments, followed by investigating the correlation and affect issues. Based on the findings, several recommendations are raised as a reference for future researchers, educators, and policy makers.
Collapse
Affiliation(s)
- Gwo-Jen Hwang
- Author Affiliations : Graduate Institute of Digital Learning and Education, National Taiwan University of Science and Technology (Dr Hwang, Ms Chang, Ms Tseng, Mr Chou, and Ms Wu); and Department of Library and Information Science, Bachelor's Program in Information Innovation and Digital life, Research and Development Center for Physical Education, Health, and Information Technology, Fu Jen Catholic University (Dr Tu), Taiwan
| | | | | | | | | | | |
Collapse
|
49
|
Ding W, Abdel-Basset M, Hawash H, Ali AM. Explainability of artificial intelligence methods, applications and challenges: A comprehensive survey. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2022.10.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
50
|
Sadasivuni S, Bhanushali SP, Banerjee I, Sanyal A. In-sensor neural network for high energy efficiency analog-to-information conversion. Sci Rep 2022; 12:18253. [PMID: 36309584 PMCID: PMC9617885 DOI: 10.1038/s41598-022-23100-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Accepted: 10/25/2022] [Indexed: 12/31/2022] Open
Abstract
This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by [Formula: see text] with test-chips prototyped in 65 nm CMOS.
Collapse
Affiliation(s)
- Sudarsan Sadasivuni
- grid.273335.30000 0004 1936 9887Electrical Engineering, University at Buffalo, Buffalo, 14260 USA
| | - Sumukh Prashant Bhanushali
- grid.215654.10000 0001 2151 2636School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287 USA
| | - Imon Banerjee
- grid.470142.40000 0004 0443 9766Mayo Clinic, Phoenix, 85054 USA
| | - Arindam Sanyal
- grid.215654.10000 0001 2151 2636School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, 85287 USA
| |
Collapse
|