JMIR Medical Informatics最新文献

{"title":"YOLOv12 Algorithm-Aided Detection and Classification of Lateral Malleolar Avulsion Fracture and Subfibular Ossicle Based on CT Images: Multicenter Study.","authors":"Jiayi Liu, Peng Sun, Yousheng Yuan, Zihan Chen, Ke Tian, Qian Gao, Xiangsheng Li, Liang Xia, Jun Zhang, Nan Xu","doi":"10.2196/79064","DOIUrl":"10.2196/79064","url":null,"abstract":"<p><strong>Background: </strong>Lateral malleolar avulsion fractures (LMAFs) and subfibular ossicles (SFOs) are distinct entities that both present as small bone fragments near the lateral malleolus in imaging but require different treatment strategies. Clinical and radiological differentiation is challenging, which can impede timely and precise management. Magnetic resonance imaging (MRI) is the diagnostic gold standard for differentiating LMAFs from SFOs, whereas radiological differentiation using computed tomography (CT) alone is challenging in routine practice. Deep convolutional neural networks (DCNNs) have shown promise in musculoskeletal imaging diagnostics, but robust, multicenter evidence in this specific context is lacking.</p><p><strong>Objective: </strong>This study aims to evaluate several state-of-the-art DCNNs-including the latest You Only Look Once (YOLO) v12 algorithm-for detecting and classifying LMAFs and SFOs in CT images, using MRI-based diagnoses as the gold standard and to compare model performance with radiologists reading CT alone.</p><p><strong>Methods: </strong>In this retrospective study, 1918 patients (LMAF: n=1253, 65.3%; SFO: n=665, 34.7%) were enrolled from 2 hospitals in China between 2014 and 2024. MRI served as the gold standard and was independently interpreted by 2 senior musculoskeletal radiologists. Only CT images were used for model training, validation, and testing. CT images were manually annotated with bounding boxes. The cohort was randomly split into a training set (n=1092, 56.93%), internal validation set (n=476, 24.82%), and external test set (n=350, 18.25%). Four deep learning models-faster R-CNN, single shot multibox detector (SSD), RetinaNet, and YOLOv12-were trained and evaluated using identical procedures. Model performance was assessed using mean average precision at intersection over union=0.5 (mAP50), area under the receiver operating curve (AUC), accuracy, sensitivity, and specificity. The external test set was also independently interpreted by 2 musculoskeletal radiologists with 7 and 15 years of experience, with results compared with the best-performing model. Saliency maps were generated using Shapley values to enhance interpretability.</p><p><strong>Results: </strong>Among the evaluated models, YOLOv12 achieved the highest detection and classification performance, with a mAP50 of 92.1% and an AUC of 0.983 on the external test set-significantly outperforming faster R-CNN (mAP50 63.7%; AUC 0.79); SSD (mAP50 63%; AUC 0.63); and RetinaNet (mAP50 67.0%; AUC 0.73)-all P<.001. When using CT alone, radiologists performed at a moderate level (accuracy: 75.6% and 69.1%; sensitivity: 75.0% and 65.2%; specificity: 76.0% and 71.1%), whereas YOLOv12 approached MRI-based reference performance (accuracy: 92.0%; sensitivity: 86.7%; specificity: 82.2%). Saliency maps corresponded well with expert-identified regions.</p><p><strong>Conclusions: </strong>While MRI (read by senior radiologists) is the gold st","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":" ","pages":"e79064"},"PeriodicalIF":3.8,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145024832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Context to Care: Rethinking Stigma Detection in Clinical Language Models.","authors":"Shefali Haldar, Oliver Bear Don't Walk Iv, Sadia Akter","doi":"10.2196/82484","DOIUrl":"10.2196/82484","url":null,"abstract":"<p><strong>Unlabelled: </strong>Natural language processing techniques are useful for identifying stigmatizing language in electronic health records but require careful consideration. This commentary article builds on \"Efficient Detection of Stigmatizing Language in Electronic Health Records via In-Context Learning\" by Chen et al, which highlights the importance of incorporating situational and temporal contexts in annotation and modeling efforts. We emphasize the need for researchers to explicitly articulate their paradigms and positionality, particularly when working with populations disproportionately affected by stigmatizing language. We also explore the differences arising from conflicting preferences across communities about what constitutes destigmatizing language. We discuss participatory and trust-centered approaches for model development to work toward unbiased impact. Such strategies have a crucial role in raising awareness and fostering inclusive health care.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e82484"},"PeriodicalIF":3.8,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12490770/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneous Network With Multiview Path Aggregation: Drug-Target Interaction Prediction Study Design.","authors":"Haixue Zhao, Kui Yao, Yunjiong Liu, Chao Che, Lin Tang","doi":"10.2196/74974","DOIUrl":"10.2196/74974","url":null,"abstract":"<p><strong>Background: </strong>Drug-target interaction (DTI) prediction is crucial in drug repositioning, as it can significantly reduce research and development costs and shorten the development cycle. Most existing deep learning-based approaches employ graph neural networks for DTI prediction. However, these approaches still face limitations in capturing complex biochemical features, integrating multilevel information, and providing interpretable model insights.</p><p><strong>Objective: </strong>This study proposes a heterogeneous network model based on multiview path aggregation, aiming to predict interactions between drugs and targets.</p><p><strong>Methods: </strong>This study employed a molecular attention transformer to extract 3D conformation features from the chemical structures of drugs and utilized Prot-T5, a protein-specific large language model, to deeply explore biophysically and functionally relevant features from protein sequences. By integrating drugs, proteins, diseases, and side effects from multisource heterogeneous data, we constructed a heterogeneous graph model to systematically characterize multidimensional associations between biological entities. On this foundation, a meta-path aggregation mechanism was proposed, which dynamically integrates information from both feature views and biological network relationship views. This mechanism effectively learned potential interaction patterns between biological entities and provided a more comprehensive representation of the complex relationships in the heterogeneous graph. It enhanced the model's ability to capture sophisticated, context-dependent relationships in biological networks. Furthermore, we integrated multiscale features of drugs and proteins within the heterogeneous network, significantly improving the prediction accuracy of DTIs and enhancing the model's interpretability and generalization ability.</p><p><strong>Results: </strong>In the DTI prediction task, the proposed model achieves an AUPR (area under the precision-recall curve) of 0.901 and an AUROC (area under the receiver operating characteristic curve) of 0.966, representing improvements of 1.7% and 0.8%, respectively, over the baseline methods. Furthermore, a case study on the KCNH2 target demonstrates that the proposed model successfully predicts 38 out of 53 candidate drugs as having interactions, which further validates its reliability and practicality in real-world scenarios.</p><p><strong>Conclusions: </strong>The proposed model shows marked superiority over baseline methods, highlighting the importance of integrating heterogeneous information with biological knowledge in DTI prediction.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e74974"},"PeriodicalIF":3.8,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12490815/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Innovative Integration of 4D Cardiovascular Reconstruction and Hologram: Framework Development of a New Visualization Tool for Coronary Artery Bypass Grafting Planning.","authors":"Shuo Wang, Tong Ren, Nan Cheng, Li Zhang, Rong Wang","doi":"10.2196/72237","DOIUrl":"10.2196/72237","url":null,"abstract":"<p><strong>Background: </strong>Planning for coronary artery bypass grafting (CABG) necessitates advanced spatial visualization skills and consideration of multiple factors, including the depth of coronary arteries within the subepicardium, calcification levels, and pericardial adhesions.</p><p><strong>Objective: </strong>This study aimed to address these requirements by reconstructing a dynamic cardiovascular model, displaying it as a naked-eye hologram, and evaluating the clinical utility of this innovative visualization tool for preoperative CABG planning.</p><p><strong>Methods: </strong>We used preoperative 4D cardiac computed tomography angiography (4D-CCTA) data from 14 patients scheduled for CABG to develop a semiautomated workflow. This workflow enabled time-resolved segmentation of the heart chambers, epicardial adipose tissue (EAT), and coronary arteries, complete with calcium scoring. Methods for segmenting cardiac structures, quantifying coronary calcification, visualizing coronary depth within EAT, and assessing pericardial adhesions via motion analysis were incorporated. These dynamic reconstructions captured spatial relationships, coronary stenosis, calcification, and depth in EAT, as well as pericardial adhesions. Dynamic cardiovascular holograms were then generated and displayed using the Looking Glass platform (Looking Glass Factory Inc). Thirteen cardiac surgeons assessed the utility of the holographic visualization tool on a Likert scale. In addition, a surgeon visually scored pericardial adhesions using the holograms of all 21 patients (including 7 undergoing secondary cardiac surgeries) and compared these scores with actual intraoperative findings.</p><p><strong>Results: </strong>Cardiac surgeons highly rated the visualization tool for its utility in preoperative planning, with a mean Likert score of 4.57/5.0 (SD 0.5). The hologram-based scoring of pericardial adhesions showed a strong correlation with intraoperative findings (correlation coefficient r=0.786; P<.001).</p><p><strong>Conclusions: </strong>This study delineates the structural framework of a visualization tool specifically designed for preoperative CABG planning. It produces high-quality, clinically relevant, dynamic holograms from patient-specific volumetric data, with clinical feedback confirming its practicality and effectiveness for preoperative surgical planning.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e72237"},"PeriodicalIF":3.8,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12483336/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Analysis of Outcomes of Influenza and COVID-19 Admissions Among Children With Asthma: A Nationwide Retrospective Cohort Study Using the US National Readmissions Database.","authors":"Ying-Chen Chen, Chia-Pi Cheng, Po-Cheng Chen, Jinn-Li Wang, Chia-Chen Wu, Ying-Chun Lu","doi":"10.2196/73047","DOIUrl":"https://doi.org/10.2196/73047","url":null,"abstract":"<p><strong>Background: </strong>Asthma is a common chronic respiratory disease with increasing prevalence among children over the past few decades. It can cause significant respiratory symptoms and acute exacerbations, often requiring emergency care or hospitalization. Moreover, exposure to respiratory viral infections, such as COVID-19 and influenza, can trigger severe complications in children with asthma. Despite these concerns, few studies have directly compared the in-hospital outcomes of children with asthma experiencing these infections.</p><p><strong>Objective: </strong>This study aimed to compare the in-hospital outcomes of these infections in children with asthma from a population-based perspective.</p><p><strong>Methods: </strong>We conducted a population-based retrospective cohort study using data from the 2020 US Nationwide Readmissions Database. Children aged 1 to 19 years with asthma who were admitted for COVID-19 or influenza were eligible for inclusion. Outcomes evaluated included in-hospital mortality, major complications, and 90-day readmission rate. Survey-weighted logistic regression models were used to compare clinical outcomes between the two infection groups, adjusting for demographic and clinical characteristics.</p><p><strong>Results: </strong>A total of 1472 hospitalized children with asthma were included, of whom 405 (27.5%) were admitted for COVID-19 and 1067 (72.5%) for influenza. After adjustment, the multivariate analysis revealed that children admitted for COVID-19 had a significantly higher risk of sepsis or shock (adjusted odds ratio [aOR] 4.30, 95% CI 1.79-10.32) but a lower risk of bacterial or fungal pneumonia (aOR 0.37, 95% CI 0.23-0.61) compared with those admitted for influenza. Stratified analyses by age revealed that among children aged 1 to 5 years, the risk of 90-day readmission was significantly higher for those with COVID-19 than for those with influenza (aOR 3.02, 95% CI 1.09-8.35). No significant difference in in-hospital mortality was detected between the two infection groups in either the multivariable model or any of the age-stratified analyses.</p><p><strong>Conclusions: </strong>US children with asthma hospitalized for COVID-19 had higher risks of sepsis or shock compared to those admitted for influenza. In contrast, children admitted for influenza had a higher risk for bacterial or fungal pneumonia. After stratifying by age, children aged 1 to 5 years with COVID-19 had a significantly higher risk of 90-day readmission than those with influenza. Our findings suggest that different clinical approaches may be needed for children with asthma, depending on infection etiology and patient age.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e73047"},"PeriodicalIF":3.8,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of a Digital Platform for Routine Outcome Monitoring in Psychotherapy: Usability Study and Thematic Analysis.","authors":"Mattia Vincenzo Olive, Antonino La Tona, Gianluca Lo Coco, Angelo Compare, Joseph Antony Cafazzo, Cristina Masella","doi":"10.2196/75885","DOIUrl":"10.2196/75885","url":null,"abstract":"<p><strong>Background: </strong>The integration of digital tools into psychotherapy has gained increasing attention, particularly for practices such as routine outcome monitoring (ROM), which involves the regular collection of patient-reported data to inform treatment decisions. However, despite the potential benefits, the adoption of digital platforms remains limited, partly due to usability concerns and workflow misalignment.</p><p><strong>Objective: </strong>This study aimed to assess the usability of a digital platform, Mindy, designed to support psychotherapists in implementing ROM and to explore broader challenges associated with the integration of digital tools into psychotherapeutic practice.</p><p><strong>Methods: </strong>This study adopted a qualitative, 2-stage approach. Sixteen psychotherapists participated in semistructured interviews, which included task-based usability testing and reflective discussions. Participants interacted with Mindy by performing typical clinical tasks, such as creating patient profiles, managing session data, and sending questionnaires. The first stage of analysis used a deductive thematic approach focused on predefined platform functionalities. The second stage followed an inductive methodology to identify broader themes related to the integration of digital tools in psychotherapy.</p><p><strong>Results: </strong>The usability assessment identified strengths in the platform's appointment scheduling, questionnaire delivery, and dashboard functionalities, which were perceived as intuitive and supportive of ROM practices. However, limitations were reported in areas such as documentation flexibility, interoperability with other systems, and control over information sharing with patients. Broader thematic analysis revealed three main challenges: (1) the tension between standardized documentation and the need for narrative and implicit information; (2) difficulties in embedding digital platforms into existing therapeutic workflows, especially for clinicians less familiar with technology; and (3) concerns about confidentiality and the potential for misinterpretation when sharing therapeutic notes with patients.</p><p><strong>Conclusions: </strong>These findings underscore the importance of considering both technical and contextual dimensions when developing and implementing digital platforms in mental health care. Tailoring digital tools to the needs and practices of psychotherapists may improve adoption and ultimately enhance the quality of care.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e75885"},"PeriodicalIF":3.8,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12483338/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145202244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthetic Tabular Data Generation Under Horizontal Federated Learning Environments in Acute Myeloid Leukemia: Case-Based Simulation Study.","authors":"Imanol Isasa, Mikel Catalina, Gorka Epelde, Naiara Aginako, Andoni Beristain","doi":"10.2196/74116","DOIUrl":"10.2196/74116","url":null,"abstract":"<p><strong>Background: </strong>Data scarcity and dispersion pose significant obstacles in biomedical research, particularly when addressing rare diseases. In such scenarios, synthetic data generation (SDG) has emerged as a promising path to mitigate the first issue. Concurrently, federated learning is a machine learning paradigm where multiple nodes collaborate to create a centralized model with knowledge that is distilled from the data in different nodes, but without the need for sharing it. This research explores the combination of SDG and federated learning technologies in the context of acute myeloid leukemia, a rare hematological disorder, evaluating their combined impact and the quality of the generated artificial datasets.</p><p><strong>Objective: </strong>This study aims to evaluate the privacy- and fidelity-related impact of horizontally federating SDG models in different data distribution scenarios and with different numbers of nodes, comparing them with centralized baseline SDG models.</p><p><strong>Methods: </strong>Two state-of-the-art generative models, conditional tabular generative adversarial network and FedTabDiff, were trained considering four different scenarios: (1) a nonfederated baseline with all the data available, (2) a federated scenario where the data were evenly distributed among different nodes, (3) a federated scenario where the data were unevenly and randomly distributed (imbalanced data), and (4) a federated scenario with nonindependent and identically distributed data distributions. For each of the federated scenarios, a fixed set of node quantities (3, 5, 7, 10) was considered to assess its impact, and the generated data were evaluated, attending to a fidelity-privacy trade-off.</p><p><strong>Results: </strong>The computed fidelity metrics exhibited statistically significant deteriorations (P<.001) up to 21% in the conditional tabular generative adversarial network and up to 62% in the FedTabDiff model due to the federation process. When comparing federated experiments trained with diverse numbers of nodes, no strong tendencies were observed, even if specific comparisons resulted in significative differences. Privacy metrics were mainly maintained while obtaining maximum improvements of 55% and maximum deteriorations of 26% between both models, although they were not statistically significant.</p><p><strong>Conclusions: </strong>Within the scope of the use case scenario in this paper, the act of horizontally federating SDG algorithms results in a loss of data fidelity compared to the nonfederated baseline while maintaining privacy levels. However, this deterioration does not significantly increase as the number of nodes used to train the models grows, even though significative differences were found in specific comparisons. The different data partition distribution configurations had no significant effect on the metrics, as similar tendencies were found for all scenarios.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e74116"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Large Language Models for Chronic Disease Management Tasks: Scoping Review.","authors":"Henry Mukalazi Serugunda, Ouyang Jianquan, Hasifah Kasujja Namatovu, Paul Ssemaluulu, Nasser Kimbugwe, Christopher Garimoi Orach, Peter Waiswa","doi":"10.2196/66905","DOIUrl":"10.2196/66905","url":null,"abstract":"<p><strong>Background: </strong>Chronic diseases present significant challenges in health care, requiring effective management to reduce morbidity and mortality. While digital technologies like wearable devices and mobile applications have been widely adopted, large language models (LLMs) such as ChatGPT are emerging as promising technologies with the potential to enhance chronic disease management. However, the scope of their current applications in chronic disease management and associated challenges remains underexplored.</p><p><strong>Objective: </strong>This scoping review investigates LLM applications in chronic disease management, identifies challenges, and proposes actionable recommendations.</p><p><strong>Methods: </strong>A systematic search for English-language primary studies on LLM use in chronic disease management was conducted across PubMed, IEEE Xplore, Scopus, and Google Scholar to identify articles published between January 1, 2023, and January 15, 2025. Of the 605 screened records, 29 studies met the inclusion criteria. Data on study objectives, LLMs used, health care settings, study designs, users, disease management tasks, and challenges were extracted and thematically analyzed using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines.</p><p><strong>Results: </strong>LLMs were primarily used for patient-centered tasks, including patient education and information provision (18/29, 62%) of studies, diagnosis and treatment (6/29, 21%), self-management and disease monitoring (8/29, 28%), and emotional support and therapeutic conversations (4/29, 14%). Practitioner-centered tasks included clinical decision support (8/29, 28%) and medical predictions (6/29, 21%). Challenges identified include inaccurate and inconsistent LLM responses (18/29, 62%), limited datasets (6/29, 21%), computational and technical (6/29, 21%), usability and accessibility (9/29, 31%), LLM evaluation (5/29, 17%), and legal, ethical, privacy, and regulatory (10/29, 35%). While models like ChatGPT, Llama, and Bard demonstrated use in diabetes management and mental health support, performance issues were evident across studies and use cases.</p><p><strong>Conclusions: </strong>LLMs show promising potential for enhancing chronic disease management across patient and practitioner-centered tasks. However, challenges related to accuracy, data scarcity, usability, and ethical concerns must be addressed to ensure patient safety and equitable use. Future studies should prioritize the integration of LLMs with low-resource platforms, wearable and mobile technologies, developing culturally and age-appropriate interfaces, and establishing robust regulatory and evaluation frameworks to support safe, effective, and inclusive use in health care.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e66905"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12479051/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145193980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data Contamination in AI Evaluation.","authors":"Alaeddin Acar","doi":"10.2196/80987","DOIUrl":"https://doi.org/10.2196/80987","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e80987"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Author's Reply: \"Data Contamination in AI Evaluation\".","authors":"ChulHyoung Park, Min Ho An, Gyubeom Hwang, Rae Woong Park, Juho An","doi":"10.2196/82057","DOIUrl":"https://doi.org/10.2196/82057","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e82057"},"PeriodicalIF":3.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}