JMIR Medical Informatics最新文献

{"title":"Comparing Diagnostic Accuracy of Clinical Professionals and Large Language Models: Systematic Review and Meta-Analysis.","authors":"Guxue Shan, Xiaonan Chen, Chen Wang, Li Liu, Yuanjing Gu, Huiping Jiang, Tingqi Shi","doi":"10.2196/64963","DOIUrl":"10.2196/64963","url":null,"abstract":"<p><strong>Background: </strong>With the rapid development of artificial intelligence (AI) technology, especially generative AI, large language models (LLMs) have shown great potential in the medical field. Through massive medical data training, it can understand complex medical texts and can quickly analyze medical records and provide health counseling and diagnostic advice directly, especially in rare diseases. However, no study has yet compared and extensively discussed the diagnostic performance of LLMs with that of physicians.</p><p><strong>Objective: </strong>This study systematically reviewed the accuracy of LLMs in clinical diagnosis and provided reference for further clinical application.</p><p><strong>Methods: </strong>We conducted searches in CNKI (China National Knowledge Infrastructure), VIP Database, SinoMed, PubMed, Web of Science, Embase, and CINAHL (Cumulative Index to Nursing and Allied Health Literature) from January 1, 2017, to the present. A total of 2 reviewers independently screened the literature and extracted relevant information. The risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST), which evaluates both the risk of bias and the applicability of included studies.</p><p><strong>Results: </strong>A total of 30 studies involving 19 LLMs and a total of 4762 cases were included. The quality assessment indicated a high risk of bias in the majority of studies, primary cause is known case diagnosis. For the optimal model, the accuracy of the primary diagnosis ranged from 25% to 97.8%, while the triage accuracy ranged from 66.5% to 98%.</p><p><strong>Conclusions: </strong>LLMs have demonstrated considerable diagnostic capabilities and significant potential for application across various clinical cases. Although their accuracy still falls short of that of clinical professionals, if used cautiously, they have the potential to become one of the best intelligent assistants in the field of human health care.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64963"},"PeriodicalIF":3.1,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12047852/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031279","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":"Integrating Health Care Data in an Informatics for Integrating Biology & the Bedside (i2b2) Model Persisted Through Elasticsearch: Design, Implementation, and Evaluation in a French University Hospital.","authors":"Romain Griffier, Fleur Mougin, Vianney Jouhet","doi":"10.2196/65753","DOIUrl":"https://doi.org/10.2196/65753","url":null,"abstract":"<p><strong>Background: </strong>The volume of digital data in health care is continually growing. In addition to its use in health care, the health data collected can also serve secondary purposes, such as research. In this context, clinical data warehouses (CDWs) provide the infrastructure and organization necessary to enhance the secondary use of health data. Various data models have been proposed for structuring data in a CDW, including the Informatics for Integrating Biology & the Bedside (i2b2) model, which relies on a relational database. However, this persistence approach can lead to performance issues when executing queries on massive data sets.</p><p><strong>Objective: </strong>This study aims to describe the necessary transformations and their implementation to enable i2b2's search engine to perform the phenotyping task using data persistence in a NoSQL Elasticsearch database.</p><p><strong>Methods: </strong>This study compares data persistence in a standard relational database with a NoSQL Elasticsearch database in terms of query response and execution performance (focusing on counting queries based on structured data, numerical data, and free text, including temporal filtering) as well as material resource requirements. Additionally, the data loading and updating processes are described.</p><p><strong>Results: </strong>We propose adaptations to the i2b2 model to accommodate the specific features of Elasticsearch, particularly its inability to perform joins between different indexes. The implementation was tested and evaluated within the CDW of Bordeaux University Hospital, which contains data on 2.5 million patients and over 3 billion observations. Overall, Elasticsearch achieves shorter query execution times compared with a relational database, with particularly significant performance gains for free-text searches. Additionally, compared with an indexed relational database (including a full-text index), Elasticsearch requires less disk space for storage.</p><p><strong>Conclusions: </strong>We demonstrate that implementing i2b2 with Elasticsearch is feasible and significantly improves query performance while reducing disk space usage. This implementation is currently in production at Bordeaux University Hospital.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e65753"},"PeriodicalIF":3.1,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12062766/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058613","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":"Prediction of Snacking Behavior Involving Snacks Having High Levels of Saturated Fats, Salt, or Sugar Using Only Information on Previous Instances of Snacking: Survey- and App-Based Study.","authors":"Shaima Dammas, Tillman Weyde, Katy Tapper, Gerasimos Spanakis, Anne Roefs, Emmanuel M Pothos","doi":"10.2196/57530","DOIUrl":"https://doi.org/10.2196/57530","url":null,"abstract":"<p><strong>Background: </strong>Consuming high amounts of foods or beverages with high levels of saturated fats, salt, or sugar (HFSS) can be harmful for health. Many snacks fall into this category (HFSS snacks). However, the palatability of these snacks means that people can sometimes struggle to reduce their intake. Machine learning algorithms could help in predicting the likely occurrence of HFSS snacking so that just-in-time adaptive interventions can be deployed. However, HFSS snacking data have certain characteristics, such as sparseness and incompleteness, which make snacking prediction a challenge for machine learning approaches. Previous attempts have employed several potential predictor variables and have achieved considerable success. Nevertheless, collecting information from several dimensions requires several potentially burdensome user questionnaires, and thus, this approach may be less acceptable for the general public.</p><p><strong>Objective: </strong>Our aim was to consider the capacity of standard (unmodified in any way; to tailor to the specific learning problem) machine learning algorithms to predict HFSS snacking based on the following minimal data that can be collected in a mostly automated way: day of the week, time of the day (divided into time bins), and location (divided into work, home, and other).</p><p><strong>Methods: </strong>A total of 111 participants in the United Kingdom were asked to record HFSS snacking occurrences and the location category over a period of 28 days, and this was considered the UK dataset. Data collection was facilitated by a purpose-specific app (Snack Tracker). Additionally, a similar dataset from the Netherlands was used (Dutch dataset). Both datasets were analyzed using machine learning methods, including random forest regressor, Extreme Gradient Boosting regressor, feed forward neural network, and long short-term memory. We additionally employed 2 baseline statistical models for prediction. In all cases, the prediction problem was the time to the next HFSS snack from the current one, and the evaluation metric was the mean absolute error.</p><p><strong>Results: </strong>The ability of machine learning methods to predict the time of the next HFSS snack was assessed. The quality of the prediction depended on the dataset, temporal resolution, and machine learning algorithm employed. In some cases, predictions were accurate to as low as 17 minutes on average. In general, machine learning methods outperformed the baseline models, but no machine learning method was clearly better than the others. Feed forward neural network showed a very marginal advantage.</p><p><strong>Conclusions: </strong>The prediction of HFSS snacking using sparse data is possible with reasonable accuracy. Our findings offer a foundation for further exploring how machine learning methods can be used in health psychology and provide directions for further research.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e57530"},"PeriodicalIF":3.1,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12059507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143999022","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":"Expectations of Intensive Care Physicians Regarding an AI-Based Decision Support System for Weaning From Continuous Renal Replacement Therapy: Predevelopment Survey Study.","authors":"Benjamin Popoff, Sandie Cabon, Marc Cuggia, Guillaume Bouzillé, Thomas Clavier","doi":"10.2196/63709","DOIUrl":"https://doi.org/10.2196/63709","url":null,"abstract":"<p><strong>Background: </strong>Critically ill patients in intensive care units (ICUs) require continuous monitoring, generating vast amounts of data. Clinical decision support systems (CDSS) leveraging artificial intelligence (AI) technologies have shown promise in improving diagnostic, prognostic, and therapeutic decision-making. However, these models are rarely implemented in clinical practice.</p><p><strong>Objective: </strong>The aim of this study was to survey ICU physicians to understand their expectations, opinions, and level of knowledge regarding a proposed AI-based CDSS for continuous renal replacement therapy (CRRT) weaning, a clinical decision-making process that is still complex and lacking in guidelines. This will be used to guide the development of an AI-based CDSS on which our team is working to ensure user-centered design and successful integration into clinical practice.</p><p><strong>Methods: </strong>A prospective cross-sectional survey of French-speaking physicians with clinical activity in intensive care was conducted between December 2023 and April 2024. The questionnaire consisted of 20 questions structured around 4 axes: overview of the problem and current practices concerning weaning from CRRT, opinion on AI-based CDSS, implementation in daily clinical practice, real-life operation and willingness to adopt the CDSS in everyday practice. Statistical analyses included Wilcoxon rank sum tests for quantitative variables and χ2 or Fisher exact tests for qualitative variables, with multivariate analyses performed using ordinal logistic regression.</p><p><strong>Results: </strong>A total of 171 complete responses were received. Physicians expressed an interest in a CDSS for CRRT weaning, with 70.2% (120/171) viewing AI-based CDSS favorably. Opinions were split regarding the difficulty of the weaning decision itself, with 46.2% (79/171) disagreeing that it is challenging, while 31.6% (54/171) agreed. However, 66.1% (113/171) of respondents supported the value of an AI-based CDSS to assist them in this decision, with younger physicians showing stronger support (81.8%, 27/33 vs 62.3%; 86/138; P=.01). Most respondents (163/171, 95.3%) emphasized the importance of understanding the criteria used by the model to make its predictions.</p><p><strong>Conclusions: </strong>Our findings highlight an optimistic attitude among ICU physicians toward AI-based CDSS for CRRT weaning, emphasizing the need for transparency, integration into existing workflows, and alignment with clinicians' decision-making processes. Actionable recommendations include incorporating key variables such as urine output and biological parameters, defining probability thresholds for recommendations and ensuring model transparency to facilitate the successful adoption and integration into clinical practice. The methodology of this survey may help the development of further predevelopment studies accompanying AI-based CDSS projects.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e63709"},"PeriodicalIF":3.1,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12043247/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144029472","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":"Authors' Reply: The Anemia Risk Warning Model Based on a Noninvasive Method: Key Insights and Clarifications.","authors":"Yahan Zhang, Yi Chun, Liping Tu, Jiatuo Xu","doi":"10.2196/74333","DOIUrl":"https://doi.org/10.2196/74333","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e74333"},"PeriodicalIF":3.1,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12056428/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060057","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":"The Anemia Risk Warning Model Based on a Noninvasive Method: Key Insights and Clarifications.","authors":"Jiaqi Wei, Nana Zheng, Depei Wu","doi":"10.2196/73297","DOIUrl":"https://doi.org/10.2196/73297","url":null,"abstract":"","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e73297"},"PeriodicalIF":3.1,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12056412/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143993523","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":"Effect of Uncertainty-Aware AI Models on Pharmacists' Reaction Time and Decision-Making in a Web-Based Mock Medication Verification Task: Randomized Controlled Trial.","authors":"Corey Lester, Brigid Rowell, Yifan Zheng, Zoe Co, Vincent Marshall, Jin Yong Kim, Qiyuan Chen, Raed Kontar, X Jessie Yang","doi":"10.2196/64902","DOIUrl":"https://doi.org/10.2196/64902","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Artificial intelligence (AI)-based clinical decision support systems are increasingly used in health care. Uncertainty-aware AI presents the model's confidence in its decision alongside its prediction, whereas black-box AI only provides a prediction. Little is known about how this type of AI affects health care providers' work performance and reaction time.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to determine the effects of black-box and uncertainty-aware AI advice on pharmacist decision-making and reaction time.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Recruitment emails were sent to pharmacists through professional listservs describing a web-based, crossover, randomized controlled trial. Participants were randomized to the black-box AI or uncertainty-aware AI condition in a 1:1 manner. Participants completed 100 mock verification tasks with AI help and 100 without AI help. The order of no help and AI help was randomized. Participants were exposed to correct and incorrect prescription fills, where the correct decision was to \"accept\" or \"reject,\" respectively. AI help provided correct (79%) or incorrect (21%) advice. Reaction times, participant decisions, AI advice, and AI help type were recorded for each verification. Likelihood ratio tests compared means across the three categories of AI type for each level of AI correctness.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 30 participants provided complete datasets. An equal number of participants were in each AI condition. Participants' decision-making performance and reaction times differed across the 3 conditions. Accurate AI recommendations resulted in the rejection of the incorrect drug 96.1% and 91.8% of the time for uncertainty-aware AI and black-box AI respectively, compared with 81.2% without AI help. Correctly dispensed medications were accepted at rates of 99.2% with black-box help, 94.1% with uncertainty-aware AI help, and 94.6% without AI help. Uncertainty-aware AI protected against bad AI advice to approve an incorrectly filled medication compared with black-box AI (83.3% vs 76.7%). When the AI recommended rejecting a correctly filled medication, pharmacists without AI help had a higher rate of correctly accepting the medication (94.6%) compared with uncertainty-aware AI help (86.2%) and black-box AI help (81.2%). Uncertainty-aware AI resulted in shorter reaction times than black-box AI and no AI help except in the scenario where \"AI rejects the correct drug.\" Black-box AI did not lead to reduced reaction times compared with pharmacists acting alone.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Pharmacists' performance and reaction times varied by AI type and AI accuracy. Overall, uncertainty-aware AI resulted in faster decision-making and acted as a safeguard against bad AI advice to approve a misfilled medication. Conversely, black-box AI had the longest reaction times, and user performance degraded in the presence of bad AI advice. However, uncertainty-awar","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e64902"},"PeriodicalIF":3.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12023801/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144056969","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":"Daily Automated Prediction of Delirium Risk in Hospitalized Patients: Model Development and Validation.","authors":"Kendrick Matthew Shaw, Yu-Ping Shao, Manohar Ghanta, Valdery Moura Junior, Eyal Y Kimchi, Timothy T Houle, Oluwaseun Akeju, Michael Brandon Westover","doi":"10.2196/60442","DOIUrl":"10.2196/60442","url":null,"abstract":"<p><strong>Background: </strong>Delirium is common in hospitalized patients and is correlated with increased morbidity and mortality. Despite this, delirium is underdiagnosed, and many institutions do not have sufficient resources to consistently apply effective screening and prevention.</p><p><strong>Objective: </strong>This study aims to develop a machine learning algorithm to identify patients at the highest risk of delirium in the hospital each day in an automated fashion based on data available in the electronic medical record, reducing the barrier to large-scale delirium screening.</p><p><strong>Methods: </strong>We developed and compared multiple machine learning models on a retrospective dataset of all hospitalized adult patients with recorded Confusion Assessment Method (CAM) screens at a major academic medical center from April 2, 2016, to January 16, 2019, comprising 23,006 patients. The patient's age, gender, and all available laboratory values, vital signs, prior CAM screens, and medication administrations were used as potential predictors. Four machine learning approaches were investigated: logistic regression with L1-regularization, multilayer perceptrons, random forests, and boosted trees. Model development used 80% of the patients; the remaining 20% was reserved for testing the final models. Laboratory values, vital signs, medications, gender, and age were used to predict a positive CAM screen in the next 24 hours.</p><p><strong>Results: </strong>The boosted tree model achieved the greatest predictive power, with an area under the receiver operator characteristic curve (AUROC) of 0.92 (95% CI 0.913-9.22), followed by the random forest (AUROC 0.91, 95% CI 0.909-0.918), multilayer perceptron (AUROC 0.86, 95% CI 0.850-0.861), and logistic regression (AUROC 0.85, 95% CI 0.841-0.852). These AUROCs decreased to 0.78-0.82 and 0.74-0.80 when limited to patients who currently do not or never have had delirium, respectively.</p><p><strong>Conclusions: </strong>A boosted tree machine learning model was able to identify hospitalized patients at elevated risk for delirium in the next 24 hours. This may allow for automated delirium risk screening and more precise targeting of proven and investigational interventions to prevent delirium.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":" ","pages":"e60442"},"PeriodicalIF":3.1,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12048784/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142899433","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":"Effect of Smartphone-Based Messaging on Interns and Nurses at an Academic Medical Center: Observational Study.","authors":"Sankirth Madabhushi, Andrew M Nguyen, Katie Hsia, Sucharita Kher, William Harvey, Jennifer Murzycki, Daniel Chandler, Michael Davis","doi":"10.2196/66859","DOIUrl":"https://doi.org/10.2196/66859","url":null,"abstract":"<p><strong>Background: </strong>Digital communication between nurses and medicine interns plays a crucial role in patient care. However, excessive messaging may contribute to alert fatigue, potentially affecting workflow efficiency and clinical decision-making. Although prior research has examined general messaging behaviors among clinicians, few studies have specifically analyzed messaging patterns between nurses and interns, who serve as primary points of contact in inpatient care.</p><p><strong>Objectives: </strong>This study aims to quantitatively characterize messaging patterns between the primary nurse and primary provider (ie, medicine intern) of hospitalized patients at an academic medical center in order to identify communication burdens and potential inefficiencies. By identifying trends in message volume, timing, and response rates, we seek to inform strategies to optimize communication workflows and mitigate alert fatigue.</p><p><strong>Methods: </strong>At a large academic hospital (Tufts Medical Center, Boston, MA), we analyzed secure messaging transactions between internal medicine interns and nurses across three medical-surgical units over 6 months. Transaction metadata, time stamps, and unique message tokens were extracted. Data processing was performed using Python, Microsoft Excel, and R. Message volume, interaction frequencies, and response times were analyzed using measures of central tendency and statistical tests of significance.</p><p><strong>Results: </strong>A total of 61,057 unique messages were exchanged between interns and nurses, with interns exchanging 2.5 times more messages per day with nurses than vice versa (P<.001). Messaging volume exhibited diurnal variation, indicating periods of increased communication burden. Interns read messages from nurses within a median of 35 (range: 0-3589) seconds, whereas nurses read messages from interns within a median of 26 (range: 0-3584) seconds (P<.001). The longest message response delays occurred at 4 AM, whereas the shortest occurred at 8 AM.</p><p><strong>Conclusions: </strong>Interns experience a significantly higher messaging burden than nurses, with distinct peaks in message volume during morning rounds and overnight shifts. These findings suggest a need for interventions such as optimized digital communication protocols to reduce nonessential messaging and alert fatigue. Future research should explore the effectiveness of these interventions in enhancing workflow efficiency and the development of both in-person and digital interventions to optimize communication workflows and mitigate alert fatigue.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e66859"},"PeriodicalIF":3.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021371/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144011586","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":"Ensuring General Data Protection Regulation Compliance and Security in a Clinical Data Warehouse From a University Hospital: Implementation Study.","authors":"Christine Riou, Mohamed El Azzouzi, Anne Hespel, Emeric Guillou, Gouenou Coatrieux, Marc Cuggia","doi":"10.2196/63754","DOIUrl":"https://doi.org/10.2196/63754","url":null,"abstract":"<p><strong>Background: </strong>The European Union's General Data Protection Regulation (GDPR) has profoundly influenced health data management, with significant implications for clinical data warehouses (CDWs). In 2021, France pioneered a national framework for GDPR-compliant CDW implementation, established by its data protection authority (Commission Nationale de l'Informatique et des Libertés). This framework provides detailed guidelines for health care institutions, offering a unique opportunity to assess practical GDPR implementation in health data management.</p><p><strong>Objective: </strong>This study evaluates the real-world applicability of France's CDW framework through its implementation at a major university hospital. It identifies practical challenges for its implementation by health institutions and proposes adaptations relevant to regulatory authorities in order to facilitate research in secondary use data domains.</p><p><strong>Methods: </strong>A systematic assessment was conducted in May 2023 at the University Hospital of Rennes, which manages data for over 2 million patients through the eHOP CDW system. The evaluation examined 116 criteria across 13 categories using a dual-assessment approach validated by information security and data protection officers. Compliance was rated as met, unmet, or not applicable, with criteria classified as software-related (n=25) or institution-related (n=91).</p><p><strong>Results: </strong>Software-related criteria showed 60% (n=15) compliance, with 28% (n=7) noncompliant or partially compliant and 12% (n=3) not applicable. Institution-related criteria achieved 72% (n=28) compliance for security requirements. Key challenges included managing genetic data, implementing automated archiving, and controlling data exports. The findings revealed effective privacy protection measures but also highlighted areas requiring regulatory adjustments to better support research.</p><p><strong>Conclusions: </strong>This first empirical assessment of a national CDW compliance framework offers valuable insights for health care institutions implementing GDPR requirements. While the framework establishes robust privacy protections, certain provisions may overly constrain research activities. The study identifies opportunities for framework evolution, balancing data protection with research imperatives.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"13 ","pages":"e63754"},"PeriodicalIF":3.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12020775/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144043412","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}