|
1
|
Wagner G, Ringeval M, Raymond L, Paré G. Digital health competences and AI beliefs as conditions for the practice of evidence-based medicine: a study of prospective physicians in Canada. MEDICAL EDUCATION ONLINE 2025; 30:2459910. [PMID: 39890587 PMCID: PMC11789221 DOI: 10.1080/10872981.2025.2459910] [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: 07/18/2024] [Revised: 12/14/2024] [Accepted: 01/19/2025] [Indexed: 02/03/2025]
Abstract
BACKGROUND The practice of evidence-based medicine (EBM) has become pivotal in enhancing medical care and patient outcomes. With the diffusion of innovation in healthcare organizations, EBM can be expected to depend on medical professionals' competences with digital health (dHealth) and artificial intelligence (AI) technologies. OBJECTIVE We aim to investigate the effect of dHealth competences and perceptions of AI on the adoption of EBM among prospective physicians. By focusing on dHealth and AI technologies, the study seeks to inform the redesign of medical curricula to better prepare students for the demands of evidence-based medical practice. METHODS A cross-sectional survey was administered online to students at the University of Montreal's medical school, which has approximately 1,400 enrolled students. The survey included questions on students' dHealth competences, perceptions of AI, and their practice of EBM. Using structural equation modeling (SEM), we analyzed data from 177 respondents to test our research model. RESULTS Our analysis indicates that medical students possess foundational knowledge competences of dHealth technologies and perceive AI to play an important role in the future of medicine. Yet, their experiential competences with dHealth technologies are limited. Our findings reveal that experiential dHealth competences are significantly related to the practice of EBM (β = 0.42, p < 0.001), as well as students' perceptions of the role of AI in the future of medicine (β = 0.39, p < 0.001), which, in turn, also affect EBM (β = 0.19, p < 0.05). CONCLUSIONS The study underscores the necessity of enhancing students' competences related to dHealth and considering their perceptions of the role of AI in the medical profession. In particular, the low levels of experiential dHealth competences highlight a promising starting point for training future physicians while simultaneously strengthening their practice of EBM. Accordingly, we suggest revising medical curricula to focus on providing students with practical experiences with dHealth and AI technologies.
Collapse
Affiliation(s)
- Gerit Wagner
- Faculty Information Systems and Applied Computer Sciences, Otto-Friedrich Universität, Bamberg, DE, Germany
| | - Mickaël Ringeval
- Département de technologies de l’information, HEC Montréal, Montréal, CA, Canada
| | | | - Guy Paré
- Département de technologies de l’information, HEC Montréal, Montréal, CA, Canada
| |
Collapse
|
|
2
|
Li B, Chen H, Duan H. Visualized hysteroscopic artificial intelligence fertility assessment system for endometrial injury: an image-deep-learning study. Ann Med 2025; 57:2478473. [PMID: 40098308 PMCID: PMC11921166 DOI: 10.1080/07853890.2025.2478473] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 05/17/2024] [Accepted: 01/04/2025] [Indexed: 03/19/2025] Open
Abstract
OBJECTIVE Asherman's syndrome (AS) is a significant cause of subfertility in women from developing countries. Over 80% of AS cases in these regions are linked to dilation and curettage (D&C) procedures following pregnancy. The incidence of AS in patients with infertility and recurrent miscarriage can be as high as 10%, while the pregnancy rate in cases of moderate to severe adhesions can be as low as 34%. We aimed to establish a hysteroscopic artificial intelligence system using image-deep-learning algorithms for fertility assessment. METHODS This diagnostic study included 555 cases with 4922 hysteroscopic images from a Chinese intrauterine adhesions cohort clinical database (NCT05381376). The study evaluated two image-deep-learning algorithms' effectiveness in predicting pregnancy within one year, using AUCs and decision curve analysis. The models' performance was evaluated for two-year prediction via concordance index and cumulative time-dependent ROC. A quantifiable visualization panel of the system was established. RESULTS The proportional hazard CNN system accurately predicted conception, with AUCs of 0.982, 0.992, and 0.990 in three randomly assigned datasets, superior to the InceptionV3 framework, and achieved a net benefit of 69.4% for subfertility assessment. The system fitted well with c-indexes of 0.920-0.940 and was time-stable. The quantifiable visualization panel displayed four intrauterine pathologies intuitively. The performance was comparable to senior hysteroscopists, with a kappa value of 0.84-0.89. CONCLUSIONS The CNN based on the proportional hazard approach accurately assesses fertility postoperatively. The quantifiable visualization panel could assist in intrauterine pathologies assessment, optimize treatment strategies, and achieve individualized and cost-efficient practices.
Collapse
Affiliation(s)
- Bohan Li
- Department of Minimally Invasive Gynecologic Center, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing Maternal and Child Health Care Hospital, Beijing, China
| | - Hui Chen
- School of Biomedical Engineering, Capital Medical University, Beijing, China
- Beijing Advanced Innovation Center for Big Data-based Precision Medicine, Capital Medical University, Beijing, China
| | - Hua Duan
- Department of Minimally Invasive Gynecologic Center, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing Maternal and Child Health Care Hospital, Beijing, China
| |
Collapse
|
|
3
|
Chen L, Lin CP, Chung CH, Lee JJ. Using longitudinal data and deep learning models to enhance resource allocation in home-based medical care. Int J Med Inform 2025; 201:105953. [PMID: 40300486 DOI: 10.1016/j.ijmedinf.2025.105953] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2025] [Revised: 03/23/2025] [Accepted: 04/23/2025] [Indexed: 05/01/2025]
Abstract
BACKGROUND The aging population is driving increased healthcare demands and costs, prompting the need for effective home healthcare programs. Accurate patient assessment is essential for optimizing resource allocation and tailoring services. OBJECTIVE This retrospective study explores the application of artificial intelligence (AI) in predicting home medical care stages to enhance care delivery. METHODS Data from Taipei City Hospital (2015-2021) included inpatient, outpatient, and home medical care records. Three deep learning (DL) models-Transformer encoder-based, long short-term memory (LSTM), and gated recurrent unit (GRU)-were compared with three baseline machine learning (ML) models. Models were trained on 3, 5, and 10 consecutive visits for binary and multiclass classification. Performance was evaluated using accuracy, precision, recall, and the area under the receiver operating characteristic curve (AUC). RESULTS The study included 4,343 patients with a mean age of 85.04 ± 11.47 years. While models trained on 10 visits generally exhibited higher performance, data from 5 visits were sufficient for accurate predictions. With five visits, the LSTM model achieved the highest AUC (0.908) for distinguishing between the absence (S0) and presence (S1-S3) of home medical care. Meanwhile, the Transformer achieved the best AUC (0.86) for classifying S0-S3, with individual stage AUCs of 0.90, 0.82, 0.81, and 0.94 for S0, S1, S2, and S3, respectively. CONCLUSIONS AI deep learning models show strong potential for accurately predicting home medical care stages. The best-performing model could be a promising tool for healthcare professionals to optimize resource allocation in home medical care settings.
Collapse
Affiliation(s)
- Ling Chen
- Institute of Hospital and Health Care Administration, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Ching-Po Lin
- Institute of Neuroscience, National Yang Ming Chiao Tung University, Taiwan; Department of Education and Research, Taipei City Hospital, Taiwan
| | - Chi-Hua Chung
- Institute of Hospital and Health Care Administration, National Yang Ming Chiao Tung University, Taipei, Taiwan
| | - Jason Jiunshiou Lee
- Department of Education and Research, Taipei City Hospital, Taiwan; Department of Family Medicine, Taipei City Hospital Yangming Branch, Taipei, Taiwan; Department of Health and Welfare, University of Taipei, Taiwan; Institute of Public Health, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Health Care Management, National Taipei University of Nursing and Health Sciences, Taipei, Taiwan.
| |
Collapse
|
|
4
|
Rahmoune H, Boutrid N, Benchoufi I. Precision medicine in celiac disease: A step ahead. Artif Intell Gastroenterol 2025; 6:105682. [DOI: 10.35712/aig.v6.i1.105682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/02/2025] [Revised: 04/05/2025] [Accepted: 05/24/2025] [Indexed: 06/06/2025] Open
Abstract
Celiac disease (CD) is a common autoimmune disorder where gluten ingestion triggers an immune response, damaging the small intestine in genetically predisposed individuals. Affecting around 1% of the global population, CD presents with diverse symptoms, including gastrointestinal issues like diarrhea and extraintestinal conditions such as anemia and osteoporosis, often complicating diagnosis. Advances in serology, histology, and genetic testing, such as HLA-DQ2/DQ8 analysis, have improved diagnostic accuracy. Precision medicine is transforming CD management by integrating genetic, clinical, and lifestyle data to enable risk prediction, personalized therapies, and improved outcomes. Tools like machine learning enhance early diagnosis, dietary management, and drug discovery, while electronic medical records support comprehensive patient profiling and disease monitoring. These technologies facilitate personalized healthcare delivery tailored to individual patient profiles.
Collapse
Affiliation(s)
- Hakim Rahmoune
- LIRSSEI Research Laboratory, Faculty of Medicine, University of Setif-1, Setif 19000, Algeria
- Department of Pediatrics, Setif University Hospital, Setif 19000, Algeria
| | - Nada Boutrid
- LIRSSEI Research Laboratory, Faculty of Medicine, University of Setif-1, Setif 19000, Algeria
- Department of Pediatrics, El Eulma Mother and Child Hospital, El Eulma 19000, Setif, Algeria
| | - Isra Benchoufi
- Department of Artificial Intelligence, National School of Artificial Intelligence, Algiers 16000, Alger, Algeria
| |
Collapse
|
|
5
|
Sun Y, Chu H. The outcome prediction method of football matches by the quantum neural network based on deep learning. Sci Rep 2025; 15:19875. [PMID: 40481179 PMCID: PMC12144118 DOI: 10.1038/s41598-025-91870-8] [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: 08/19/2024] [Accepted: 02/24/2025] [Indexed: 06/11/2025] Open
Abstract
The precise prediction of football match outcomes holds significant value in the sports domain. However, traditional prediction methods are limited by data complexity and model capabilities, struggling to meet the demands for high accuracy. Quantum neural networks (QNNs) leverage the unique quantum properties of quantum bits (qubits) such as superposition and entanglement. They have enhanced information processing capabilities and potential pattern mining abilities when dealing with vast, high-dimensional, and complex football match data. This makes QNNs a superior choice compared to traditional neural networks and other advanced models for football match prediction. This study focuses on a deep learning (DL)-based QNN model, aiming to construct and optimize this model to analyze historical football match data for high-precision predictions of future match outcomes. Specifically, detailed match records from 2008 to 2022 of major European football leagues were obtained from the "European Football Database" public dataset on Kaggle. The data includes various factors such as match outcomes, team information, player stats, and match venues. The data are cleaned, standardized, and feature-engineered to meet the input requirements of neural network models. A multilayer perceptron model consisting of an input layer, multiple hidden layers, and an output layer is designed and implemented. During the model training phase, gradient descent is used to optimize weight parameters, and quantum algorithms are integrated to continuously adjust network weights to minimize prediction errors. The model is trained, parameter tuning is completed, and performance is evaluated using the training, validation, and independent test sets. The model's effectiveness is measured using indicators such as F1 score, accuracy, and recall. The study results indicate that the optimized QNN model significantly outperforms other advanced models in prediction accuracy. The optimized QNN model has an improvement of more than 20.5% in precision, an enhancement of over 23.2% in recall, and an increase of over 22.3% and 21.8% in accuracy and F1 score. Additionally, the model predicts the championship probabilities for Spain, France, England, and the Netherlands in the European Championship as 31.72%, 27.61%, 22.58%, and 18.09%, respectively. This study innovatively applies the optimized QNN model to outcome prediction in football matches, validating its effectiveness in the sports prediction field. It provides new ideas and methods for football match outcome prediction while offering valuable references for developing prediction models for other sports events. By integrating public data with DL technology, this study lays the foundation for the practical application of sports data analysis and prediction models, holding significant theoretical and practical value. Furthermore, future research can further explore the integration of QNN models with mathematical analysis systems, expanding their application scenarios in the real world. For example, sports betting agencies are provided with more accurate risk assessments, assisting teams in formulating more scientific tactical strategies, and optimizing event organization arrangements, to fully leverage their potential value.
Collapse
Affiliation(s)
- Yang Sun
- College of Physical Education and Health Science, Chongqing Normal University, Chongqing City, 401331, China
| | - Hongyang Chu
- Sports Training College, Tianjin University of Sport, Tianjin City, 301617, China.
| |
Collapse
|
|
6
|
Shabani F, Jodeiri A, Mohammad-Alizadeh-Charandabi S, Abbasalizadeh F, Tanha J, Mirghafourvand M. Developing and validating an artificial intelligence-based application for predicting some pregnancy outcomes: a multi-phase study protocol. Reprod Health 2025; 22:99. [PMID: 40481447 PMCID: PMC12144753 DOI: 10.1186/s12978-025-02048-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2025] [Accepted: 05/25/2025] [Indexed: 06/11/2025] Open
Abstract
Background Pregnancy complications such as preterm birth, low birth weight, gestational diabetes mellitus, preeclampsia, and intrauterine growth restriction significantly affect both maternal and neonatal health outcomes. Early identification of high-risk pregnancies is essential for timely interventions; however, traditional predictive models often lack accuracy. This study aims to develop and validate an AI-based application to improve risk assessment and clinical decision-making regarding pregnancy outcomes through a multi-phase approach. Methods This study comprises three phases. In Phase 1, retrospective case-control data will be collected from medical records, including Mother and Infant System (IMaN), Hospital Information System (HIS), and archived records of women who gave birth at Al-Zahra and Taleghani Educational and Medical Centers in Tabriz between 2022 and 2024. In Phase 2, an artificial intelligence model will be developed using machine learning algorithms such as Random Forest, XGBoost, Support Vector Machines (SVM), and neural networks, followed by model training, validation, and integration into a user-friendly application. Phase 3 will focus on a prospective cohort study of pregnant women attending clinics after 22 weeks of gestation, evaluating the AI model’s predictive performance through metrics like AUROC (area under the receiver operating characteristic curve), sensitivity, specificity, and predictive values, along with real-time data collection. Content validity will be determined through expert reviews. Discussion This study protocol presents a multi-phase approach to developing and validating an AI-based application for predicting pregnancy outcomes. By integrating retrospective data analysis, machine learning, and prospective validation, the study aims to improve early risk detection and maternal care. If successful, this application could support personalized obstetric decision-making. This study aims to develop and validate an artificial intelligence (AI)-based tool to predict pregnancy complications, including preterm birth, low birth weight, gestational diabetes, intrauterine growth restriction, and preeclampsia. The research will be conducted in three phases. First, past medical records from two hospitals will be analysed to identify key risk factors. Next, a machine learning model will be developed and integrated into a user-friendly application. Finally, the tool will be tested on a group of pregnant women to assess its accuracy in predicting adverse pregnancy outcomes. By leveraging AI, this study seeks to enhance early risk detection, enabling healthcare providers to implement timely preventive measures and improve maternal and neonatal health outcomes. If successful, this AI-based application could serve as a valuable resource in maternity care, assisting midwives and doctors in delivering personalized care and reducing complications. The findings could also advance the use of AI technology in obstetric practice, improving decision-making and optimizing healthcare resources.
Collapse
Affiliation(s)
- Fatemeh Shabani
- Midwifery Department, Faculty of Nursing and Midwifery, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Ata Jodeiri
- Faculty of Advanced Medical Sciences, Tabriz University of Medical Sciences, Tabriz, Iran
| | | | - Fatemeh Abbasalizadeh
- Department of Obstetrics and Gynecology, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Jafar Tanha
- Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
| | - Mojgan Mirghafourvand
- Social Determinants of Health Research Center, Faculty of Nursing and Midwifery, Tabriz University of Medical Sciences, Tabriz, Iran.
| |
Collapse
|
|
7
|
Dashtkoohi M, Ghadimi DJ, Moodi F, Behrang N, Khormali E, Salari HM, Cohen NT, Gholipour T, Saligheh Rad H. Focal cortical dysplasia detection by artificial intelligence using MRI: A systematic review and meta-analysis. Epilepsy Behav 2025; 167:110403. [PMID: 40158413 DOI: 10.1016/j.yebeh.2025.110403] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Revised: 02/06/2025] [Accepted: 03/21/2025] [Indexed: 04/02/2025]
Abstract
PURPOSE Focal cortical dysplasia (FCD) is a common cause of pharmacoresistant epilepsy. However, it can be challenging to detect FCD using MRI alone. This study aimed to review and analyze studies that used machine learning and artificial neural networks (ANN) methods as an additional tool to enhance MRI findings in FCD patients. METHODS A systematic search was conducted in four databases (Embase, PubMed, Scopus, and Web of Science). The quality of the studies was assessed using QUADAS-AI, and a bivariate random-effects model was used for analysis. The main outcome analyzed was the sensitivity and specificity of patient-wise outcomes. Heterogeneity among studies was assessed using I2. RESULTS A total of 41 studies met the inclusion criteria, including 24 ANN-based studies and 17 machine learning studies. Meta-analysis of internal validation datasets showed a pooled sensitivity of 0.81 and specificity of 0.92 for AI-based models in detecting FCD lesions. Meta-analysis of external validation datasets yielded a pooled sensitivity of 0.73 and specificity of 0.66. There was moderate heterogeneity among studies in the external validation dataset, but no significant publication bias was found. CONCLUSION Although there is an increasing number of machine learning and ANN-based models for FCD detection, their clinical applicability remains limited. Further refinement and optimization, along with longitudinal studies, are needed to ensure their integration into clinical practice. Addressing the identified limitations and intensifying research efforts will improve their relevance and reliability in real medical scenarios.
Collapse
Affiliation(s)
- Mohammad Dashtkoohi
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; Interdisciplinary Neuroscience Research Program, Tehran University of Medical Sciences, Tehran, Iran
| | - Delaram J Ghadimi
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Farzan Moodi
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Nima Behrang
- Computer Science Department, Sharif University of Technology, Tehran, Iran
| | - Ehsan Khormali
- Student Research Committee, School of Medicine, Mazandaran University of Medical Sciences, Sari, Iran
| | - Hanieh Mobarak Salari
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran
| | - Nathan T Cohen
- Center for Neuroscience Research, Children's National Hospital, The George Washington University School of Medicine, Washington, DC, USA
| | - Taha Gholipour
- Department of Neurosciences, University of California San Diego, La Jolla, CA, USA
| | - Hamidreza Saligheh Rad
- Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran; Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
|
8
|
Ryhänen J, Wong GC, Anttila T, Chung KC. Overview of artificial intelligence in hand surgery. J Hand Surg Eur Vol 2025; 50:738-751. [PMID: 40035151 DOI: 10.1177/17531934251322723] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/05/2025]
Abstract
Artificial intelligence has evolved significantly since its inception, becoming a powerful tool in medicine. This paper provides an overview of the core principles, applications and future directions of artificial intelligence in hand surgery. Artificial intelligence has shown promise in improving diagnostic accuracy, predicting outcomes and assisting in patient education. However, despite its potential, its application in hand surgery is still nascent, with most studies being retrospective and limited by small sample sizes. To harness the full potential of artificial intelligence in hand surgery and support broader adoption, more robust, large-scale studies are needed. Collaboration among researchers, through data sharing and federated learning, is essential for advancing artificial intelligence from experimental to clinically validated tools, ultimately enhancing patient care and clinical workflows.
Collapse
Affiliation(s)
- Jorma Ryhänen
- Musculoskeletal and Plastic Surgery, Department of Hand Surgery, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Gordon C Wong
- Section of Plastic Surgery, Michigan Medicine, Ann Arbor, MI, USA
| | - Turkka Anttila
- Musculoskeletal and Plastic Surgery, Department of Hand Surgery, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
| | - Kevin C Chung
- Section of Plastic Surgery, Department of Surgery, Michigan Medicine, Ann Arbor, MI, USA
| |
Collapse
|
|
9
|
Fishman EK, Soyer P, Hellmann DB, Chu LC. The radiologist and data: Do we add value or is data just data? Clin Imaging 2025; 122:110481. [PMID: 40252272 DOI: 10.1016/j.clinimag.2025.110481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2025] [Revised: 04/02/2025] [Accepted: 04/09/2025] [Indexed: 04/21/2025]
Abstract
Artificial intelligence in radiology critically depends on vast amounts of quality data, and there are controversies surrounding the topic of data ownership. In the current clinical framework, the secondary use of clinical data should be treated as a form of public good to benefit future patients. In this article, we propose that the physicians' input in data curation and interpretation adds value to the data and is crucial for building clinically relevant artificial intelligence models.
Collapse
Affiliation(s)
- Elliot K Fishman
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 600 North Wolfe Street, Baltimore, MD 21287, United States of America
| | - Philippe Soyer
- Université Paris Cité, Faculté de Médicine, 75006 Paris, France; Department of Radiology, Hôpital Cochin, APHP, 75014 Paris, France
| | - David B Hellmann
- Department of Medicine, Johns Hopkins University School of Medicine, 5501 Hopkins Bayview Circle, Baltimore, MD 21224, United States of America
| | - Linda C Chu
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 600 North Wolfe Street, Baltimore, MD 21287, United States of America.
| |
Collapse
|
|
10
|
Aravazhi PS, Gunasekaran P, Benjamin NZY, Thai A, Chandrasekar KK, Kolanu ND, Prajjwal P, Tekuru Y, Brito LV, Inban P. The integration of artificial intelligence into clinical medicine: Trends, challenges, and future directions. Dis Mon 2025; 71:101882. [PMID: 40140300 DOI: 10.1016/j.disamonth.2025.101882] [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] [Indexed: 03/28/2025]
Abstract
BACKGROUND AND OBJECTIVES AI has emerged as a transformative force in clinical medicine, changing the diagnosis, treatment, and management of patients. Tools have been derived for working with ML, DL, and NLP algorithms to analyze large complex medical datasets with unprecedented accuracy and speed, thereby improving diagnostic precision, treatment personalization, and patient care outcomes. For example, CNNs have dramatically improved the accuracy of medical imaging diagnoses, and NLP algorithms have greatly helped extract insights from unstructured data, including EHRs. However, there are still numerous challenges that face AI integration into clinical workflows, including data privacy, algorithmic bias, ethical dilemmas, and problems with the interpretability of "black-box" AI models. These barriers have thus far prevented the widespread application of AI in health care, and its possible trends, obstacles, and future implications are necessary to be systematically explored. The purpose of this paper is, therefore, to assess the current trends in AI applications in clinical medicine, identify those obstacles that are hindering adoption, and identify possible future directions. This research hopes to synthesize evidence from other peer-reviewed articles to provide a more comprehensive understanding of the role that AI plays to advance clinical practices, improve patient outcomes, or enhance decision-making. METHODS A systematic review was done according to the PRISMA guidelines to explore the integration of Artificial Intelligence in clinical medicine, including trends, challenges, and future directions. PubMed, Cochrane Library, Web of Science, and Scopus databases were searched for peer-reviewed articles from 2014 to 2024 with keywords such as "Artificial Intelligence in Medicine," "AI in Clinical Practice," "Machine Learning in Healthcare," and "Ethical Implications of AI in Medicine." Studies focusing on AI application in diagnostics, treatment planning, and patient care reporting measurable clinical outcomes were included. Non-clinical AI applications and articles published before 2014 were excluded. Selected studies were screened for relevance, and then their quality was critically appraised to synthesize data reliably and rigorously. RESULTS This systematic review includes the findings of 8 studies that pointed out the transformational role of AI in clinical medicine. AI tools, such as CNNs, had diagnostic accuracy more than the traditional methods, particularly in radiology and pathology. Predictive models efficiently supported risk stratification, early disease detection, and personalized medicine. Despite these improvements, significant hurdles, including data privacy, algorithmic bias, and resistance from clinicians regarding the "black-box" nature of AI, had yet to be surmounted. XAI has emerged as an attractive solution that offers the promise to enhance interpretability and trust. As a whole, AI appeared promising in enhancing diagnostics, treatment personalization, and clinical workflows by dealing with systemic inefficiencies. CONCLUSION The transformation potential of AI in clinical medicine can transform diagnostics, treatment strategies, and efficiency. Overcoming obstacles such as concerns about data privacy, the danger of algorithmic bias, and difficulties with interpretability may pave the way for broader use and facilitate improvement in patient outcomes while transforming clinical workflows to bring sustainability into healthcare delivery.
Collapse
Affiliation(s)
| | | | | | - Andy Thai
- Internal Medicine, Alameda Health System, Highland Hospital, Oakland, USA
| | | | | | | | - Yogesh Tekuru
- RVM Institute of Medical Sciences and Research Center, Laxmakkapally, India
| | | | - Pugazhendi Inban
- Internal Medicine, St. Mary's General Hospital and Saint Clare's Health, NY, USA.
| |
Collapse
|
|
11
|
Li C, Petruchik O, Grishanina E, Kovalchuk S. Multi-agent norm perception and induction in distributed healthcare. J Biomed Inform 2025; 166:104835. [PMID: 40360136 DOI: 10.1016/j.jbi.2025.104835] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2024] [Revised: 04/19/2025] [Accepted: 04/21/2025] [Indexed: 05/15/2025]
Abstract
This paper presents a Multi-Agent Norm Perception and Induction Learning Model aimed at facilitating the integration of autonomous agent systems into distributed healthcare environments through dynamic interaction processes. The nature of the medical norm system and its sharing channels necessitates distinct approaches for Multi-Agent Systems to learn two types of norms. Building on this foundation, the model enables agents to simultaneously learn descriptive norms, which capture collective tendencies, and prescriptive norms, which dictate ideal behaviors. Through parameterized mixed probability density models and practice-enhanced Markov games, the multi-agent system perceives descriptive norms in dynamic interactions and captures emergent prescriptive norms. We conducted experiments using a dataset from a neurological medical center spanning from 2016 to 2020. The descriptive norm-sharing experiment results demonstrate that the model can effectively perceive the descriptive collective medical norms - which embody the current best clinical practices - across medical communities of varying scales. By contrasting this with the fact that the real descriptive diagnostic practice patterns in the neurological medical center dataset gradually converged over a period of 5 years, we find that the model, through prolonged learning and sharing processes, progressively mirrors the actual descriptive diagnostic trends and collective behavioral tendencies present within the medical community. In the experiment where multiple agents infer prescriptive norms within a dynamic healthcare environment, the agents effectively learned the key clinical protocols within the norm space H, which includes control norms, without developing high belief in invalid norms. Furthermore, the agents' belief update process was relatively smooth, avoiding any discontinuous stepwise updates.
Collapse
Affiliation(s)
- Chao Li
- ITMO University, Saint Petersburg, 197101, Russia.
| | - Olga Petruchik
- Rostov State Medical University, Rostov-on-Don, 344022, Russia.
| | | | | |
Collapse
|
|
12
|
Chen J, Qiu RLJ, Wang T, Momin S, Yang X. A review of artificial intelligence in brachytherapy. J Appl Clin Med Phys 2025; 26:e70034. [PMID: 40014044 DOI: 10.1002/acm2.70034] [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: 11/03/2024] [Revised: 01/25/2025] [Accepted: 01/30/2025] [Indexed: 02/28/2025] Open
Abstract
Artificial intelligence (AI) has the potential to revolutionize brachytherapy's clinical workflow. This review comprehensively examines the application of AI, focusing on machine learning and deep learning, in various aspects of brachytherapy. We analyze AI's role in making brachytherapy treatments more personalized, efficient, and effective. The applications are systematically categorized into seven categories: imaging, preplanning, treatment planning, applicator reconstruction, quality assurance, outcome prediction, and real-time monitoring. Each major category is further subdivided based on cancer type or specific tasks, with detailed summaries of models, data sizes, and results presented in corresponding tables. Additionally, we discuss the limitations, challenges, and ethical concerns of current AI applications, along with perspectives on future directions. This review offers insights into the current advancements, challenges, and the impact of AI on treatment paradigms, encouraging further research to expand its clinical utility.
Collapse
Affiliation(s)
- Jingchu Chen
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
- School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA
| | - Richard L J Qiu
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
| | - Tonghe Wang
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Shadab Momin
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
- School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA
| |
Collapse
|
|
13
|
Orakwue CJ, Tajrishi FZ, Gistand CM, Feng H, Ferdinand KC. Combating cardiovascular disease disparities: The potential role of artificial intelligence. Am J Prev Cardiol 2025; 22:100954. [PMID: 40161231 PMCID: PMC11951981 DOI: 10.1016/j.ajpc.2025.100954] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2024] [Revised: 02/20/2025] [Accepted: 03/07/2025] [Indexed: 04/02/2025] Open
Affiliation(s)
| | - Farbod Zahedi Tajrishi
- Department of Internal Medicine, Tulane University School of Medicine, New Orleans, LA, USA
| | - Constance M. Gistand
- Department of Internal Medicine, Tulane University School of Medicine, New Orleans, LA, USA
| | - Han Feng
- Tulane Research and Innovation for Arrhythmia Discoveries - TRIAD Center, Tulane University School of Medicine, New Orleans, LA, USA
| | - Keith C. Ferdinand
- Section of Cardiology, Tulane University School of Medicine, New Orleans, LA, USA
| |
Collapse
|
|
14
|
Dorfner FJ, Dada A, Busch F, Makowski MR, Han T, Truhn D, Kleesiek J, Sushil M, Adams LC, Bressem KK. Evaluating the effectiveness of biomedical fine-tuning for large language models on clinical tasks. J Am Med Inform Assoc 2025; 32:1015-1024. [PMID: 40190132 DOI: 10.1093/jamia/ocaf045] [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: 11/20/2024] [Accepted: 03/02/2025] [Indexed: 05/21/2025] Open
Abstract
OBJECTIVES Large language models (LLMs) have shown potential in biomedical applications, leading to efforts to fine-tune them on domain-specific data. However, the effectiveness of this approach remains unclear. This study aims to critically evaluate the performance of biomedically fine-tuned LLMs against their general-purpose counterparts across a range of clinical tasks. MATERIALS AND METHODS We evaluated the performance of biomedically fine-tuned LLMs against their general-purpose counterparts on clinical case challenges from NEJM and JAMA, and on multiple clinical tasks, such as information extraction, document summarization and clinical coding. We used a diverse set of benchmarks specifically chosen to be outside the likely fine-tuning datasets of biomedical models, ensuring a fair assessment of generalization capabilities. RESULTS Biomedical LLMs generally underperformed compared to general-purpose models, especially on tasks not focused on probing medical knowledge. While on the case challenges, larger biomedical and general-purpose models showed similar performance (eg, OpenBioLLM-70B: 66.4% vs Llama-3-70B-Instruct: 65% on JAMA), smaller biomedical models showed more pronounced underperformance (OpenBioLLM-8B: 30% vs Llama-3-8B-Instruct: 64.3% on NEJM). Similar trends appeared across CLUE benchmarks, with general-purpose models often achieving higher scores in text generation, question answering, and coding. Notably, biomedical LLMs also showed a higher tendency to hallucinate. DISCUSSION Our findings challenge the assumption that biomedical fine-tuning inherently improves LLM performance, as general-purpose models consistently performed better on unseen medical tasks. Retrieval-augmented generation may offer a more effective strategy for clinical adaptation. CONCLUSION Fine-tuning LLMs on biomedical data may not yield the anticipated benefits. Alternative approaches, such as retrieval augmentation, should be further explored for effective and reliable clinical integration of LLMs.
Collapse
Affiliation(s)
- Felix J Dorfner
- Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin 10117, Germany
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA 02129, United States
| | - Amin Dada
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), Essen 45131, Germany
| | - Felix Busch
- Department of Radiology, Klinikum Rechts Der Isar, Technical University Munich, Munich 81675, Germany
| | - Marcus R Makowski
- Department of Radiology, Klinikum Rechts Der Isar, Technical University Munich, Munich 81675, Germany
| | - Tianyu Han
- Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen 52074, Germany
| | - Daniel Truhn
- Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen 52074, Germany
| | - Jens Kleesiek
- Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), Essen 45131, Germany
- Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR), Essen 45147, Germany
- German Cancer Consortium (DKTK, Partner Site Essen), Heidelberg, Germany
- Department of Physics, TU Dortmund, Dortmund 44227, Germany
| | - Madhumita Sushil
- Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA 94158, United States
| | - Lisa C Adams
- Department of Radiology, Klinikum Rechts Der Isar, Technical University Munich, Munich 81675, Germany
| | - Keno K Bressem
- Department of Radiology, Klinikum Rechts Der Isar, Technical University Munich, Munich 81675, Germany
- German Heart Center Munich, Technical University Munich, Munich 80636, Germany
| |
Collapse
|
|
15
|
Alcaraz JML, Bouma H, Strodthoff N. Enhancing clinical decision support with physiological waveforms - A multimodal benchmark in emergency care. Comput Biol Med 2025; 192:110196. [PMID: 40311469 DOI: 10.1016/j.compbiomed.2025.110196] [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: 10/15/2024] [Revised: 03/04/2025] [Accepted: 04/09/2025] [Indexed: 05/03/2025]
Abstract
BACKGROUND AI-driven prediction algorithms have the potential to enhance emergency medicine by enabling rapid and accurate decision-making regarding patient status and potential deterioration. However, the integration of multimodal data, including raw waveform signals, remains underexplored in clinical decision support. METHODS We present a dataset and benchmarking protocol designed to advance multimodal decision support in emergency care. Our models utilize demographics, biometrics, vital signs, laboratory values, and electrocardiogram (ECG) waveforms as inputs to predict both discharge diagnoses and patient deterioration. RESULTS The diagnostic model achieves area under the receiver operating curve (AUROC) scores above 0.8 for 609 out of 1,428 conditions, covering both cardiac (e.g., myocardial infarction) and non-cardiac (e.g., renal disease, diabetes) diagnoses. The deterioration model attains AUROC scores above 0.8 for 14 out of 15 targets, accurately predicting critical events such as cardiac arrest, mechanical ventilation, ICU admission, and mortality. CONCLUSIONS Our study highlights the positive impact of incorporating raw waveform data into decision support models, improving predictive performance. By introducing a unique, publicly available dataset and baseline models, we provide a foundation for measurable progress in AI-driven decision support for emergency care.
Collapse
Affiliation(s)
- Juan Miguel Lopez Alcaraz
- AI4Health Division, Carl von Ossietzky Universität Oldenburg, Ammerländer Heerstraße 114-118, Oldenburg, 26129, Lower Saxony, Germany.
| | - Hjalmar Bouma
- Department of Internal Medicine, Department of Acute Care, and Department of Clinical Pharmacy & Pharmacology, University Medical Center Groningen, Hanzeplein 1, Groningen, 9713, Groningen, Netherlands.
| | - Nils Strodthoff
- AI4Health Division, Carl von Ossietzky Universität Oldenburg, Ammerländer Heerstraße 114-118, Oldenburg, 26129, Lower Saxony, Germany.
| |
Collapse
|
|
16
|
Gim N, Blazes M, Sánchez CI, Zalunardo L, Corradetti G, Elze T, Honda N, Waheed NK, Cairns AM, Canto-Soler MV, Domalpally A, Durbin M, Ferrara D, Hu J, Nair P, Sadda SR, Keenan TDL, Lee CS. Retinal imaging in an era of open science and privacy protection. Exp Eye Res 2025; 255:110341. [PMID: 40090567 PMCID: PMC12059805 DOI: 10.1016/j.exer.2025.110341] [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: 10/22/2024] [Revised: 02/27/2025] [Accepted: 03/12/2025] [Indexed: 03/18/2025]
Abstract
Artificial intelligence (AI) holds great promise for analyzing complex data to advance patient care and disease research. For example, AI interpretation of retinal imaging may enable the development of noninvasive retinal biomarkers of systemic disease. One potential limitation, however, is government regulation regarding retinal imaging as biometric data, which has been recently under debate in the United States. Although careful regard for patient privacy is key to maintaining trust in the widespread use of AI in healthcare, the designation of retinal imaging as biometric data would greatly restrict retinal biomarker research. There are several reasons why retinal imaging should not be considered biometric data. Unlike images of the iris, high quality images of the retina are more difficult to obtain, requiring specialized training and equipment, and often requiring pupil dilation for optimal quality. In addition, retinal imaging features can vary over time with changes in health status, and retinal images are not currently linked to any large identification databases. While the protection of patient privacy is imperative, there is also a need for large retinal imaging datasets to advance AI research. Given the limitations of retinal imaging as a source of biometric data, the research community should work to advocate for the continued use of retinal imaging in AI research.
Collapse
Affiliation(s)
- Nayoon Gim
- Department of Ophthalmology, University of Washington, Seattle, WA, USA; Roger and Angie Karalis Johnson Retina Center, Seattle, WA, USA; Department of Bioengineering, University of Washington, Seattle, WA, USA
| | - Marian Blazes
- Department of Ophthalmology, University of Washington, Seattle, WA, USA; Roger and Angie Karalis Johnson Retina Center, Seattle, WA, USA
| | - Clara I Sánchez
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Center, Amsterdam, the Netherlands; Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, University of Amsterdam, Amsterdam, the Netherlands
| | | | - Giulia Corradetti
- Doheny Eye Institute, Pasadena, CA, USA; Department of Ophthalmology, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA
| | - Tobias Elze
- Mass. Eye and Ear, Department of Ophthalmology, Harvard Medical School, Boston, MA, USA
| | | | | | | | - M Valeria Canto-Soler
- CellSight Ocular Stem Cell and Regeneration Research Program, Department of Ophthalmology, Sue Anschutz-Rodgers Eye Center, University of Colorado, Aurora, CO, USA
| | - Amitha Domalpally
- Wisconsin Reading Center, Department of Ophthalmology and Visual Sciences, University of Wisconsin, Madison, WI, USA
| | | | | | - Jewel Hu
- Doheny Eye Institute, Pasadena, CA, USA
| | - Prashant Nair
- Proceedings of the National Academy of Sciences, Washington, DC, USA
| | - Srinivas R Sadda
- Doheny Eye Institute, Pasadena, CA, USA; Department of Ophthalmology, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA
| | - Tiarnan D L Keenan
- Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, MD, USA
| | - Cecilia S Lee
- Department of Ophthalmology, University of Washington, Seattle, WA, USA; Roger and Angie Karalis Johnson Retina Center, Seattle, WA, USA.
| |
Collapse
|
|
17
|
Omar M, Watad A, McGonagle D, Soffer S, Glicksberg BS, Nadkarni GN, Klang E. The role of deep learning in diagnostic imaging of spondyloarthropathies: a systematic review. Eur Radiol 2025; 35:3661-3672. [PMID: 39658683 PMCID: PMC12081588 DOI: 10.1007/s00330-024-11261-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2024] [Revised: 09/22/2024] [Accepted: 11/02/2024] [Indexed: 12/12/2024]
Abstract
AIM Diagnostic imaging is an integral part of identifying spondyloarthropathies (SpA), yet the interpretation of these images can be challenging. This review evaluated the use of deep learning models to enhance the diagnostic accuracy of SpA imaging. METHODS Following PRISMA guidelines, we systematically searched major databases up to February 2024, focusing on studies that applied deep learning to SpA imaging. Performance metrics, model types, and diagnostic tasks were extracted and analyzed. Study quality was assessed using QUADAS-2. RESULTS We analyzed 21 studies employing deep learning in SpA imaging diagnosis across MRI, CT, and X-ray modalities. These models, particularly advanced CNNs and U-Nets, demonstrated high accuracy in diagnosing SpA, differentiating arthritis forms, and assessing disease progression. Performance metrics frequently surpassed traditional methods, with some models achieving AUCs up to 0.98 and matching expert radiologist performance. CONCLUSION This systematic review underscores the effectiveness of deep learning in SpA imaging diagnostics across MRI, CT, and X-ray modalities. The studies reviewed demonstrated high diagnostic accuracy. However, the presence of small sample sizes in some studies highlights the need for more extensive datasets and further prospective and external validation to enhance the generalizability of these AI models. KEY POINTS Question How can deep learning models improve diagnostic accuracy in imaging for spondyloarthropathies (SpA), addressing challenges in early detection and differentiation from other forms of arthritis? Findings Deep learning models, especially CNNs and U-Nets, showed high accuracy in SpA imaging across MRI, CT, and X-ray, often matching or surpassing expert radiologists. Clinical relevance Deep learning models can enhance diagnostic precision in SpA imaging, potentially reducing diagnostic delays and improving treatment decisions, but further validation on larger datasets is required for clinical integration.
Collapse
Affiliation(s)
- Mahmud Omar
- Tel-Aviv University, Faculty of Medicine, Tel-Aviv, Israel.
| | - Abdulla Watad
- Tel-Aviv University, Faculty of Medicine, Tel-Aviv, Israel
- Department of Medicine B and Zabludowicz Center for Autoimmune Diseases, Sheba Medical Center, Tel-Hashomer, Ramat-Gan, Israel
- Section of Musculoskeletal Disease, NIHR Leeds Musculoskeletal Biomedical Research Centre, Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Chapel Allerton Hospital, Leeds, UK
| | - Dennis McGonagle
- Section of Musculoskeletal Disease, NIHR Leeds Musculoskeletal Biomedical Research Centre, Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Chapel Allerton Hospital, Leeds, UK
| | - Shelly Soffer
- Institute of Hematology, Davidoff Cancer Center, Rabin Medical Center, Petah-Tikva, Israel
| | - Benjamin S Glicksberg
- The Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Girish N Nadkarni
- The Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
- Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Eyal Klang
- The Charles Bronfman Institute of Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, USA
- Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
|
18
|
Kühne S, Jacobsen J, Legewie N, Dollmann J. Attitudes Toward AI Usage in Patient Health Care: Evidence From a Population Survey Vignette Experiment. J Med Internet Res 2025; 27:e70179. [PMID: 40424613 DOI: 10.2196/70179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2024] [Revised: 02/28/2025] [Accepted: 04/11/2025] [Indexed: 05/29/2025] Open
Abstract
BACKGROUND The integration of artificial intelligence (AI) holds substantial potential to alter diagnostics and treatment in health care settings. However, public attitudes toward AI, including trust and risk perception, are key to its ethical and effective adoption. Despite growing interest, empirical research on the factors shaping public support for AI in health care (particularly in large-scale, representative contexts) remains limited. OBJECTIVE This study aimed to investigate public attitudes toward AI in patient health care, focusing on how AI attributes (autonomy, costs, reliability, and transparency) shape perceptions of support, risk, and personalized care. In addition, it examines the moderating role of sociodemographic characteristics (gender, age, educational level, migration background, and subjective health status) in these evaluations. Our study offers novel insights into the relative importance of AI system characteristics for public attitudes and acceptance. METHODS We conducted a factorial vignette experiment with a probability-based survey of 3030 participants from Germany's general population. Respondents were presented with hypothetical scenarios involving AI applications in diagnosis and treatment in a hospital setting. Linear regression models assessed the relative influence of AI attributes on the dependent variables (support, risk perception, and personalized care), with additional subgroup analyses to explore heterogeneity by sociodemographic characteristics. RESULTS Mean values between 4.2 and 4.4 on a 1-7 scale indicate a generally neutral to slightly negative stance toward AI integration in terms of general support, risk perception, and personalized care expectations, with responses spanning the full scale from strong support to strong opposition. Among the 4 dimensions, reliability emerges as the most influential factor (percentage of explained variance [EV] of up to 10.5%). Respondents expect AI to not only prevent errors but also exceed current reliability standards while strongly disapproving of nontraceable systems (transparency is another important factor, percentage of EV of up to 4%). Costs and autonomy play a comparatively minor role (percentage of EVs of up to 1.5% and 1.3%), with preferences favoring collaborative AI systems over autonomous ones, and higher costs generally leading to rejection. Heterogeneity analysis reveals limited sociodemographic differences, with education and migration background influencing attitudes toward transparency and autonomy, and gender differences primarily affecting cost-related perceptions. Overall, attitudes do not substantially differ between AI applications in diagnosis versus treatment. CONCLUSIONS Our study fills a critical research gap by identifying the key factors that shape public trust and acceptance of AI in health care, particularly reliability, transparency, and patient-centered approaches. Our findings provide evidence-based recommendations for policy makers, health care providers, and AI developers to enhance trust and accountability, key concerns often overlooked in system development and real-world applications. The study highlights the need for targeted policy and educational initiatives to support the responsible integration of AI in patient care.
Collapse
Affiliation(s)
- Simon Kühne
- Faculty of Sociology, Bielefeld University, Bielefeld, Germany
| | - Jannes Jacobsen
- Data-Method-Monitoring Cluster, German Center for Integration and Migration Research, Berlin, Germany
| | - Nicolas Legewie
- Institute of Sociology, University of Münster, Münster, Germany
| | - Jörg Dollmann
- Data-Method-Monitoring Cluster, German Center for Integration and Migration Research, Berlin, Germany
- Mannheim Centre for European Social Research (MZES), University of Mannheim, Mannheim, Germany
| |
Collapse
|
|
19
|
Hong Y, Pan T, Zhu S, Hu M, Zhou Z, Xu T. A visualization system for intelligent diagnosis and statistical analysis of oral diseases based on panoramic radiography. Sci Rep 2025; 15:18222. [PMID: 40414918 DOI: 10.1038/s41598-025-01733-5] [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: 12/05/2024] [Accepted: 05/07/2025] [Indexed: 05/27/2025] Open
Abstract
Panoramic radiography is an essential auxiliary diagnostic tool for oral diseases. It is a difficult and time-consuming task to conduct extensive panoramic radiography interpretation. These challenges are exacerbated by the creation of electronic medical records and the investigation of oral diseases using collective data. So, we develop a visualization system based on panoramic radiographs. Its function focuses on the intelligent diagnosis and statistical analysis of oral diseases. Firstly, we provide a human-machine collaborative tool for the diagnosis and data extraction of oral diseases in panoramic radiographs. After that, the system generates electronic medical records, including visual charts of oral health status and radiology reports. We further develop statistical correlation analysis to visually evaluate and interactively explore the statistical data from oral health surveys. We conduct intelligent diagnosis, obtain the electronic medical records and do collective analysis based on 521 panoramic radiographs. The available analyses cover disease-prone teeth, disease distribution per tooth position and association of age, sex with oral diseases. The results are reported from a comprehensive case study showing that our system can improve the efficiency in disease detection and data mining. It can also fuel research studies in the field of public oral health and provide robust support for oral healthcare strategies.
Collapse
Affiliation(s)
- Yue Hong
- Department of Stomatology, First Affiliated Hospital, Zhejiang University, Hangzhou, China
- School of Medicine, Zhejiang University, Hangzhou, China
| | - Tianya Pan
- Intelligent Big Data Visualization Lab, Hangzhou Dianzi University, Hangzhou, China
| | - Shenji Zhu
- Intelligent Big Data Visualization Lab, Hangzhou Dianzi University, Hangzhou, China
| | - Miaoxin Hu
- Intelligent Big Data Visualization Lab, Hangzhou Dianzi University, Hangzhou, China
| | - Zhiguang Zhou
- Intelligent Big Data Visualization Lab, Hangzhou Dianzi University, Hangzhou, China.
| | - Ting Xu
- Department of Stomatology, First Affiliated Hospital, Zhejiang University, Hangzhou, China.
- School of Medicine, Zhejiang University, Hangzhou, China.
| |
Collapse
|
|
20
|
Mahl D, Schäfer MS, Voinea SA, Adib K, Duncan B, Salvi C, Novillo-Ortiz D. Responsible artificial intelligence in public health: a Delphi study on risk communication, community engagement and infodemic management. BMJ Glob Health 2025; 10:e018545. [PMID: 40409762 DOI: 10.1136/bmjgh-2024-018545] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2024] [Accepted: 04/08/2025] [Indexed: 05/25/2025] Open
Abstract
INTRODUCTION Artificial intelligence (AI) holds the potential to fundamentally transform how public health authorities use risk communication, community engagement and infodemic management (RCCE-IM) to prepare for, manage and mitigate public health emergencies. As research on this crucial transformation remains limited, we conducted a modified Delphi study on the impact of AI on RCCE-IM. METHODS In two successive surveys, 54 experts-scholars with expertise in public health, digital health, health communication, risk communication and AI, as well as RCCE-IM professionals-from 27 countries assessed opportunities, challenges and risks of AI, anticipated future scenarios, and identified principles and actions to facilitate the responsible use of AI. The first Delphi round followed an open, exploratory approach, while the second sought to prioritise and rank key findings from the initial phase. Qualitative thematic analysis and statistical methods were applied to evaluate responses. RESULTS According to the expert panel, AI could be highly beneficial, particularly for risk communication (eg, tailoring messages) and infodemic management (eg, social listening), while its utility for fostering community engagement was viewed more critically. Challenges and risks affect all three components of RCCE-IM equally, with algorithmic bias and privacy breaches being of particular concern. Panellists anticipated both optimistic (eg, democratisation of information) and pessimistic (eg, erosion of public trust) future scenarios. They identified seven principles for the responsible use of AI for public health practices, with equity and transparency being the most important. Prioritised actions ranged from regulatory measures, resource allocation and feedback loops to capacity building, public trust initiatives and educational training. CONCLUSION To responsibly navigate the multifaceted opportunities, challenges and risks of AI for RCCE-IM in public health emergencies, clear guiding principles, ongoing critical evaluation and training as well as societal collaboration across countries are needed.
Collapse
Affiliation(s)
- Daniela Mahl
- Department of Communication and Media Research, University of Zurich, Zurich, Switzerland
| | - Mike S Schäfer
- Department of Communication and Media Research, University of Zurich, Zurich, Switzerland
| | | | - Keyrellous Adib
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | - Ben Duncan
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | - Cristiana Salvi
- World Health Organization Regional Office for Europe, Copenhagen, Denmark
| | | |
Collapse
|
|
21
|
Alter IL, Dias C, Briano J, Rameau A. Digital health technologies in swallowing care from screening to rehabilitation: A narrative review. Auris Nasus Larynx 2025; 52:319-326. [PMID: 40403345 DOI: 10.1016/j.anl.2025.05.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2025] [Revised: 05/14/2025] [Accepted: 05/16/2025] [Indexed: 05/24/2025]
Abstract
OBJECTIVES Digital health technologies (DHTs) have rapidly advanced in the past two decades, through developments in mobile and wearable devices and most recently with the explosion of artificial intelligence (AI) capabilities and subsequent extension into the health space. DHT has myriad potential applications to deglutology, many of which have undergone promising investigations and developments in recent years. We present the first literature review on applications of DHT in swallowing health, from screening to therapeutics. Public health interventions for swallowing care are increasingly needed in the setting of aging populations in the West and East Asia, and DHT may offer a scalable and low-cost solution. METHODS A narrative review was performed using PubMed and Google Scholar to identify recent research on applications of AI and digital health in swallow practice. Database searches, conducted in September 2024, included terms such as "digital," "AI," "machine learning," "tools" in combination with "deglutition," "Otolaryngology," "Head and Neck," "speech language pathology," "swallow," and "dysphagia." Primary literature pertaining to digital health in deglutology was included for review. RESULTS We review the various applications of DHT in swallowing care, including prevention, screening, diagnosis, treatment planning and rehabilitation. CONCLUSION DHT may offer innovative and scalable solutions for swallowing care as public health needs grow and in the setting of limited specialized healthcare workforce. These technological advances are also being explored as time and resource saving solutions at many points of care in swallow practice. DHT could bring affordable and accurate information for self-management of dysphagia to broader patient populations that otherwise lack access to expert providers.
Collapse
Affiliation(s)
- Isaac L Alter
- Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medical College, 240 E 59 St, NY, NY 10022, USA
| | - Carla Dias
- Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medical College, 240 E 59 St, NY, NY 10022, USA
| | - Jack Briano
- Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medical College, 240 E 59 St, NY, NY 10022, USA
| | - Anaïs Rameau
- Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medical College, 240 E 59 St, NY, NY 10022, USA.
| |
Collapse
|
|
22
|
Jeong ES, Hwang IH, Han SW. Quantitative analysis of EXAFS data sets using deep reinforcement learning. Sci Rep 2025; 15:17417. [PMID: 40394175 PMCID: PMC12092777 DOI: 10.1038/s41598-025-94376-5] [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: 08/27/2024] [Accepted: 03/13/2025] [Indexed: 05/22/2025] Open
Abstract
Extended X-ray absorption fine structure (EXAFS) serves as a unique tool for accurately characterizing the local structural properties surrounding specific atoms. However, the quantitative analysis of EXAFS data demands significant effort. Artificial intelligence (AI) techniques, including deep reinforcement learning (RL) methods, present a promising avenue for the rapid and precise analysis of EXAFS data sets. Unlike other AI approaches, a deep RL method utilizing reward values does not necessitate a large volume of pre-prepared data sets for training the neural networks of the AI system. We explored the application of a deep RL method for the quantitative analysis of EXAFS data sets, utilizing the reciprocal of the R-factor of a fit as the reward metric. The deep RL method effectively determined the local structural properties of PtOx and Zn-O complexes by fitting a series of EXAFS data sets to theoretical EXAFS calculations without imposing specific constraints. Looking ahead, AI has the potential to independently analyze any EXAFS data, although there are still challenges to overcome.
Collapse
Affiliation(s)
- Eun-Suk Jeong
- Department of Physics Education, Institute of Fusion Science, and Institute of Science Education, Jeonbuk National University, Jeonju, 54896, Korea
| | - In-Hui Hwang
- Pohang Accelerator Laboratory, POSTECH, Pohang, 37673, Korea
| | - Sang-Wook Han
- Department of Physics Education, Institute of Fusion Science, and Institute of Science Education, Jeonbuk National University, Jeonju, 54896, Korea.
| |
Collapse
|
|
23
|
Shi L. Enhancing medical explainability in deep learning for age-related macular degeneration diagnosis. Sci Rep 2025; 15:16975. [PMID: 40374798 PMCID: PMC12081899 DOI: 10.1038/s41598-025-01496-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2025] [Accepted: 05/05/2025] [Indexed: 05/18/2025] Open
Abstract
Deep learning models hold significant promise for disease diagnosis but often lack transparency in their decision-making processes, limiting trust and hindering clinical adoption. This study introduces a novel multi-task learning framework to enhance the medical explainability of deep learning models for diagnosing age-related macular degeneration (AMD) using fundus images. The framework simultaneously performs AMD classification and lesion segmentation, allowing the model to support its diagnoses with AMD-associated lesions identified through segmentation. In addition, we perform an in-depth interpretability analysis of the model, proposing the Medical Explainability Index (MXI), a novel metric that quantifies the medical relevance of the generated heatmaps by comparing them with the model's lesion segmentation output. This metric provides a measurable basis to evaluate whether the model's decisions are grounded in clinically meaningful information. The proposed method was trained and evaluated on the Automatic Detection Challenge on Age-Related Macular Degeneration (ADAM) dataset. Experimental results demonstrate robust performance, achieving an area under the curve (AUC) of 0.96 for classification and a Dice similarity coefficient (DSC) of 0.59 for segmentation, outperforming single-task models. By offering interpretable and clinically relevant insights, our approach aims to foster greater trust in AI-driven disease diagnosis and facilitate its adoption in clinical practice.
Collapse
Affiliation(s)
- Lily Shi
- The Harker School, San Jose, CA, 95129, USA.
| |
Collapse
|
|
24
|
Loni M, Poursalim F, Asadi M, Gharehbaghi A. A review on generative AI models for synthetic medical text, time series, and longitudinal data. NPJ Digit Med 2025; 8:281. [PMID: 40374917 DOI: 10.1038/s41746-024-01409-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2024] [Accepted: 12/22/2024] [Indexed: 05/18/2025] Open
Abstract
This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.
Collapse
Affiliation(s)
- Mohammad Loni
- School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden.
| | | | - Mehdi Asadi
- ICT Department, Turku University of Applied Sciences, Turku, Finland
| | - Arash Gharehbaghi
- Department of Biomedical Engineering, Linköping University, Linköping, Sweden.
| |
Collapse
|
|
25
|
Lu X, Gao X, Wang X, Gong Z, Cheng J, Hu W, Wu S, Wang R, Li X. Comparison of medical history documentation efficiency and quality based on GPT-4o: a study on the comparison between residents and artificial intelligence. Front Med (Lausanne) 2025; 12:1545730. [PMID: 40438356 PMCID: PMC12116629 DOI: 10.3389/fmed.2025.1545730] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2024] [Accepted: 04/24/2025] [Indexed: 06/01/2025] Open
Abstract
Background As medical technology advances, physicians' responsibilities in clinical practice continue to increase, with medical history documentation becoming an essential component. Artificial Intelligence (AI) technologies, particularly advances in Natural Language Processing (NLP), have introduced new possibilities for medical documentation. This study aims to evaluate the efficiency and quality of medical history documentation by ChatGPT-4o compared to resident physicians and explore the potential applications of AI in clinical documentation. Methods Using a non-inferiority design, this study compared the documentation time and quality scores between 5 resident physicians from the hematology department (with an average of 2.4 years of clinical experience) and ChatGPT-4o based on identical case materials. Medical history quality was evaluated by two attending physicians with over 10 years of clinical experience using ten case content criteria. Data were analyzed using paired t-tests and Wilcoxon signed-rank tests, with Kappa coefficients used to assess scoring consistency. Detailed scoring criteria included completeness (coverage of history elements), accuracy (correctness of information), logic (organization and coherence of content), and professionalism (appropriate use of medical terminology and format), each rated on a 10-point scale. Results In terms of medical history quality, ChatGPT-4o achieved an average score of 88.9, while resident physicians scored 89.6, with no statistically significant difference between the two (p = 0.25). The Kappa coefficient between the two evaluators was 0.82, indicating good consistency in scoring. Non-inferiority testing showed that ChatGPT-4o's quality scores fell within the preset non-inferiority margin (5 points), indicating that its documentation quality was not inferior to that of resident physicians. ChatGPT-4o's average documentation time was 40.1 s, significantly shorter than the resident physicians' average of 14.9 min (p < 0.001). Conclusion While maintaining quality comparable to resident physicians, ChatGPT-4o significantly reduced the time required for medical history documentation. Despite these positive results, practical considerations such as data preprocessing, data security, and privacy protection must be addressed in real-world applications. Future research should further explore ChatGPT-4o's capabilities in handling complex cases and its applicability across different clinical settings.
Collapse
Affiliation(s)
- Xiaojing Lu
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xinqi Gao
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Xinyi Wang
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zhenye Gong
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Jie Cheng
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Weiguo Hu
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Shaun Wu
- WORK Medical Technology Group LTD, Hangzhou, China
| | - Rong Wang
- Shanghai Resident Sandardized Training Center, Shanghai, China
| | - Xiaoyang Li
- Department of Medical Education, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| |
Collapse
|
|
26
|
Dai F, Yao S, Wang M, Zhu Y, Qiu X, Sun P, Qiu C, Yin J, Shen G, Sun J, Wang M, Wang Y, Yang Z, Sang J, Wang X, Sun F, Cai W, Zhang X, Lu H. Improving AI models for rare thyroid cancer subtype by text guided diffusion models. Nat Commun 2025; 16:4449. [PMID: 40360460 PMCID: PMC12075465 DOI: 10.1038/s41467-025-59478-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2024] [Accepted: 04/24/2025] [Indexed: 05/15/2025] Open
Abstract
Artificial intelligence applications in oncology imaging often struggle with diagnosing rare tumors. We identify significant gaps in detecting uncommon thyroid cancer types with ultrasound, where scarce data leads to frequent misdiagnosis. Traditional augmentation strategies do not capture the unique disease variations, hindering model training and performance. To overcome this, we propose a text-driven generative method that fuses clinical insights with image generation, producing synthetic samples that realistically reflect rare subtypes. In rigorous evaluations, our approach achieves substantial gains in diagnostic metrics, surpasses existing methods in authenticity and diversity measures, and generalizes effectively to other private and public datasets with various rare cancers. In this work, we demonstrate that text-guided image augmentation substantially enhances model accuracy and robustness for rare tumor detection, offering a promising avenue for more reliable and widespread clinical adoption.
Collapse
Affiliation(s)
- Fang Dai
- Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
- SJTU-Yale Joint Center of Biostatistics and Data Science, Technical Center for Digital Medicine, National Center for Translational Medicine, Shanghai Jiao Tong University, Shanghai, China
- Department of Clinical Laboratory Medicine, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, PR China
| | - Siqiong Yao
- SJTU-Yale Joint Center of Biostatistics and Data Science, Technical Center for Digital Medicine, National Center for Translational Medicine, Shanghai Jiao Tong University, Shanghai, China.
| | - Min Wang
- Department of Critical Care Medicine, Jiuquan Hospital of Shanghai General Hospital, Shanghai Jiaotong University School of Medicine, Jiuquan, Gansu, PR China
| | - Yicheng Zhu
- Department of Ultrasound, Pudong New Area People's Hospital Affiliated to Shanghai University of Medicine and Health Sciences, Shanghai, PR China
| | - Xiangjun Qiu
- Department of Automation, Tsinghua University, Beijing, PR China
| | - Peng Sun
- Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
| | - Cheng Qiu
- Medical college, Nantong University, Nantong, Jiangsu, PR China
| | - Jisheng Yin
- Shcool of Artificial Intelligence, University of Chinese Academy of sciences, Beijing, PR China
| | - Guangtai Shen
- Xin'an League People's Hospital, Xing'an League, Inner Mongolia, PR China
| | - Jingjing Sun
- Department of Ultrasound, Shanghai Fourth People's Hospital Affiliated to Tongji University, Shanghai, PR China
| | - Maofeng Wang
- Department of Biomedical Sciences Laboratory, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang, PR China
| | - Yun Wang
- Department of Hepatobiliary pancreatic center, Xuzhou City Central Hospital, Xuzhou, Jiangsu, China
| | - Zheyu Yang
- Department of General Surgery, Ruijin Hospital, Shanghai Jiaotong University School of medicine, Shanghai, PR China
| | - Jianfeng Sang
- Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, Jiangsu, PR China
| | - Xiaolei Wang
- Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
| | - Fenyong Sun
- Department of Clinical Laboratory Medicine, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, PR China.
| | - Wei Cai
- Department of General Surgery, Ruijin Hospital, Shanghai Jiaotong University School of medicine, Shanghai, PR China.
| | | | - Hui Lu
- Department of Bioinformatics and Biostatistics, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China.
- SJTU-Yale Joint Center of Biostatistics and Data Science, Technical Center for Digital Medicine, National Center for Translational Medicine, Shanghai Jiao Tong University, Shanghai, China.
- Institute of Bioinformatics, Shanghai Academy of Experimental Medicine, Shanghai, China.
| |
Collapse
|
|
27
|
Jantscher M, Gunzer F, Reishofer G, Kern R. Causal insights from clinical information in radiology: Enhancing future multimodal AI development. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 268:108810. [PMID: 40378553 DOI: 10.1016/j.cmpb.2025.108810] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/08/2024] [Revised: 04/09/2025] [Accepted: 04/24/2025] [Indexed: 05/19/2025]
Abstract
PURPOSE This study investigates the causal mechanisms underlying radiology report generation by analyzing how clinical information and prior imaging examinations contribute to annotation shifts. We systematically estimate why and how biases manifest, providing insights into the data generation process that influences radiology reporting. METHODS This retrospective study analyzes 172,380 chest X-ray reports from 45,561 distinct patients in the MIMIC-IV CXR database. The study focuses on conditional effects for the diseases pneumonia, pleurisy, heart failure, rib fracture, and COPD. Propensity score matching is employed to balance the treatment and control groups, followed by logistic regression and neural network models to estimate causal effects. Statistical analysis involves calculating risk differences and 95% confidence intervals to determine significance (p ≤ 0.05). Sensitivity analysis is deployed to estimate the robustness of the effect estimates. RESULTS The inclusion of clinical questions significantly influences the reporting of key observational findings. For instance, the probability of mentioning cardiomegaly increases by 15% (p ≤ 0.05) when a clinical question is posed conditioned on rib fracture. Similar effects are observed for support devices across multiple diseases. However, the impact of clinical information varies by disease. For instance, in the presence of clinical questions, the mention of pneumonia increases significantly for one disease, while for others there is no significant effect. CONCLUSION This study demonstrates how annotation bias in radiology reports arises from clinical context and prior imaging access. Understanding these causal mechanisms is essential for mitigating biases in dataset curation, ensuring more reliable AI models, and improving the generalizability of multimodal medical imaging systems.
Collapse
Affiliation(s)
| | - Felix Gunzer
- Diagnostic and interventional Radiology, University Hospital Zurich, Zurich, Switzerland; Department of Neuroradiology, University Hospital Zurich, Zurich, Switzerland
| | - Gernot Reishofer
- Division of Neuroradiology, Vascular and Interventional Radiology, Department of Radiology, Medical University Graz, Graz, Austria; BioTechMed-Graz, Graz, Austria
| | - Roman Kern
- Machine Learning and Neural Computation, Graz University of Technology, Graz, Austria
| |
Collapse
|
|
28
|
Zhao X, Li C, Yang J, Gu X, Li B, Wang Y, Zhang BL, Li X, Zhao J, Wang J, Yu W. Diagnostic report generation for macular diseases by natural language processing algorithms. Br J Ophthalmol 2025:bjo-2024-326064. [PMID: 40348396 DOI: 10.1136/bjo-2024-326064] [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: 07/04/2024] [Accepted: 04/24/2025] [Indexed: 05/14/2025]
Abstract
AIMS To investigate rule-based and deep learning (DL)-based methods for the automatically generating natural language diagnostic reports for macular diseases. METHODS This diagnostic study collected the ophthalmic images of 2261 eyes from 1303 patients. Colour fundus photographs and optical coherence tomography images were obtained. Eyes without retinal diseases as well as eyes diagnosed with four macular diseases were included. For each eye, a diagnostic report was written with a format consisting of lesion descriptions, diagnoses and recommendations. Subsequently, a rule-based natural language processing (NLP) and a DL-based NLP system were developed to automatically generate a diagnostic report. To assess the effectiveness of these models, two junior ophthalmologists wrote diagnostic reports for the collected images independently. A questionnaire was designed and judged by two retina specialists to grade each report's readability, correctness of diagnosis, lesion description and recommendations. RESULTS The rule-based NLP reports achieved higher grades over junior ophthalmologists in correctness of diagnosis (9.13±1.52 vs 9.03±1.42 points) and recommendations (8.55±2.74 vs 8.50±2.53 points). Furthermore, the DL-based NLP reports got slightly lower grades to those of junior ophthalmologists in lesion description (8.82±1.84 vs 9.12±1.20 points, p<0.05), correctness of diagnosis (8.72±2.36 vs 9.08±1.55 points, p<0.05) and recommendations (8.81±2.52 vs 9.15±1.65 points, p<0.05). For readability, the DL-based reports performed better than junior ophthalmologists, with scores of 9.98±0.17 vs 9.94±0.25 points (p=0.094). CONCLUSIONS The multimodal AI system, coupled with the NLP algorithm, has demonstrated competence in generating reports for four macular diseases compared with junior ophthalmologists.
Collapse
Affiliation(s)
- Xufeng Zhao
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Chunshi Li
- Department of Ophthalmology, Dalian No.3 People's Hospital, Dalian, Liaoning, China
| | - Jingyuan Yang
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Xingwang Gu
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Bing Li
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Yuelin Wang
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| | - Bi-Lei Zhang
- Department of Ophthalmology, Hunan Provincial People's Hospital, Changsha, Hunan, China
| | - Xirong Li
- Key Lab of DEKE, Renmin University of China, Beijing, China
| | - Jianchun Zhao
- Vistel AI Lab, Visionary Intelligence Ltd, Beijing, China
| | - Jie Wang
- Vistel AI Lab, Visionary Intelligence Ltd, Beijing, China
| | - Weihong Yu
- Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, China
- Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation, Beijing, China
- Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences, Beijing, China
| |
Collapse
|
|
29
|
Vinas A, Blanco F, Matute H. The combined effect of patient classification systems and availability of resources can bias the judgments of treatment effectiveness. Sci Rep 2025; 15:15915. [PMID: 40335554 PMCID: PMC12059125 DOI: 10.1038/s41598-025-01043-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2024] [Accepted: 05/02/2025] [Indexed: 05/09/2025] Open
Abstract
Patient classification systems (PCS) support clinical decision-making but may rely on incorrect, outdated, or insufficient data. Doctors can sometimes override errors using their experience. However, certain factors such as scarcity of resources could lead to reliance on incorrect PCS recommendations, with consequences for patients. We conducted two experiments where participants interacted with a PCS that incorrectly classified fictitious patients as more or less sensitive to a treatment. Participants had the opportunity to administer the treatment on a series of patients, and use the feedback to learn that the PCS was wrong and all patients were equally sensitive. This was tested in contexts of abundant and scarce resources. Additionally, the treatment was effective in Experiment 1, but ineffective in Experiment 2. Results indicate that people generally trust the PCS recommendation, to some extent neglecting the information they collect during the task. This can lead to uneven resource allocation, especially in scarcity conditions, and incorrect perceptions of effectiveness, which in Experiment 2 implies believing that an ineffective treatment works. We preregistered the experiments, and all data and materials are public.
Collapse
Affiliation(s)
- Aranzazu Vinas
- Department of Psychology, Deusto University, Bilbao, Spain
| | - Fernando Blanco
- Department of Social Psychology, University of Granada, Granada, Spain
- Mind, Brain and Behavior Research Center (CIMCyC), Granada, Spain
| | - Helena Matute
- Department of Psychology, Deusto University, Bilbao, Spain.
| |
Collapse
|
|
30
|
Cheema B, Hourmozdi J, Kline A, Ahmad F, Khera R. Artificial Intelligence in the Management of Heart Failure. J Card Fail 2025:S1071-9164(25)00194-0. [PMID: 40345521 DOI: 10.1016/j.cardfail.2025.02.020] [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: 10/11/2024] [Revised: 02/10/2025] [Accepted: 02/10/2025] [Indexed: 05/11/2025]
Abstract
Artificial intelligence (AI) has the potential to revolutionize the management of heart failure. AI-based tools can guide the diagnosis and treatment of known risk factors, identify asymptomatic structural heart disease, improve cardiomyopathy diagnosis and symptomatic heart failure treatment, and uncover patients transitioning to advanced disease. By integrating multimodal data, including omics, imaging, signals, and electronic health records, state-of-the-art algorithms allow for a more tailored approach to patient care, addressing the unique needs of the individual. The past decade has led to the development of numerous AI solutions targeting each aspect of the heart failure syndrome. However, significant barriers to implementation remain and have limited clinical uptake. Data-privacy concerns, real-world model performance, integration challenges, trust in AI, model governance, and concerns about fairness and bias are some of the topics requiring additional research and the development of best practices. This review highlights progress in the use of AI to guide the diagnosis and management of heart failure while underscoring the importance of overcoming key implementation challenges that are currently slowing progress.
Collapse
Affiliation(s)
- Baljash Cheema
- Bluhm Cardiovascular Institute, Center for Artificial Intelligence, Northwestern Medicine, Chicago, IL; Northwestern University, Feinberg School of Medicine, Chicago, IL.
| | | | - Adrienne Kline
- Bluhm Cardiovascular Institute, Center for Artificial Intelligence, Northwestern Medicine, Chicago, IL; Northwestern University, Feinberg School of Medicine, Chicago, IL
| | - Faraz Ahmad
- Bluhm Cardiovascular Institute, Center for Artificial Intelligence, Northwestern Medicine, Chicago, IL; Northwestern University, Feinberg School of Medicine, Chicago, IL
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT; Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT; Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
| |
Collapse
|
|
31
|
Yu Y, Ren W, Mao L, Ouyang W, Hu Q, Yao Q, Tan Y, He Z, Ban X, Hu H, Lin R, Wang Z, Chen Y, Wu Z, Chen K, Ouyang J, Li T, Zhang Z, Liu G, Chen X, Li Z, Duan X, Wang J, Yao H. MRI-based multimodal AI model enables prediction of recurrence risk and adjuvant therapy in breast cancer. Pharmacol Res 2025; 216:107765. [PMID: 40345352 DOI: 10.1016/j.phrs.2025.107765] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/02/2025] [Revised: 04/06/2025] [Accepted: 05/06/2025] [Indexed: 05/11/2025]
Abstract
Timely intervention and improved prognosis for breast cancer patients rely on early metastasis risk detection and accurate treatment predictions. This study introduces an advanced multimodal MRI and AI-driven 3D deep learning model, termed the 3D-MMR-model, designed to predict recurrence risk in non-metastatic breast cancer patients. We conducted a multicenter study involving 1199 non-metastatic breast cancer patients from four institutions in China, with comprehensive MRI and clinical data retrospectively collected. Our model employed multimodal-data fusion, utilizing contrast-enhanced T1-weighted imaging (T1 + C) and T2-weighted imaging (T2WI) volumes, processed through a modified 3D-UNet for tumor segmentation and a DenseNet121-based architecture for disease-free survival (DFS) prediction. Additionally, we performed RNA-seq analysis to delve further into the relationship between concentrated hotspots within the tumor region and the tumor microenvironment. The 3D-MR-model demonstrated superior predictive performance, with time-dependent ROC analysis yielding AUC values of 0.90, 0.89, and 0.88 for 2-, 3-, and 4-year DFS predictions, respectively, in the training cohort. External validation cohorts corroborated these findings, highlighting the model's robustness across diverse clinical settings. Integration of clinicopathological features further enhanced the model's accuracy, with a multimodal approach significantly improving risk stratification and decision-making in clinical practice. Visualization techniques provided insights into the decision-making process, correlating predictions with tumor microenvironment characteristics. In summary, the 3D-MMR-model represents a significant advancement in breast cancer prognosis, combining cutting-edge AI technology with multimodal imaging to deliver precise and clinically relevant predictions of recurrence risk. This innovative approach holds promise for enhancing patient outcomes and guiding individualized treatment plans in breast cancer care.
Collapse
Affiliation(s)
- Yunfang Yu
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China; Guangdong Provincial Key Laboratory of Cancer Pathogenesis and Precision Diagnosis and Treatment, Joint Big Data Laboratory, Department of Medical Oncology, Shenshan Medical Center, Memorial Hospital of Sun Yat-sen University, Shanwei, China; Institute for AI in Medicine and faculty of Medicine, Macau University of Science and Technology, Taipa, Macao, China; Department of Breast Surgery, The First Affiliated Hospital, Jinan University, Guangzhou, China
| | - Wei Ren
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Luhui Mao
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Wenhao Ouyang
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Qiugen Hu
- Department of Radiology, Shunde Hospital, Southern Medical University, Foshan, China
| | - Qinyue Yao
- Cells Vision (Guangzhou) Medical Technology Inc., Guangzhou, China
| | - Yujie Tan
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zifan He
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiaohua Ban
- Imaging Diagnostic and Interventional Center, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China
| | - Huijun Hu
- Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Ruichong Lin
- Faculty of Innovation Engineering, Macau University of Science and Technology, Taipa, Macao, China
| | - Zehua Wang
- Faculty of Innovation Engineering, Macau University of Science and Technology, Taipa, Macao, China; UMedEVO and UMedREVO Artificial Intelligence Technology (Guangzhou) Co., Ltd
| | - Yongjian Chen
- Dermatology and Venereology Division, Department of Medicine Solna, Center for Molecular Medicine, Karolinska Institutet, Stockholm, Sweden
| | - Zhuo Wu
- Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Kai Chen
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Jie Ouyang
- Department of Breast Surgery, Tungwah Hospital, Dongguan, China
| | - Tang Li
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zebang Zhang
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Guoying Liu
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiuxing Chen
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Zhuo Li
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Xiaohui Duan
- Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
| | - Jin Wang
- Cells Vision (Guangzhou) Medical Technology Inc., Guangzhou, China.
| | - Herui Yao
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangdong-Hong Kong Joint Laboratory for RNA Medicine, Department of Medical Oncology, Breast Tumor Centre, Phase I Clinical Trial Centre, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
|
32
|
Arbelaez Ossa L, Rost M, Bont N, Lorenzini G, Shaw D, Elger BS. Exploring Patient Participation in AI-Supported Health Care: Qualitative Study. JMIR AI 2025; 4:e50781. [PMID: 40324765 PMCID: PMC12089863 DOI: 10.2196/50781] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Revised: 10/30/2024] [Accepted: 03/15/2025] [Indexed: 05/07/2025]
Abstract
BACKGROUND The introduction of artificial intelligence (AI) into health care has sparked discussions about its potential impact. Patients, as key stakeholders, will be at the forefront of interacting with and being impacted by AI. Given the ethical importance of patient-centered health care, patients must navigate how they engage with AI. However, integrating AI into clinical practice brings potential challenges, particularly in shared decision-making and ensuring patients remain active participants in their care. Whether AI-supported interventions empower or undermine patient participation depends largely on how these technologies are envisioned and integrated into practice. OBJECTIVE This study explores how patients and medical AI professionals perceive the patient's role and the factors shaping participation in AI-supported care. METHODS We conducted qualitative semistructured interviews with 21 patients and 21 medical AI professionals from different disciplinary backgrounds. Data were analyzed using reflexive thematic analysis. We identified 3 themes to describe how patients and professionals describe factors that shape participation in AI-supported care. RESULTS The first theme explored the vision of AI as an unavoidable and potentially harmful force of change in health care. The second theme highlights how patients perceive limitations in their capabilities that may prevent them from meaningfully participating in AI-supported care. The third theme describes patients' adaptive responses, such as relying on experts or making value judgments leading to acceptance or rejection of AI-supported care. CONCLUSIONS Both external and internal preconceptions influence how patients and medical AI professionals perceive patient participation. Patients often internalize AI's complexity and inevitability as an obstacle to their active participation, leading them to feel they have little influence over its development. While some patients rely on doctors or see AI as something to accept or reject, these strategies risk placing them in a disempowering role as passive recipients of care. Without adequate education on their rights and possibilities, these responses may not be enough to position patients at the center of their care.
Collapse
Affiliation(s)
| | - Michael Rost
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
| | - Nathalie Bont
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
| | - Giorgia Lorenzini
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
| | - David Shaw
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
- Care and Public Health Research Institute, Maastricht University, Maastricht, The Netherlands
| | - Bernice Simone Elger
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
- Center for Legal Medicine (CURML), University of Geneva, Geneva, Switzerland
| |
Collapse
|
|
33
|
Raju V, Reddy R, Javan AC, Hajihossainlou B, Weissleder R, Guiseppi-Elie A, Kurabayashi K, Jones SA, Faghih RT. Tracking inflammation status for improving patient prognosis: A review of current methods, unmet clinical needs and opportunities. Biotechnol Adv 2025; 82:108592. [PMID: 40324661 DOI: 10.1016/j.biotechadv.2025.108592] [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: 12/20/2024] [Revised: 04/07/2025] [Accepted: 04/29/2025] [Indexed: 05/07/2025]
Abstract
Inflammation is the body's response to infection, trauma or injury and is activated in a coordinated fashion to ensure the restoration of tissue homeostasis and healthy physiology. This process requires communication between stromal cells resident to the tissue compartment and infiltrating immune cells which is dysregulated in disease. Clinical innovations in patient diagnosis and stratification include measures of inflammatory activation that support the assessment of patient prognosis and response to therapy. We propose that (i) the recent advances in fast, dynamic monitoring of inflammatory markers (e.g., cytokines) and (ii) data-dependent theoretical and computational modeling of inflammatory marker dynamics will enable the quantification of the inflammatory response, identification of optimal, disease-specific biomarkers and the design of personalized interventions to improve patient outcomes - multidisciplinary efforts in which biomedical engineers may potentially contribute. To illustrate these ideas, we describe the actions of cytokines, acute phase proteins and hormones in the inflammatory response and discuss their role in local wounds, COVID-19, cancer, autoimmune diseases, neurodegenerative diseases and aging, with a central focus on cardiac surgery. We also discuss the challenges and opportunities involved in tracking and modulating inflammation in clinical settings.
Collapse
Affiliation(s)
- Vidya Raju
- Department of Biomedical Engineering, New York University Tandon School of Engineering, New York, 11201, NY, USA
| | - Revanth Reddy
- Department of Biomedical Engineering, New York University Tandon School of Engineering, New York, 11201, NY, USA
| | | | - Behnam Hajihossainlou
- Department of Infectious Diseases, Harlem Medical Center, and Columbia University, New York, 10032, NY, USA
| | - Ralph Weissleder
- Center for Systems Biology, Massachusetts General Hospital, Department of Systems Biology, Harvard Medical School, and Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, 02115, Massachusetts, USA
| | - Anthony Guiseppi-Elie
- Department of Biomedical Engineering, Center for Bioelectronics, Biosensors and Biochips (C3B), and Department of Electrical and Computer Engineering, Texas A & M University, College Station, 77843, TX, USA; Department of Cardiovascular Sciences, Houston Methodist Institute for Academic Medicine and Houston Methodist Research Institute, Houston, 77030, TX, USA; ABTECH Scientific, Inc., Biotechnology Research Park, Richmond, 23219, Virginia, USA
| | - Katsuo Kurabayashi
- Department of Mechanical and Aerospace Engineering, New York University, New York 11201, NY, USA
| | - Simon A Jones
- Division of Infection and Immunity, and School of Medicine, Cardiff University, UK; Systems Immunity University Research Institute, Cardiff University, Cardiff CF14 4XN, UK
| | - Rose T Faghih
- Department of Biomedical Engineering, New York University Tandon School of Engineering, New York, 11201, NY, USA.
| |
Collapse
|
|
34
|
Portik D, Lacombe D, Faivre-Finn C, Achard V, Andratschke N, Correia D, Spalek M, Guckenberger M, Ost P, Ehret F. The 2024 State of Science report from the European Organisation for Research and Treatment of Cancer's Radiation Oncology Scientific Council. Eur J Cancer 2025; 220:115334. [PMID: 40127505 DOI: 10.1016/j.ejca.2025.115334] [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: 02/25/2025] [Accepted: 02/27/2025] [Indexed: 03/26/2025]
Abstract
BACKGROUND Radiotherapy (RT) is a central pillar of a multimodal cancer treatment approach. The ongoing advances in the fields of RT, imaging technologies, cancer biology, and others yield the potential to refine the use of RT. The European Organisation for Research and Treatment of Cancer (EORTC) hosted a dedicated workshop to identify and prioritize key research questions and to define future RT-based treatment strategies to improve the survival and quality of life of cancer patients. METHODS An initial call for relevant RT research topics led to the formation of workgroups to develop these into new clinical research proposals and projects. The EORTC Radiation Oncology Scientific Council (ROSC) State of Science workshop was held in Brussels, Belgium, in February 2024, bringing together EORTC members and international stakeholders to connect and work on the proposals. RESULTS Four topics of interest were identified: I) De-escalation of RT, minimizing toxicity while maintaining patients' quality of life, II) Technology-driven RT utilizing advances in treatment techniques, such as spatially fractionated RT to improve outcomes in patients with bulky disease and localized high tumor burden, III) Biology-driven RT, integrating the rapid advances in cancer biology and functional imaging to guide and personalize RT, and IV) New indications adding value and expanding the use of RT. CONCLUSION The EORTC ROSC State of Science workshop prioritized clinical questions to be addressed in prospective clinical research projects to advance RT care and improve patient outcomes.
Collapse
Affiliation(s)
- Daniel Portik
- European Organisation for Research and Treatment of Cancer (EORTC) Headquarters, Brussels, Belgium; Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands.
| | - Denis Lacombe
- European Organisation for Research and Treatment of Cancer (EORTC) Headquarters, Brussels, Belgium
| | - Corinne Faivre-Finn
- Department of Clinical Oncology, The Christie Hospital NHS Foundation Trust, University of Manchester, Manchester, United Kingdom
| | - Vérane Achard
- Department of Radiotherapy, Institut Bergonié, Bordeaux, France and University of Geneva, Geneva, Switzerland
| | - Nicolaus Andratschke
- Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Dora Correia
- Department of Radiation Oncology, Cantonal Hospital Aarau, Aarau, Switzerland
| | - Mateusz Spalek
- Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland
| | - Matthias Guckenberger
- Department of Radiation Oncology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Piet Ost
- Department of Human Structure and Repair, Ghent University, Ghent, Belgium; Iridium Network, Radiation Oncology, Wilrijk, Belgium
| | - Felix Ehret
- Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Radiation Oncology, Berlin, Germany; German Cancer Consortium (DKTK), partner site Berlin, a partnership between DKFZ and Charité - Universitätsmedizin Berlin, Germany
| |
Collapse
|
|
35
|
Panzeri D, Laohawetwanit T, Akpinar R, De Carlo C, Belsito V, Terracciano L, Aghemo A, Pugliese N, Chirico G, Inverso D, Calderaro J, Sironi L, Di Tommaso L. Assessing the diagnostic accuracy of ChatGPT-4 in the histopathological evaluation of liver fibrosis in MASH. Hepatol Commun 2025; 9:e0695. [PMID: 40304570 PMCID: PMC12045550 DOI: 10.1097/hc9.0000000000000695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/17/2024] [Accepted: 01/26/2025] [Indexed: 05/02/2025] Open
Abstract
BACKGROUND Large language models like ChatGPT have demonstrated potential in medical image interpretation, but their efficacy in liver histopathological analysis remains largely unexplored. This study aims to assess ChatGPT-4-vision's diagnostic accuracy, compared to liver pathologists' performance, in evaluating liver fibrosis (stage) in metabolic dysfunction-associated steatohepatitis. METHODS Digitized Sirius Red-stained images for 59 metabolic dysfunction-associated steatohepatitis tissue biopsy specimens were evaluated by ChatGPT-4 and 4 pathologists using the NASH-CRN staging system. Fields of view at increasing magnification levels, extracted by a senior pathologist or randomly selected, were shown to ChatGPT-4, asking for fibrosis staging. The diagnostic accuracy of ChatGPT-4 was compared with pathologists' evaluations and correlated to the collagen proportionate area for additional insights. All cases were further analyzed by an in-context learning approach, where the model learns from exemplary images provided during prompting. RESULTS ChatGPT-4's diagnostic accuracy was 81% when using images selected by a pathologist, while it decreased to 54% with randomly cropped fields of view. By employing an in-context learning approach, the accuracy increased to 88% and 77% for selected and random fields of view, respectively. This method enabled the model to fully and correctly identify the tissue structures characteristic of F4 stages, previously misclassified. The study also highlighted a moderate to strong correlation between ChatGPT-4's fibrosis staging and collagen proportionate area. CONCLUSIONS ChatGPT-4 showed remarkable results with a diagnostic accuracy overlapping those of expert liver pathologists. The in-context learning analysis, applied here for the first time to assess fibrosis deposition in metabolic dysfunction-associated steatohepatitis samples, was crucial in accurately identifying the key features of F4 cases, critical for early therapeutic decision-making. These findings suggest the potential for integrating large language models as supportive tools in diagnostic pathology.
Collapse
Affiliation(s)
- Davide Panzeri
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Thiyaphat Laohawetwanit
- Division of Pathology, Chulabhorn International College of Medicine, Thammasat University, Pathum Thani, Thailand
| | - Reha Akpinar
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Camilla De Carlo
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Vincenzo Belsito
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Luigi Terracciano
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Alessio Aghemo
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Gastroenterology, Division of Internal Medicine and Hepatology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Nicola Pugliese
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Gastroenterology, Division of Internal Medicine and Hepatology, IRCCS Humanitas Research Hospital, Milan, Italy
| | - Giuseppe Chirico
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Donato Inverso
- Division of Immunology, Transplantation and Infectious Diseases IRCCS San Raffaele Scientific Institute, Milan, Italy
- Vita-Salute San Raffaele University, Milan, Italy
| | - Julien Calderaro
- Team «Viruses, Hepatology, Cancer», Institut Mondor de Recherche Biomédicale, INSERM U955, Hôpital, Henri Mondor (AP-HP), Université Paris-Est, Créteil, France
- Department of Pathology, AP-HP, Henri Mondor University Hospital, Créteil, France
| | - Laura Sironi
- Department of Physics, University of Milano-Bicocca, Milan, Italy
| | - Luca Di Tommaso
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
- Department of Pathology, IRCCS Humanitas Research Hospital, Milan, Italy
| |
Collapse
|
|
36
|
Yang Y, Fu H, Aviles-Rivero AI, Xing Z, Zhu L. DiffMIC-v2: Medical Image Classification via Improved Diffusion Network. IEEE TRANSACTIONS ON MEDICAL IMAGING 2025; 44:2244-2255. [PMID: 40031019 DOI: 10.1109/tmi.2025.3530399] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/05/2025]
Abstract
Recently, Denoising Diffusion Models have achieved outstanding success in generative image modeling and attracted significant attention in the computer vision community. Although a substantial amount of diffusion-based research has focused on generative tasks, few studies apply diffusion models to medical diagnosis. In this paper, we propose a diffusion-based network (named DiffMIC-v2) to address general medical image classification by eliminating unexpected noise and perturbations in image representations. To achieve this goal, we first devise an improved dual-conditional guidance strategy that conditions each diffusion step with multiple granularities to enhance step-wise regional attention. Furthermore, we design a novel Heterologous diffusion process that achieves efficient visual representation learning in the latent space. We evaluate the effectiveness of our DiffMIC-v2 on four medical classification tasks with different image modalities, including thoracic diseases classification on chest X-ray, placental maturity grading on ultrasound images, skin lesion classification using dermatoscopic images, and diabetic retinopathy grading using fundus images. Experimental results demonstrate that our DiffMIC-v2 outperforms state-of-the-art methods by a significant margin, which indicates the universality and effectiveness of the proposed model on multi-class and multi-label classification tasks. DiffMIC-v2 can use fewer iterations than our previous DiffMIC to obtain accurate estimations, and also achieves greater runtime efficiency with superior results. The code will be publicly available at https://github.com/scott-yjyang/DiffMICv2.
Collapse
|
|
37
|
Santos-Lopes M, Araújo R, David R, Correia PL. Automated analysis of bird head motion in unconstrained settings: a foundational study on semicircular canal evolution in archosaurs. J R Soc Interface 2025; 22:20240919. [PMID: 40425042 PMCID: PMC12115815 DOI: 10.1098/rsif.2024.0919] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2024] [Revised: 02/28/2025] [Accepted: 05/01/2025] [Indexed: 05/29/2025] Open
Abstract
This study presents a framework to automatically analyse head motion in birds from videos of natural behaviours. The process involves detecting birds, identifying key points on their heads and tracking changes in their positions over time. Bird detection and key point extraction were trained on publicly available datasets, featuring videos and images of diverse bird species in uncontrolled settings. Initial challenges with complex video backgrounds causing misidentifications and inaccurate key points were addressed through validation, refinement, filtering and smoothing. Head angular velocities and rotation frequencies were computed from the refined key points. The algorithm performed well at moderate speeds but was limited by the 30 Hz frame rate of most videos, which constrained measurable angular velocities and frequencies and caused motion blur, affecting key point detection. Our findings suggest that the framework may provide plausible estimates of head motion but also emphasize the importance of high frame-rate videos in future research, including extensive comparisons against ground truth data, to fully characterize bird head movements. Importantly, this work is a foundational effort to understand the evolutionary drivers of the semicircular canals, the biosensor that monitors head rotations, for both extinct and extant tetrapods.
Collapse
Affiliation(s)
- Marco Santos-Lopes
- Instituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| | - Ricardo Araújo
- CERENA (Centro de Recursos Naturais e Ambiente), Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| | | | - Paulo L. Correia
- Instituto de Telecomunicações, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| |
Collapse
|
|
38
|
Safwan N, Suchak KK, Liran O, Kingsberg SA, Spiegel BMR, Shufelt CL, Faubion SS. Virtual reality for menopause symptom management: opportunities, challenges, and next steps. Menopause 2025; 32:475-480. [PMID: 40067758 DOI: 10.1097/gme.0000000000002529] [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: 11/15/2024] [Accepted: 12/18/2024] [Indexed: 04/26/2025]
Abstract
IMPORTANCE AND OBJECTIVE Menopause is the natural cessation of ovarian function, typically occurring at a mean age of 52 years in the United States. Vasomotor symptoms (VMS; hot flashes and night sweats) affect over 75% of midlife women and typically last 7 to 9 years, with only 54% seeking medical attention. Although hormone therapy is the most effective treatment for VMS, <4% of women currently use it, primarily due to safety concerns. There is evidence that cognitive behavioral therapy (CBT) is an effective management strategy for VMS. Virtual reality (VR) has shown promise in delivering an immersive form of CBT for various medical conditions, including acute and chronic pain, sleep, and mood disorders, potentially overcoming barriers such as access and cost while improving quality of life. This narrative review aims to summarize the existing literature on VR for managing menopause symptoms. METHODS A comprehensive literature review was conducted through PubMed and Medline databases. The search focused on keyword combinations related to VR, artificial intelligence, and menopause symptoms. DISCUSSION AND CONCLUSION The search yielded one study specifically targeting symptoms related to menopause. A pilot study (n = 42) evaluating an immersive VR and artificial intelligence intervention based on CBT and mindfulness techniques for managing hot flashes in women with breast or ovarian cancer demonstrated a significant reduction in frequency of hot flashes ( P < 0.01) and improvements in sleep quality, mood, anxiety, stress, and overall quality of life. However, these women experienced hot flashes that might have been associated with their cancer diagnosis or treatment rather than relating specifically to menopause, potentially limiting the generalizability of the findings to women with menopause symptoms. Although VR has shown effectiveness in delivering CBT for other conditions, there remains a significant gap in research on its specific use for menopause-related symptoms.
Collapse
Affiliation(s)
- Nancy Safwan
- Division of General Internal Medicine, Mayo Clinic, Jacksonville, FL
- Mayo Clinic Center for Women's Health, Mayo Clinic, Rochester, MN
| | - Karisma K Suchak
- Division of Health Services Research, Department of Medicine, Cedars-Sinai, Los Angeles, CA
- Virtual Medicine Program, Cedars-Sinai Medical Center, Los Angeles, CA
| | - Omer Liran
- Division of Health Services Research, Department of Medicine, Cedars-Sinai, Los Angeles, CA
- Virtual Medicine Program, Cedars-Sinai Medical Center, Los Angeles, CA
| | - Sheryl A Kingsberg
- Department of Obstetrics and Gynecology, University Hospitals Cleveland Medical Center, Cleveland, OH
| | - Brennan M R Spiegel
- Division of Health Services Research, Department of Medicine, Cedars-Sinai, Los Angeles, CA
- Virtual Medicine Program, Cedars-Sinai Medical Center, Los Angeles, CA
| | - Chrisandra L Shufelt
- Division of General Internal Medicine, Mayo Clinic, Jacksonville, FL
- Mayo Clinic Center for Women's Health, Mayo Clinic, Rochester, MN
- Women's Health Research Center, Mayo Clinic, Rochester, MN
| | - Stephanie S Faubion
- Division of General Internal Medicine, Mayo Clinic, Jacksonville, FL
- Mayo Clinic Center for Women's Health, Mayo Clinic, Rochester, MN
- Women's Health Research Center, Mayo Clinic, Rochester, MN
| |
Collapse
|
|
39
|
Chen X, Dai C, Peng M, Wang D, Sui X, Duan L, Wang X, Wang X, Weng W, Wang S, Zhao H, Wang Z, Geng J, Chen C, Hu Y, Hu Q, Jiang C, Zheng H, Bao Y, Sun C, Cui Z, Zeng X, Han H, Xia C, Liu J, Yang B, Qi J, Ji F, Wang S, Hong N, Wang J, Chen K, Zhu Y, Yu F, Yang F. Artificial intelligence driven 3D reconstruction for enhanced lung surgery planning. Nat Commun 2025; 16:4086. [PMID: 40312393 PMCID: PMC12046031 DOI: 10.1038/s41467-025-59200-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2024] [Accepted: 04/14/2025] [Indexed: 05/03/2025] Open
Abstract
The increasing complexity of lung surgeries necessitates the need for enhanced imaging support to improve the precision and efficiency of preoperative planning. Despite the promise of 3D reconstruction, clinical adoption remains limited due to time constraints and insufficient validation. To address this, we evaluate an artificial intelligence-driven 3D reconstruction system for pulmonary vessels and bronchi in a retrospective, multi-center multi-reader multi-case study. Using a two-stage crossover design, ten thoracic surgeons assess 140 cases with and without the system's assistance. The system significantly improves the accuracy of anatomical variant identification by 8% (p < 0.01), reducing errors by 41%. Improvements in secondary endpoints are also observed. Operation procedure selection accuracy is improved by 8%, with a 35% decrease in errors. Preoperative planning time is decreased by 25%, and user satisfaction is high at 99%. These benefits are consistent across surgeons of varying experience. In conclusion, the artificial intelligence-driven 3D reconstruction system significantly improves the identification of anatomical variants, addressing a critical need in preoperative planning for thoracic surgery.
Collapse
Affiliation(s)
- Xiuyuan Chen
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Chenyang Dai
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| | - Muyun Peng
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Dawei Wang
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Xizhao Sui
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Liang Duan
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| | - Xiang Wang
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Xun Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Wenhan Weng
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Shaodong Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Heng Zhao
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Zhenfan Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Jiayi Geng
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Chen Chen
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Yan Hu
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Qikang Hu
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China
| | - Chao Jiang
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| | - Hui Zheng
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| | - Yi Bao
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China
| | - Chao Sun
- Department of Radiology, Peking University People's Hospital, Beijing, China
| | - Zhuoer Cui
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Xiangyu Zeng
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Huiming Han
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Chen Xia
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Jinlong Liu
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Bing Yang
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Ji Qi
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Fanghang Ji
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Shaokang Wang
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Nan Hong
- Department of Radiology, Peking University People's Hospital, Beijing, China
| | - Jun Wang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Kezhong Chen
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China
| | - Yuming Zhu
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai, China.
| | - Fenglei Yu
- Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China.
| | - Fan Yang
- Department of Thoracic Surgery, Peking University People's Hospital, Beijing, China.
- Thoracic Oncology Institute, Peking University People's Hospital, Beijing, China.
- Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, China.
- Institute of Advanced Clinical Medicine, Peking University, Beijing, China.
- Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People's Hospital, Beijing, China.
| |
Collapse
|
|
40
|
Delvaux BV, Maupain O, Giral T, Bowness JS, Mercadal L. Evaluation of AI-based nerve segmentation on ultrasound: relevance of standard metrics in the clinical setting. Br J Anaesth 2025; 134:1497-1502. [PMID: 40016039 DOI: 10.1016/j.bja.2024.12.040] [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: 11/26/2024] [Revised: 12/12/2024] [Accepted: 12/14/2024] [Indexed: 03/01/2025] Open
Abstract
BACKGROUND In artificial intelligence for ultrasound-guided regional anaesthesia, accurate nerve identification is essential. The technology community typically favours objective metrics of pixel overlap on still-frame images, whereas clinical assessments often use subjective evaluation of cine loops by physician experts. No clinically acceptable threshold of pixel overlap has been defined for nerve segmentation. We investigated the relationship between these approaches and identify thresholds for objective pixel-based metrics when clinical evaluations identify high-quality nerve segmentation. METHODS cNerve™ is a deep learning segmentation tool on GE Healthcare's Venue™ ultrasound systems. It highlights nerves of the interscalene-supraclavicular-level brachial plexus, femoral, and popliteal-level sciatic block regions. Expert anaesthesiologists subjectively rated overall segmentation quality of cNerve™ on ultrasound cine loop sequences using a 1-5 Likert scale (1 = poor; 5 = excellent). Objective assessments of nerve segmentation, using the Intersection over Union and Dice similarity coefficient metrics, were applied to frames from sequences rated 5. RESULTS A total of 173 still image frames were analysed. The median Intersection over Union for nerves was 0.49, and the median Dice similarity coefficient was 0.65, indicating variable performance based on objective metrics, despite subjective clinical evaluations rating the artificial intelligence-generated nerve segmentation as excellent. CONCLUSIONS Variable objective segmentation metric scores correspond to excellent performance on clinically oriented assessment and lack the context provided by subjective expert evaluations. Further work is needed to establish standardised evaluation criteria that incorporate both objective pixel-based and subjective clinical assessments. Collaboration between clinicians and technologists is needed to develop these evaluation methods for improved clinical applicability.
Collapse
Affiliation(s)
- Bernard V Delvaux
- Department of Anesthesiology and Perioperative Medicine, Ramsay Santé, Claude Galien Private Hospital, Quincy-Sous-Sénart, France
| | - Olivier Maupain
- Department of Anesthesiology and Perioperative Medicine, Ramsay Santé, Claude Galien Private Hospital, Quincy-Sous-Sénart, France
| | - Thomas Giral
- Department of Anesthesiology and Perioperative Medicine, Ramsay Santé, Claude Galien Private Hospital, Quincy-Sous-Sénart, France
| | - James S Bowness
- Department of Anaesthesia, University College London Hospitals, London, UK; Department of Targeted Intervention, University College London, London, UK.
| | - Luc Mercadal
- Department of Anesthesiology and Perioperative Medicine, Ramsay Santé, Claude Galien Private Hospital, Quincy-Sous-Sénart, France
| |
Collapse
|
|
41
|
Phipps B, Hadoux X, Sheng B, Campbell JP, Liu TYA, Keane PA, Cheung CY, Chung TY, Wong TY, van Wijngaarden P. AI image generation technology in ophthalmology: Use, misuse and future applications. Prog Retin Eye Res 2025; 106:101353. [PMID: 40107410 DOI: 10.1016/j.preteyeres.2025.101353] [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: 08/30/2024] [Revised: 03/12/2025] [Accepted: 03/13/2025] [Indexed: 03/22/2025]
Abstract
BACKGROUND AI-powered image generation technology holds the potential to reshape medical practice, yet it remains an unfamiliar technology for both medical researchers and clinicians alike. Given the adoption of this technology relies on clinician understanding and acceptance, we sought to demystify its use in ophthalmology. To this end, we present a literature review on image generation technology in ophthalmology, examining both its theoretical applications and future role in clinical practice. METHODS First, we consider the key model designs used for image synthesis, including generative adversarial networks, autoencoders, and diffusion models. We then perform a survey of the literature for image generation technology in ophthalmology prior to September 2024, presenting both the type of model used and its clinical application. Finally, we discuss the limitations of this technology, the risks of its misuse and the future directions of research in this field. RESULTS Applications of this technology include improving AI diagnostic models, inter-modality image transformation, more accurate treatment and disease prognostication, image denoising, and individualised education. Key barriers to its adoption include bias in generative models, risks to patient data security, computational and logistical barriers to development, challenges with model explainability, inconsistent use of validation metrics between studies and misuse of synthetic images. Looking forward, researchers are placing a further emphasis on clinically grounded metrics, the development of image generation foundation models and the implementation of methods to ensure data provenance. CONCLUSION Compared to other medical applications of AI, image generation is still in its infancy. Yet, it holds the potential to revolutionise ophthalmology across research, education and clinical practice. This review aims to guide ophthalmic researchers wanting to leverage this technology, while also providing an insight for clinicians on how it may change ophthalmic practice in the future.
Collapse
Affiliation(s)
- Benjamin Phipps
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, 3002, VIC, Australia; Ophthalmology, Department of Surgery, University of Melbourne, Parkville, 3010, VIC, Australia.
| | - Xavier Hadoux
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, 3002, VIC, Australia; Ophthalmology, Department of Surgery, University of Melbourne, Parkville, 3010, VIC, Australia
| | - Bin Sheng
- Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - J Peter Campbell
- Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, Portland, USA
| | - T Y Alvin Liu
- Retina Division, Wilmer Eye Institute, Johns Hopkins University, Baltimore, MD, 21287, USA
| | - Pearse A Keane
- NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust, London, UK; Institute of Ophthalmology, University College London, London, UK
| | - Carol Y Cheung
- Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, 999077, China
| | - Tham Yih Chung
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Centre for Innovation and Precision Eye Health, Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore and National University Health System, Singapore; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Eye Academic Clinical Program (Eye ACP), Duke NUS Medical School, Singapore
| | - Tien Y Wong
- Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Tsinghua Medicine, Tsinghua University, Beijing, China; Beijing Visual Science and Translational Eye Research Institute, Beijing Tsinghua Changgung Hospital, Beijing, China
| | - Peter van Wijngaarden
- Centre for Eye Research Australia, Royal Victorian Eye and Ear Hospital, East Melbourne, 3002, VIC, Australia; Ophthalmology, Department of Surgery, University of Melbourne, Parkville, 3010, VIC, Australia; Florey Institute of Neuroscience & Mental Health, Parkville, VIC, Australia
| |
Collapse
|
|
42
|
Ortega-Martorell S, Olier I, Ohlsson M, Lip GYH. Advancing personalised care in atrial fibrillation and stroke: The potential impact of AI from prevention to rehabilitation. Trends Cardiovasc Med 2025; 35:205-211. [PMID: 39653093 DOI: 10.1016/j.tcm.2024.12.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/20/2024] [Revised: 12/01/2024] [Accepted: 12/03/2024] [Indexed: 12/13/2024]
Abstract
Atrial fibrillation (AF) is a complex condition caused by various underlying pathophysiological disorders and is the most common heart arrhythmia worldwide, affecting 2 % of the European population. This prevalence increases with age, imposing significant financial, economic, and human burdens. In Europe, stroke is the second leading cause of death and the primary cause of disability, with numbers expected to rise due to ageing and improved survival rates. Functional recovery from AF-related stroke is often unsatisfactory, leading to prolonged hospital stays, severe disability, and high mortality. Despite advances in AF and stroke research, the full pathophysiological and management issues between AF and stroke increasingly need innovative approaches such as artificial intelligence (AI) and machine learning (ML). Current risk assessment tools focus on static risk factors, neglecting the dynamic nature of risk influenced by acute illness, ageing, and comorbidities. Incorporating biomarkers and automated ECG analysis could enhance pathophysiological understanding. This paper highlights the need for personalised, integrative approaches in AF and stroke management, emphasising the potential of AI and ML to improve risk prediction, treatment personalisation, and rehabilitation outcomes. Further research is essential to optimise care and reduce the burden of AF and stroke on patients and healthcare systems.
Collapse
Affiliation(s)
- Sandra Ortega-Martorell
- Data Science Research Centre, Liverpool John Moores University, Liverpool L3 3AF, UK; Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, UK.
| | - Ivan Olier
- Data Science Research Centre, Liverpool John Moores University, Liverpool L3 3AF, UK; Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, UK
| | - Mattias Ohlsson
- Computational Science for Health and Environment, Centre for Environmental and Climate Science, Lund University, Lund, Sweden
| | - Gregory Y H Lip
- Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, UK; Danish Center for Health Services Research, Department of Clinical Medicine, Aalborg University, Aalborg, Denmark; Medical University of Bialystok, Bialystok, Poland
| |
Collapse
|
|
43
|
Roach M, Zhang J, Mohamad O, van der Wal D, Simko JP, DeVries S, Huang HC, Joun S, Schaeffer EM, Morgan TM, Keim-Malpass J, Chen E, Yamashita R, Monson JM, Naz F, Wallace J, Bahary JP, Wilke D, Batra S, Biedermann GB, Faria S, Hwang L, Sandler HM, Spratt DE, Pugh SL, Esteva A, Tran PT, Feng FY. Assessing Algorithmic Fairness With a Multimodal Artificial Intelligence Model in Men of African and Non-African Origin on NRG Oncology Prostate Cancer Phase III Trials. JCO Clin Cancer Inform 2025; 9:e2400284. [PMID: 40344545 DOI: 10.1200/cci-24-00284] [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: 11/08/2024] [Revised: 11/15/2024] [Accepted: 11/15/2024] [Indexed: 05/11/2025] Open
Abstract
PURPOSE Artificial intelligence (AI) tools could improve clinical decision making or exacerbate inequities because of bias. African American (AA) men reportedly have a worse prognosis for prostate cancer (PCa) and are underrepresented in the development genomic biomarkers. We assess the generalizability of tools developed using a multimodal AI (MMAI) deep learning system using digital histopathology and clinical data from NRG/Radiation Therapy Oncology Group PCa trials across racial subgroups. METHODS In total, 5,708 patients from five randomized phase III trials were included. Two MMAI algorithms were evaluated: (1) the distant metastasis (DM) MMAI model optimized to predict risk of DM, and (2) the PCa-specific mortality (PCSM) MMAI model optimized to focus on prediction death in the presence of DM (DDM). The prognostic performance of the MMAI algorithms was evaluated in AA and non-AA subgroups using time to DM (primary end point) and time to DDM (secondary end point). Exploratory end points included time to biochemical failure and overall survival with Fine-Gray or Cox proportional hazards models. Cumulative incidence estimates were computed for time-to-event end points and compared using Gray's test. RESULTS There were 948 (16.6%) AA patients, 4,731 non-AA patients (82.9%), and 29 (0.5%) patients with unknown or missing race status. The DM-MMAI algorithm showed a strong prognostic signal for DM in the AA (subdistribution hazard ratio [sHR], 1.2 [95% CI, 1.0 to 1.3]; P = .007) and non-AA subgroups (sHR, 1.4 [95% CI, 1.3 to 1.5]; P < .001). Similarly, the PCSM-MMAI score showed a strong prognostic signal for DDM in both AA (sHR, 1.3 [95% CI, 1.1 to 1.5]; P = .001) and non-AA subgroups (sHR, 1.5 [95% CI, 1.4 to 1.6]; P < .001), with similar distributions of risk. CONCLUSION Using cooperative group data sets with a racially diverse population, the MMAI algorithm performed well across racial subgroups without evidence of algorithmic bias.
Collapse
Affiliation(s)
| | | | - Osama Mohamad
- University of California San Francisco, San Francisco, CA
| | | | | | | | | | | | | | - Todd M Morgan
- University of Michigan Comprehensive Cancer Center, Ann Arbor, MI
| | | | | | | | | | - Farah Naz
- Horizon Health Network-Saint John Regional Hospital, Saint John, NB
| | | | - Jean-Paul Bahary
- CHUM-Centre Hospitalier de l'Universite de Montreal, Montreal, QC
| | - Derek Wilke
- Nova Scotia Cancer Centre/Nova Scotia Health/QEII Health Sciences Centre, Halifax, NS
| | | | | | - Sergio Faria
- The Research Institute of the McGill University Health Centre (MUHC), Montreal, QC
| | | | | | - Daniel E Spratt
- University Hospitals Seidman Cancer Center, Case Western Reserve University, Cleveland, OH
| | - Stephanie L Pugh
- NRG Oncology Statistics and Data Management Center, Philadelphia, PA
- American College of Radiology, Philadelphia, PA
| | | | - Phuoc T Tran
- Johns Hopkins University/Sidney Kimmel Cancer Center, Baltimore, MD
| | - Felix Y Feng
- University of California San Francisco, San Francisco, CA
| |
Collapse
|
|
44
|
Thomas JL, Heagerty AHM, Goldberg Oppenheimer P. Emerging Technologies for Timely Point-of-Care Diagnostics of Skin Cancer. GLOBAL CHALLENGES (HOBOKEN, NJ) 2025; 9:2400274. [PMID: 40352638 PMCID: PMC12065104 DOI: 10.1002/gch2.202400274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/27/2024] [Revised: 01/07/2025] [Indexed: 05/14/2025]
Abstract
Skin cancer is a global health crisis and a leading cause of morbidity and mortality worldwide. A leading factor of malignancy remains the UV radiation, driving various biomolecular changes. With shifting population behaviors, deficiency in screening programs and reliance on self-presentation, climate change and the ageing world populace, global incidents have been surging alarmingly. There is an urgent need for new technologies to achieve timely intervention through rapid and accurate diagnostics of skin cancer. Raman spectroscopy has been emerging as a highly promising analytical technology for diagnostic applications, poised to outpace the current costly, invasive and slow procedures, frequently hindered by varying sensitivity, specificity and lack of portability. Herein, complex and intricate progress are overviewed and consolidated across medical and engineering disciplines with a focus on the latest advances in the traditional and emerging skin cancer diagnostics. Methods detecting structural and chemical responses are categorized along with emerging chemo-biophysical sensing techniques. Particular attention is drawn to Raman spectroscopy, as a non-invasive, rapid and accurate sensing of molecular fingerprints in dermatological matrix with an additional focus on artificial intelligence, as a decision support tool collectively, laying the platform toward development and rapid translation of point-of-care diagnostic technologies for skin cancer to real-world applications.
Collapse
Affiliation(s)
- Jarrod L. Thomas
- Advanced Nanomaterials Structures and Applications LaboratoriesSchool of Chemical EngineeringCollege of Engineering and Physical SciencesUniversity of BirminghamEdgbastonBirminghamB15 2TTUK
- Healthcare Technologies InstituteInstitute of Translational MedicineMindelsohn WayBirminghamB15 2THUK
| | - Adrian H. M. Heagerty
- Department of DermatologyUniversity Hospitals Birmingham NHS Foundation TrustMindelsohn WayBirminghamB15 2GWUK
- Institute of Inflammation and AgeingCollege of Medical and Dental SciencesMindelsohn WayBirminghamB15 2GWUK
| | - Pola Goldberg Oppenheimer
- Advanced Nanomaterials Structures and Applications LaboratoriesSchool of Chemical EngineeringCollege of Engineering and Physical SciencesUniversity of BirminghamEdgbastonBirminghamB15 2TTUK
- Healthcare Technologies InstituteInstitute of Translational MedicineMindelsohn WayBirminghamB15 2THUK
| |
Collapse
|
|
45
|
Sivasubramanian S, Raval A. Artificial Intelligence-augmented public health interventions in India. HEALTH AFFAIRS SCHOLAR 2025; 3:qxaf097. [PMID: 40443397 PMCID: PMC12120350 DOI: 10.1093/haschl/qxaf097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/16/2025] [Revised: 04/08/2025] [Accepted: 05/06/2025] [Indexed: 06/02/2025]
Abstract
The adoption and scaling of technology in public health settings in the Global South have traditionally been challenging. The introduction of artificial intelligence (AI) technology has exacerbated the challenges, but AI also brings with it exciting new frontiers. India is a large, diverse country that encapsulates well the challenges and opportunities for AI in the Global South. Here, we describe the landscape for AI as a force for driving public health outcomes in India and the critical role in this played by technology platforms. We give examples of our own work in Tuberculosis and infant health to illustrate how AI can be fruitfully integrated into large-scale platforms in order to meaningfully address gaps in public health. Finally, we point out the importance of learning lessons from early deployments on these platforms, despite the varying levels of AI maturity and readiness across modalities.
Collapse
Affiliation(s)
| | - Alpan Raval
- Wadhwani Institute for Artificial Intelligence, New Delhi 110024, India
| |
Collapse
|
|
46
|
Guidoux C, Jouvent E. Editorial commentary: Artificial intelligence, atrial fibrillation, and stroke: AII about removing barriers. Trends Cardiovasc Med 2025; 35:212-213. [PMID: 39952448 DOI: 10.1016/j.tcm.2025.02.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/02/2025] [Accepted: 02/02/2025] [Indexed: 02/17/2025]
Affiliation(s)
- Celine Guidoux
- APHP, Bichat Hospital, Department of Neurology and FHU NeuroVasc 2030, F-75475 Paris, France
| | - Eric Jouvent
- APHP, Lariboisière Hospital, Department of Neurology and FHU NeuroVasc 2030, F-75475 Paris, France; Université Paris Cité, France.
| |
Collapse
|
|
47
|
Liu J, Sandhu K, Woon DTS, Perera M, Lawrentschuk N. The Value of Artificial Intelligence in Prostate-Specific Membrane Antigen Positron Emission Tomography: An Update. Semin Nucl Med 2025; 55:371-376. [PMID: 39893058 DOI: 10.1053/j.semnuclmed.2024.12.001] [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: 12/03/2024] [Revised: 12/15/2024] [Accepted: 12/17/2024] [Indexed: 02/04/2025]
Abstract
This review aims to provide an up-to-date overview of the utility of artificial intelligence (AI) in evaluating prostate-specific membrane antigen (PSMA) positron emission tomography (PET) scans for prostate cancer (PCa). A literature review was conducted on the Medline, Embase, Web of Science, and IEEE Xplore databases. The search focused on studies that utilizes AI to evaluate PSMA PET scans. Original English language studies published from inception to October 2024 were included, while case reports, series, commentaries, and conference proceedings were excluded. AI applications show promise in automating the detection of metastatic disease and anatomical segmentation in PSMA PET scans. AI was also able to predict response to PSMA-based theragnostic and aids in tumor burden segmentation, improving radiotherapy planning. AI could also differentiate intraprostatic PCa with higher histological grade and predict extra-prostatic extension. AI has potential in evaluating PSMA PET scans for PCa, particularly in detecting metastasis, measuring tumor burden, detecting high grade intraprostatic cancer, and predicting treatment outcomes. Larger multicenter prospective studies are necessary to validate and enhance the generalizability of these AI models.
Collapse
Affiliation(s)
- Jianliang Liu
- EJ Whitten Prostate Cancer Research Centre, Epworth Healthcare, Melbourne, Australia; Department of Urology, The Royal Melbourne Hospital, University of Melbourne, Melbourne, Australia; University of Melbourne, Department of Surgery, Melbourne, Australia; Department of Cancer Surgery, Peter MacCallum Cancer Centre, Melbourne, Australia
| | - Kieran Sandhu
- Department of Cancer Surgery, Peter MacCallum Cancer Centre, Melbourne, Australia
| | - Dixon T S Woon
- EJ Whitten Prostate Cancer Research Centre, Epworth Healthcare, Melbourne, Australia; University of Melbourne, Department of Surgery, Melbourne, Australia
| | - Marlon Perera
- University of Melbourne, Department of Surgery, Melbourne, Australia; Department of Cancer Surgery, Peter MacCallum Cancer Centre, Melbourne, Australia
| | - Nathan Lawrentschuk
- EJ Whitten Prostate Cancer Research Centre, Epworth Healthcare, Melbourne, Australia; Department of Urology, The Royal Melbourne Hospital, University of Melbourne, Melbourne, Australia; University of Melbourne, Department of Surgery, Melbourne, Australia; Department of Cancer Surgery, Peter MacCallum Cancer Centre, Melbourne, Australia.
| |
Collapse
|
|
48
|
Reincke SM, Espinosa C, Chung P, James T, Berson E, Aghaeepour N. Mitigation of outcome conflation in predicting patient outcomes using electronic health records. J Am Med Inform Assoc 2025; 32:920-927. [PMID: 40056434 PMCID: PMC12012356 DOI: 10.1093/jamia/ocaf033] [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: 10/17/2024] [Revised: 02/04/2025] [Accepted: 02/18/2025] [Indexed: 03/10/2025] Open
Abstract
OBJECTIVES Artificial intelligence (AI) models utilizing electronic health record data for disease prediction can enhance risk stratification but may lack specificity, which is crucial for reducing the economic and psychological burdens associated with false positives. This study aims to evaluate the impact of confounders on the specificity of single-outcome prediction models and assess the effectiveness of a multi-class architecture in mitigating outcome conflation. MATERIALS AND METHODS We evaluated a state-of-the-art model predicting pancreatic cancer from disease code sequences in an independent cohort of 2.3 million patients and compared this single-outcome model with a multi-class model designed to predict multiple cancer types simultaneously. Additionally, we conducted a clinical simulation experiment to investigate the impact of confounders on the specificity of single-outcome prediction models. RESULTS While we were able to independently validate the pancreatic cancer prediction model, we found that its prediction scores were also correlated with ovarian cancer, suggesting conflation of outcomes due to underlying confounders. Building on this observation, we demonstrate that the specificity of single-outcome prediction models is impaired by confounders using a clinical simulation experiment. Introducing a multi-class architecture improves specificity in predicting cancer types compared to the single-outcome model while preserving performance, mitigating the conflation of outcomes in both the real-world and simulated contexts. DISCUSSION Our results highlight the risk of outcome conflation in single-outcome AI prediction models and demonstrate the effectiveness of a multi-class approach in mitigating this issue. CONCLUSION The number of predicted outcomes needs to be carefully considered when employing AI disease risk prediction models.
Collapse
Affiliation(s)
- S Momsen Reincke
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States
| | - Camilo Espinosa
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States
| | - Philip Chung
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
| | - Tomin James
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States
| | - Eloïse Berson
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States
- Department of Pathology, Stanford University, Stanford, CA 94305, United States
| | - Nima Aghaeepour
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, United States
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States
| |
Collapse
|
|
49
|
Mayfield JD, Romero J. Establishing a Chain of Evidence for AI in Radiology: Sham AI and Randomized Controlled Trials. Radiol Artif Intell 2025; 7:e250334. [PMID: 40434278 DOI: 10.1148/ryai.250334] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/29/2025]
Affiliation(s)
- John D Mayfield
- Division of Neuroradiology, Massachusetts General Hospital/Harvard Medical School, 55 Fruit Street, Boston, MA 02114
| | - Javier Romero
- Division of Neuroradiology, Massachusetts General Hospital/Harvard Medical School, 55 Fruit Street, Boston, MA 02114
| |
Collapse
|
|
50
|
Berger M, Licandro R, Nenning KH, Langs G, Bonelli SB. Artificial intelligence applied to epilepsy imaging: Current status and future perspectives. Rev Neurol (Paris) 2025; 181:420-424. [PMID: 40175210 DOI: 10.1016/j.neurol.2025.03.006] [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: 02/16/2025] [Revised: 03/20/2025] [Accepted: 03/23/2025] [Indexed: 04/04/2025]
Abstract
In recent years, artificial intelligence (AI) has become an increasingly prominent focus of medical research, significantly impacting epileptology as well. Studies on deep learning (DL) and machine learning (ML) - the core of AI - have explored their applications in epilepsy imaging, primarily focusing on lesion detection, lateralization and localization of epileptogenic areas, postsurgical outcome prediction and automatic differentiation between people with epilepsy and healthy individuals. Various AI-driven approaches are being investigated across different neuroimaging modalities, with the ultimate goal of integrating these tools into clinical practice to enhance the diagnosis and treatment of epilepsy. As computing power continues to advance, the development, research integration, and clinical implementation of AI applications are expected to accelerate, making them even more effective and accessible. However, ensuring the safety of patient data will require strict regulatory measures. Despite these challenges, AI represents a transformative opportunity for medicine, particularly in epilepsy neuroimaging. Since ML and DL models thrive on large datasets, fostering collaborations and expanding open-access databases will become increasingly pivotal in the future.
Collapse
Affiliation(s)
- M Berger
- Department of Neurology, Medical University of Vienna, Spitalgasse 23, 1090 Vienna, Austria.
| | - R Licandro
- Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
| | - K-H Nenning
- Nathan S. Kline Institute for Psychiatric Research, Orangeburg, NY, USA
| | - G Langs
- Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria
| | - S B Bonelli
- Department of Neurology, Medical University of Vienna, Spitalgasse 23, 1090 Vienna, Austria
| |
Collapse
|