Journal of the American Medical Informatics Association最新文献

{"title":"A comparison of Fast Healthcare Interoperability Resources and Observational Medical Mutcomes Partnership electronic health record data within the All of Us Research Program.","authors":"Jason Patterson, Elise Minto, Maura Beaton, Adit Anand, Mark Velez, Paul Harris, George Hripcsak, Karthik Natarajan","doi":"10.1093/jamia/ocag095","DOIUrl":"10.1093/jamia/ocag095","url":null,"abstract":"<p><strong>Objective: </strong>This study compares the contents of two data standards; the Observational Medical Outcomes Partnership (OMOP) and Fast Healthcare Interoperability Resources (FHIR), highlighting their strength and weaknesses and serve as an initial step toward understanding how each standard supports secondary data analysis.</p><p><strong>Materials and methods: </strong>Participant electronic health record data in both OMOP and FHIR formats from the All of Us Research Program (AoURP) were compared, including codeable event volume, healthcare encounters, and person timelines. A phenotype-based assessment was also conducted using Type-II Diabetes Mellitus (T2DM).</p><p><strong>Results: </strong>Among 29 512 participants identified with overlapping FHIR and OMOP data, Median codeable event counts were comparable between FHIR and OMOP within the Measurement (OMOP = 846; FHIR = 832), Drug (OMOP = 92; FHIR = 90), and Observation (OMOP = 65; FHIR = 100) domains, but were higher in OMOP within the Condition (OMOP = 258; FHIR = 11) and Procedure (OMOP = 72; FHIR = 4) domains. Within the T2DM cohort, OMOP contained more data, except for medications. Very few participants had encounters in FHIR (1.5%) relative to OMOP (97.0%). On average, only 15.9% of visit dates overlapped in both standards, with most visit dates occurring only in OMOP (65.3%) or only FHIR (18.4%).</p><p><strong>Discussion: </strong>Data in OMOP showed a higher volume of observation and procedure codeable events, reported encounters, and T2DM symptoms, complications, and comorbidities. FHIR data was able to capture data across multiple providers and health systems.</p><p><strong>Conclusion: </strong>Based on AoURP data, both standards were shown to support healthcare data capture, although OMOP shows greater utility for research purposes as its extract, transform, and load process enables more flexible data capture relative to extracting data from FHIR payloads. FHIR, however, captures patient-level data from beyond the health system and can thus be used to supplement OMOP.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1593-1604"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580739/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148303844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"OMOP common data model transformation: leveraging a nationwide community-based health care database to support AI/ML research.","authors":"Taona P Haderlein, Claudia Der-Martirosian, Wyatt P Bensken, Robert Schuff","doi":"10.1093/jamia/ocag087","DOIUrl":"10.1093/jamia/ocag087","url":null,"abstract":"<p><strong>Objective: </strong>To demonstrate a large-scale EHR data transformation to the Observational Medical Outcomes Partnership (OMOP) Common Data model in the OCHIN network to support AI/ML analyses within the AIM-AHEAD national research consortium. We highlight customized workflows and infrastructure development processes designed to support OCHIN database use by AI/ML researchers of varied academic backgrounds and skillsets.</p><p><strong>Materials and methods: </strong>Automated and manual mappings were used to ingest and transform OCHIN's i2b2-formatted database to the OMOP Common Data Model.</p><p><strong>Results: </strong>360 million encounters across 10+ million OCHIN patients were mapped over the course of a single calendar year, with custom concepts created to represent social drivers of health.</p><p><strong>Discussion: </strong>The successful transformation of the OCHIN Research Data Warehouse benefitted from incorporating both customized and legacy data workflows.</p><p><strong>Conclusion: </strong>OCHIN's efforts will facilitate parallel analyses across AIM-AHEAD datasets and support AI/ML model representativeness of affected populations.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1785-1789"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580724/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148279684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Charting the future of ACMI: a report from the 2025 ACMI symposium.","authors":"Randi Foraker, Adela Grando, Gregory L Alexander, Kenrick Cato, Hadi Kharrazi, Peter Embi, Michael E Matheny, Philip R O Payne","doi":"10.1093/jamia/ocag107","DOIUrl":"10.1093/jamia/ocag107","url":null,"abstract":"<p><p>The 2025 American College of Medical Informatics (ACMI) Symposium, themed Charting the Future of ACMI, provided a forum for fellows to reflect on the 2020-2025 ACMI Strategic Plan and define future priorities. Discussions centered on: (1) mobilizing ACMI's expertise to guide the responsible use of artificial intelligence (AI) in medical informatics, (2) advancing informatics education and mentorship across career stages, and (3) strengthening local, national, and global interdisciplinary partnerships. Proposed actions include establishing an AI Task Force, developing an online Education Resource Library, expanding structured mentorship, and cultivating strategic partnerships with relevant informatics, engineering, and clinical organizations. Fellows also identified cross-cutting challenges, including financial pressures, competition with alternative convening spaces, and the need to engage emerging leaders. By addressing these challenges while advancing its strategic imperatives, ACMI aims to serve as a trusted compass for the informatics community.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1843-1846"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148320396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthesized annotation guidelines are knowledge-lite boosters for clinical information extraction.","authors":"Enshuo Hsu, Martin Ugbala, Krishna Kumar Kookal, Kawtar Zouaidi, Nicholas L Rider, Muhammad F Walji, Kirk Roberts","doi":"10.1093/jamia/ocag084","DOIUrl":"10.1093/jamia/ocag084","url":null,"abstract":"<p><strong>Objective: </strong>Generative information extraction using large language models (LLMs), particularly through prompting combined with few-shot learning, has become a popular method. In many ways such prompts with examples resemble the annotation guidelines long used for manual labeling of data for information extraction, and indeed studies have demonstrated the direct use of these guidelines as effective prompts. However, constructing annotation guidelines is both labor- and knowledge-intensive. Instead, this paper proposes to leverage LLMs' impressive ability to automatically create such annotation guidelines.</p><p><strong>Materials and methods: </strong>Specifically, we propose a zero-shot hierarchical prompt engineering method that harvests the knowledge summarization and text generation capacity of LLMs to synthesize annotation guidelines to improve downstream LLMs while requiring minimal human input.</p><p><strong>Results: </strong>Zero-shot clinical named entity recognition benchmarks, 2012 i2b2 EVENT, 2012 i2b2 TIMEX, 2014 i2b2, and 2018 n2c2 showed improvements of 0.2% to 25.86% for Llama 3.1 and 5.82% to 16.13% for GPT-OSS in strict F1 scores from the no-guideline baseline. The LLM-synthesized guidelines showed equivalent or better performance compared to human-written guidelines by 0.23% to 10.00% in most tasks.</p><p><strong>Discussion: </strong>LLMs generate high-quality annotation guidelines following a consistent pattern (eg, title, entity types, examples) without human guidance, indicating that a representation of such a concept has been encoded during the pre-training. Nuances in definitions, however, still require adjustment by researchers to align with the project.</p><p><strong>Conclusion: </strong>This study proposes a novel hierarchical prompt engineering method that requires minimal knowledge transfer from a human expert and is applicable to multiple biomedical domains.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1735-1747"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148279636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models for full-text methods assessment: a case study on mediation analysis.","authors":"Wenqing Zhang, Trang Nguyen, Elizabeth A Stuart, Yiqun T Chen","doi":"10.1093/jamia/ocag108","DOIUrl":"10.1093/jamia/ocag108","url":null,"abstract":"<p><strong>Objective: </strong>Systematic reviews remain labor-intensive, particularly when extracting methodological details from full texts. Using mediation analysis as a case study, we evaluated whether large language models (LLMs) can match human-expert-level full-text methodological review on key causal assumptions (eg, no unmeasured confounding, temporal ordering) and best practices (eg, sensitivity analyses, interaction assessments, covariate adjustment) for psychiatry and psychology studies.</p><p><strong>Materials and methods: </strong>We evaluated 6 LLMs from 3 major families (ChatGPT-4o-mini/4o/o3/5, Claude Sonnet 4, Gemini 2.5 Flash) on 180 full-text mediation analysis articles from 2013 to 2018 previously reviewed by expert methodologists. LLMs assessed 14 binary methodological criteria ranging from straightforward checks (eg, whether the exposure was randomized) to nuanced assessments (eg, whether the temporal ordering between mediator and outcome was established). Performance was benchmarked against expert consensus labels and individual reviewers using accuracy, precision, recall, F1, AUC, and PR-AUC.</p><p><strong>Results: </strong>LLM performance strongly correlated with human reviewers across methodological criteria (accuracy correlation 0.71; F1 correlation 0.95), indicating tasks difficult for humans were likewise challenging for models. Advanced LLMs achieved near-human accuracy on explicit methodological features but lagged behind top reviewers by up to 15% on inference-intensive tasks. Longer documents reduced model accuracy. Common model errors include overinterpreting on linguistic cues and colloquial use of technical terms.</p><p><strong>Discussion and conclusion: </strong>Our findings support a criterion-specific human-AI collaboration strategy for full-text methodological assessment and provide a reproducible framework for future testing in other evidence-synthesis settings.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1702-1712"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580725/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148273645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The GUIDE-CDSS framework: a comprehensive framework to GUIDE and evaluate the implementation of Clinical Decision Support Systems in healthcare, based on an overview of reviews.","authors":"Esther R C Janssen, Jesper Knoop, Gianmatteo Farabolini, Nicoló Baldini, Thomas Hoogeboom, Maria Gabriella Ceravolo, Stefano Negrini, Carlotte Kiekens","doi":"10.1093/jamia/ocag080","DOIUrl":"10.1093/jamia/ocag080","url":null,"abstract":"<p><strong>Objectives: </strong>Despite the significant potential for Clinical Decision Support Systems (CDSSs) to improve care processes and health outcomes, several barriers hinder their widespread implementation in healthcare. While numerous systematic reviews have summarized potential barriers and facilitators for CDSS implementation, a comprehensive framework to guide and evaluate the implementation of CDSSs in healthcare is lacking. This overview of reviews, aims to establish a framework-GUIDE-CDSS-aimed at guiding and evaluating implementation of CDSSs in healthcare.</p><p><strong>Materials and methods: </strong>An overview of systematic and scoping reviews was conducted by searching 6 databases. Systematic reviews or scoping reviews that used qualitative research methods to described implementation determinants for CDSSs in the healthcare domain were included. The AMSTAR 2 tool was used to assess the methodological quality. Results were collated into the GUIDE-CDSS framework. This framework describes implementation determinants and elements within those determinants found to impact implementation of CDSSs in healthcare.</p><p><strong>Results: </strong>Twenty-three reviews were included in the analysis. All reviews had at least 2 critical weaknesses, showing a limited methodological quality of included reviews. Eight determinants and 38 elements for implementation of CDSSs in healthcare and were described in the GUIDE-CDSS framework: perceived relevance, perceived effect, trustworthiness, ease of use, workflow, training and skills, resources, and implementation strategy.</p><p><strong>Discussion and conclusion: </strong>This overview provides a comprehensive synthesis of the determinants influencing the implementation of CDSSs in healthcare, collated in the GUIDE-CDSS framework. The findings underscore that for successful CDSS development, implementation and evaluation is multifactorial.</p><p><strong>Protocol registration: </strong>This study was registered in PROSPERO (No. CRD42024512455).</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1811-1821"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580735/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148228936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Malfunctions in distributed clinical decision support: 3 cases from a multi‑component clinical decision support system.","authors":"Jeritt G Thayer, Gerald P Shaeffer, Alexander G Fiks, Brian P Jenssen, Janani Ramachandran, Dean Karavite, Emara Nabi-Burza, Jonathan P Winickoff, Robert W Grundmeier","doi":"10.1093/jamia/ocag114","DOIUrl":"10.1093/jamia/ocag114","url":null,"abstract":"<p><strong>Introduction: </strong>Clinical decision support (CDS) is increasingly delivered through distributed architectures that connect electronic health record (EHR) workflows to external services and community partners. While these designs enable rapid deployment and interoperability, they also introduce new failure modes that can silently disrupt time‑sensitive care processes. Practical, real‑world descriptions of these distributed CDS malfunctions remain limited.</p><p><strong>Case report: </strong>We describe 3 malfunctions in a distributed CDS system used to support smoking cessation referrals. The issues reflected common distributed‑system failure modes, including clock drift, timing‑related data availability problems, and asynchronous processing across partner systems.</p><p><strong>Conclusion and recommendations: </strong>Given the implications software architecture can have on distributed systems, it is critical to expand the definition of what constitutes the CDS system to include components outside the EHR, including those of third-party partners system. Further, monitoring techniques for distributed systems may also require multiple methods to account for differences in how each component can fail.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1790-1797"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580745/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148334073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Let large language models judge each other: multi-agent peer-reviewed reasoning for medical question answering.","authors":"Zaifu Zhan, Shuang Zhou, Rui Zhang","doi":"10.1093/jamia/ocag042","DOIUrl":"10.1093/jamia/ocag042","url":null,"abstract":"<p><strong>Objective: </strong>To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA).</p><p><strong>Materials and methods: </strong>We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought (CoT) reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with 5 state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, and GPT-oss-20B) on 3 benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model CoT reasoning and CoT-based majority voting.</p><p><strong>Results: </strong>Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains.</p><p><strong>Conclusion: </strong>The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1649-1659"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580728/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148254212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PDA (Privacy-Preserving Distributed Algorithms) in action: ten principles for high-quality multi-site clinical evidence generation.","authors":"Yong Chen, Jiayi Tong, Yiwen Lu, Rui Duan, Chongliang Luo, Marc A Suchard, Patrick B Ryan, Andrew E Williams, John H Holmes, Jason H Moore, Hua Xu, Yun Lu, Raymond J Carroll, Scott L Zeger, George Hripcsak, Martijn J Schuemie","doi":"10.1093/jamia/ocag119","DOIUrl":"10.1093/jamia/ocag119","url":null,"abstract":"<p><strong>Background: </strong>Distributed Research Networks (DRNs) offer significant opportunities for collaborative multi-site research and have significantly advanced healthcare research based on clinical observational data. However, generating high-quality real-world evidence using fit-for-use data from multi-site studies faces important challenges, including biases associated with various types of heterogeneity within and across sites and data sharing difficulties. Over the last 10 years, Privacy-Preserving Distributed Algorithms (PDA) have been developed and utilized in numerous national and international real-world studies spanning diverse domains, from comparative effectiveness research, target trial emulation, to healthcare delivery, policy evaluation, and system performance assessment. Despite these advances, there remains a lack of comprehensive and clear guiding principles for generating high-quality real-world evidence through collaborative studies leveraging the methods under PDA.</p><p><strong>Objective: </strong>The paper aims to establish 10 principles of best practice for conducting high-quality multi-site studies using PDA. These principles cover all phases of research, including study preparation, protocol development, analysis, and final reporting.</p><p><strong>Discussion: </strong>The 10 principles for conducting a PDA study outline a principled, efficient, and transparent framework for employing distributed learning algorithms within DRNs to generate reliable and reproducible real-world evidence.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1636-1648"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580733/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148431510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GAT-BiGRU: explainable multi-task temporal graph learning for glucose forecasting, hypoglycemia risk, and counterfactual insulin adjustment.","authors":"Muhammad Abdullah Sarwar, Sarmad Maqsood, Egle Belousovienė, Rytis Maskeliūnas","doi":"10.1093/jamia/ocag104","DOIUrl":"10.1093/jamia/ocag104","url":null,"abstract":"<p><strong>Background: </strong>People with type 1 diabetes mellitus (T1DM) show glucose variability driven by insulin dosing, meals, activity, and circadian rhythms. Many deep learning approaches treat glucose forecasting and hypoglycemia detection as separate tasks and provide limited transparency.</p><p><strong>Objective: </strong>We developed an explainable, multi-task temporal graph framework that jointly predicts glucose trajectories and hypoglycemia risk at 30 and 60 minute horizons, and provides bounded, patient-specific insulin adjustment recommendations.</p><p><strong>Methods: </strong>Temporal GAT-BiGRU transforms multimodal continuous glucose monitoring (CGM) time series into a temporal k-neighborhood graph, with each time point represented as a feature-enriched node. A graph-attention encoder performs multi-head message passing over history edges, while an attention-based BiGRU captures longer dependencies. We evaluated OhioT1DM and BrisT1D using hypoglycemia and predicted Time in Range (TIR) metrics. A prediction-driven counterfactual module retrospectively generates bounded basal/bolus adjustments using patient-specific Insulin-to-Carbohydrate Ratio (ICR) and Insulin Sensitivity Factor (ISF); interpretability is supported via GNNExplainer.</p><p><strong>Results: </strong>On OhioT1DM, Temporal GAT-BiGRU achieved hypoglycemia precision-recall area under the curve (PR-AUC) 0.93, mean absolute error (MAE) 9.40 mg/dL, root mean square error (RMSE) 15.8 mg/dL, mean absolute relative difference (MARD) 6.01%, and predicted TIR 71.39%. On BrisT1D, performance remained strong with PR-AUC 0.98, MAE 9.36 mg/dL, RMSE 15.3 mg/dL, MARD 7.55%, and predicted TIR 64.78%. The insulin module generated bounded, subject-specific recommendations, typically suggesting ∼10% basal increases with individualized meal-bolus updates.</p><p><strong>Conclusions: </strong>Temporal GAT-BiGRU provides accurate glucose prediction through temporal graph reasoning, sequence modeling, and interpretable explanations. It supports personalized decision support and closed-loop glucose management systems.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1713-1725"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580734/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148279718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}