Journal of the American Medical Informatics Association最新文献

{"title":"Integrating human and artificial intelligence for robust postmarketing safety surveillance systems: reflections from the FDA Sentinel Innovation Center.","authors":"Rishi J Desai, Robert Ball, Gerald Dal Pan, Sebastian Schneeweiss","doi":"10.1093/jamia/ocag121","DOIUrl":"10.1093/jamia/ocag121","url":null,"abstract":"<p><strong>Objectives: </strong>To describe considerations for integration of human and artificial intelligence for creating a postmarketing surveillance system capable of timely and reliably identifying causal effects of medications on safety endpoints.</p><p><strong>Materials and methods: </strong>The FDA has prioritized more extensive Electronic Health Records (EHR) integration along with generative artificial intelligence and machine learning (Gen AI/ML) into the national active surveillance program for medical products-the Sentinel Initiative. Based on our experience of leading these efforts, we provide perspectives on the opportunities and challenges of Gen AI/ML integration into Sentinel.</p><p><strong>Results: </strong>Using specific examples, we outline the role of Gen AI and ML in a causal inference framework for scalable information extraction, assessment of fitness-for-purpose of data sources, diagnosing residual confounding, and enhancing confounding adjustment. Critically, we outline steps and checkpoints along the way where human involvement remains indispensable.</p><p><strong>Discussion and conclusion: </strong>In public health applications where stakes are high, use of Gen AI/ML needs to be carefully considered with appropriate guardrails ensuring human expert involvement.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1834-1838"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148450256","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":"Digital divide in clinical and operational artificial intelligence adoption and implementation stages: US hospital diffusion patterns and AI deserts.","authors":"Ace Vo, Youyou Tao, Rui Sundrup, Abhay N Mishra, Dezhi Wu, Leena S Nathan","doi":"10.1093/jamia/ocag086","DOIUrl":"10.1093/jamia/ocag086","url":null,"abstract":"<p><strong>Objectives: </strong>We examine how hospital characteristics relate to clinical and operational artificial intelligence (AI) adoption and implementation stages and characterize AI deserts and spatial clustering patterns to highlight place-based AI access gaps among United States (US) hospitals.</p><p><strong>Materials and methods: </strong>We used the 2024 American Hospital Association Annual Survey data from 2720 hospitals with at least one AI response. We applied logistic regression models to examine the associations between hospital characteristics and AI adoption, local indicators of spatial association to identify local clusters, and distance analyses to locate AI desert hospitals (ie, geographically isolated nonadopters located >50 miles from the nearest AI adopters).</p><p><strong>Results: </strong>We found that system membership, larger bed size, and nurse staffing intensity are positively associated with clinical and operational AI adoption and implementation stages, whereas rural location, for-profit ownership, and physician intensity are negatively associated with them. Teaching status is more strongly associated with clinical AI, while system membership is more positively associated with operational AI. Although 68.0% of hospitals adopted ≥1 clinical AI functionalities and 60.7% adopted ≥1 operational AI functionalities, 12.1% of clinical and 13.2% of operational non-adopters are classified as AI desert hospitals.</p><p><strong>Discussion: </strong>AI deserts reveal regional implementation gaps; sustained diffusion requires building shared regional capacity rather than relying only on hospital-level incentives. Policy implications to emerging divides may include tracking implementation stage, providing domain-specific support, and funding regional partnerships.</p><p><strong>Conclusion: </strong>US hospital AI diffusion is uneven and spatially structured. AI deserts mark regional gaps in access to AI-adopting hospitals.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1605-1616"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580732/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148370639","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":"Remembering Clement J. McDonald, MD: advancing healthcare interoperability standards.","authors":"Suzanne Bakken","doi":"10.1093/jamia/ocag141","DOIUrl":"10.1093/jamia/ocag141","url":null,"abstract":"","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":"33 9","pages":"1569-1570"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580718/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148984116","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":"Characterization and validation of EHR computable phenotypes for Long COVID using patient-reported symptoms: insights from the nationwide RECOVER program.","authors":"Victor M Castro, Vivian Gainer, Nich Wattanasin, Andrew Cagan, Ana Holzbach, James Chan, Leora Horwitz, Rachel Kenney, Ivan Diaz, Hannah Mandel, Shannon Wuller, Mady Hornig, Lisa O'Brien, Andrew Wylam, James Doster, Richard A Moffitt, Emily Pfaff, Mark G Weiner, Sajjad Abedian, Michael Koropsak, Sairam Parthasarathy, Hanieh Razzaghi, Justin Manjourides, Elizabeth W Karlson, Shawn N Murphy","doi":"10.1093/jamia/ocag115","DOIUrl":"10.1093/jamia/ocag115","url":null,"abstract":"<p><strong>Objective: </strong>Long COVID (LC) remains poorly understood, and there is a critical need for advanced computational tools to better identify and characterize patients. In this study, we use summarized symptom reports by RECOVER-Adult cohort participants linked to EHR data to characterize patients and train a computable phenotype algorithm of LC.</p><p><strong>Materials and methods: </strong>The study included adult participants with linked Fast Health Interoperability Resource-sourced EHR data. We characterized EHR diagnoses, procedures, medications, lab tests, and vital sign features associated with LC. A computable phenotyping algorithm was trained and validated against patient-reported symptoms.</p><p><strong>Main outcome and measures: </strong>We assessed model discrimination and calibration in a held-out test set. We describe important model features and evaluate model discrimination and calibration.</p><p><strong>Results: </strong>The study included 1501 RECOVER-Adult cohort participants with linked EHR data. 376 (25%) met criteria for highly symptomatic LC based on the RECOVER Long COVID Research Index (LCRI). EHR features associated with LC included clinician diagnosis of shortness of breath, malaise and fatigue, and cardiac dysrhythmias; documented treatment with albuterol, gabapentin, or duloxetine; or elevated heart rate. The algorithm identifying patients with highly symptomatic LC had an area under the receiver operating characteristic curve of 0.80 (95% CI 0.74-0.85), and area under the precision-recall curve of 0.58 (95% CI, 0.47-0.69).</p><p><strong>Conclusion and relevance: </strong>These findings demonstrate that, using EHR data, a machine-learning model can accurately select patients with sets of self-reported LC symptoms. The model could help identify patients within a health system with the highest probability of the condition and facilitate screening, recruitment for clinical trials, and etiologic studies.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1759-1769"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580738/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148581042","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":"Use of SNOMED CT, 2020-2025: literature review.","authors":"Eunsuk Chang, Javed Mostafa","doi":"10.1093/jamia/ocag094","DOIUrl":"10.1093/jamia/ocag094","url":null,"abstract":"<p><strong>Objective: </strong>To examine the evolving role and application of SNOMED CT (SCT) during 2020-2025, a period marked by the COVID-19 pandemic and accelerated adoption of artificial intelligence (AI) in healthcare.</p><p><strong>Materials and methods: </strong>We searched PubMed and Embase for articles published from October 2020 to June 2025. Included articles were classified into focus categories by implementation maturity (Theoretical, Predevelopment, Implementation, Evaluation/Commodity, and Non-operational) and usage categories. We compared trends with our previous review covering January 2015-September 2020.</p><p><strong>Results: </strong>Following exclusion criteria, 651 articles were included for final review. The United States (n = 188) and United Kingdom (n = 92) were the largest contributors. COVID-19 emerged as the second most-investigated domain. The 2020-2025 period witnessed a dramatic shift toward mature implementation stages: Implementation (26.4%) and Evaluation/Commodity (32.0%) categories expanded, while Theoretical and Predevelopment categories decreased. SCT was increasingly used for knowledge graph construction, machine learning model validation, and patient data retrieval from registries. The most prominent use case involved retrieving patient data from national and commercial registries (n = 186).</p><p><strong>Discussion: </strong>SCT's role evolved from a clinical terminology to a machine-interpretable biomedical knowledge base, supporting explainable AI. However, coding consistency remains challenging, and evidence demonstrating improved patient outcomes is lacking.</p><p><strong>Conclusion: </strong>SCT use has matured significantly, with widespread implementation in data repositories and emerging applications in AI. Future research must demonstrate clinical and operational benefits to ensure continued adoption.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1798-1810"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580736/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148228952","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 model biases in health care: a scoping review and call for an integrated assessment framework.","authors":"Lu He, D Phuong Do, Vishesh Girish Shet, Omar Farghaly, Priya Deshpande, Praveen Madiraju, Jiancheng Ye, Molly Beestrum","doi":"10.1093/jamia/ocag089","DOIUrl":"10.1093/jamia/ocag089","url":null,"abstract":"<p><strong>Objectives: </strong>To conduct a scoping review of bias assessment in studies applying large language models (LLMs) to health data and to synthesize their prevailing conceptualization of bias.</p><p><strong>Materials and methods: </strong>Following PRISMA guidelines, we queried PubMed and Scopus. Two annotators screened titles, abstracts, and full texts for eligibility, calibrating their assessments throughout the process. For included studies, we extracted and summarized data on LLMs (name and version, development domain, open- or closed-sourced status, and commercial or academic origin), natural language processing tasks (task formulation, gold-standard dataset, evaluation metrics, prompting or fine-tuning strategies), and biases (type, assessment, and bias summary).</p><p><strong>Results: </strong>Of the 1585 records retrieved, 76 papers met the eligibility criteria for full review. Among these, 59 reported identifying bias. Three major conceptualizations of bias emerged: behavioral output bias (nonstereotyping and stereotyping), predictive outcome bias, and representational bias. Studies generally adopted an observational approach (measuring bias using the existing dataset) or an experimental approach (altering prompts, eg, with different demographic information, and comparing outputs).</p><p><strong>Discussion and conclusion: </strong>Behavioral output bias and predictive outcome bias, both of which emphasize parity, dominate existing studies. Whether evaluated against external accuracy or internal equality benchmarks, these approaches often assume that equal performance across groups is inherently desirable. Treating all disparities as bias risks conflating poor model behavior with real-world disparities, and researchers should remain aware of potential tradeoffs between parity and accuracy objectives. We introduce an integrated framework that combines parity and accuracy benchmarks and encourages transparent, context-aware interpretation of group differences.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1822-1833"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580731/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148254146","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":"Role of electronic health record in stigma experiences, trust, and care decisions by women with history of pregnancy and substance use disorder: a qualitative study of perceptions of clinical note language.","authors":"Meghan E Davis, Mohit Sharma, Jessica S Ancker, Jyotishman Pathak, Marianne Sharko","doi":"10.1093/jamia/ocag096","DOIUrl":"10.1093/jamia/ocag096","url":null,"abstract":"<p><strong>Objectives: </strong>Stigma impacts outcomes across stigmatizing conditions, including substance use disorders (SUDs). Recent policy changes give patients rapid access to clinical notes in the electronic health record (EHR), which may include stigmatizing language. The objective of this study was to assess the perspectives of women with history of pregnancy and SUDs on typical language used in clinical notes.</p><p><strong>Materials and methods: </strong>Women with a history of pregnancy and SUD were recruited through an online crowd-sourcing platform. Respondents viewed examples of clinical language and answered survey questions about perceived stigma. An inductive approach was used to analyze open-text responses, and themes were developed.</p><p><strong>Results: </strong>Three hundred seventy survey respondents wrote a response to at least one open-text question. Thematic analysis yielded 4 major themes: (1) anticipation of future stigma facilitated by EHR documentation can affect patients' care decisions for themselves and their babies; (2) documented SUD history could have short- and long-term effects on patients' experience of stigma and discrimination, especially in labor and delivery; (3) phrases using \"denies\" and quotes within quotation marks could be perceived as stigmatizing and decrease trust in providers; (4) nonstigmatizing language and acknowledgement of recovery in notes can facilitate positive experiences for patients, but patients want more acknowledgement of recovery and positive language.</p><p><strong>Conclusion: </strong>Electronic health record documentation can modulate stigma experiences for women during and after pregnancy through stigmatizing language in clinical notes and facilitating discrimination, decreasing trust in providers and negatively impacting health outcomes. Raising providers' awareness of nonstigmatizing and positive language or implementing technology to prompt nonstigmatizing terminology could contribute to positive experiences among women with a history of pregnancy and SUD.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1748-1758"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580747/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148284703","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":"Translating machine learning predictions into meaningful risk estimates to support clinical decisions: a post hoc analysis of chronic obstructive pulmonary disease adverse outcomes using unified auto clinical scores.","authors":"Anthony Lianjie Li, Moses YiDong Lim, Weixiang Lian, Htet Lin Htun, Hwee Pin Phua, Ser Hon Puah, Geak Poh Tan, Huiying Xu, John Arputhan Abisheganaden, Wei-Yen Lim","doi":"10.1093/jamia/ocag116","DOIUrl":"10.1093/jamia/ocag116","url":null,"abstract":"<p><strong>Objective: </strong>The successful integration of Machine Learning (ML) models into clinical practice remains limited, as they often lack the standardized, quantifiable risk measures essential for clinical workflows. This study, therefore, aims to demonstrate the Unified Auto Clinical Scores (Uni-ACS) method as a means to translate ML predictions into interpretable biostatistical formats, a translation critical for clinical adoption and alignment with evidence-based practice guidelines.</p><p><strong>Materials and methods: </strong>We employed the Uni-ACS post hoc methodology to convert ML model outputs into clinical scores and odds ratios. Validation was performed on a retrospective cohort of Chronic Obstructive Pulmonary Disease patients admitted between 2016 and 2018, predicting adverse outcomes from 2019 to 2020. The performance of Uni-ACS was benchmarked against the original ML models and logistic regression.</p><p><strong>Results: </strong>The successful application of Uni-ACS enabled the conversion of complex ML model outputs into readily interpretable clinical scores and metrics, like odds ratios. Clinical scores derived from the ML models' SHAP values using Uni-ACS maintained a strong, interpretable predictive performance (AUROC 0.69-0.80), which was comparable to the original ML models (AUROC 0.71-0.83) and logistic regression (AUROC 0.72-0.81).</p><p><strong>Discussion: </strong>Uni-ACS addresses the fundamental clinical requirement for standardized, meaningful risk stratification. It efficiently translates complex ML predictions into validated clinical scores with minimal computational burden.</p><p><strong>Conclusion: </strong>In conclusion, this approach facilitates the widespread adoption of ML-driven risk assessment across diverse healthcare settings while ensuring compatibility with existing clinical guidelines and regulatory frameworks.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1582-1592"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580737/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148450259","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":"Medical code embeddings from claims-based co-occurrences: a unified semantic space for ICD-10 diagnoses and ATC medications.","authors":"Corentin Faujour, Stéphane Bouée, Corinne Emery, Anne-Sophie Jannot","doi":"10.1093/jamia/ocag113","DOIUrl":"10.1093/jamia/ocag113","url":null,"abstract":"<p><strong>Objective: </strong>The analysis of care trajectories derived from electronic health records and claims data has become increasingly common in biomedical informatics. This has enabled large-scale studies of care processes, yet widely used binary code representations result in high-dimensional, sparse data that fail to capture semantic relationships between medical concepts. Learning dense vector representations (embeddings) has emerged as a promising approach to address these limitations. We aimed to construct and share joint embeddings for the International Classification of Diseases (ICD-10) and the Anatomical Therapeutic Chemical (ATC) classification system, providing reusable semantic representations of diagnoses and treatments from real-world claims data.</p><p><strong>Materials and methods: </strong>Using claims records from 1.5 million patients, we defined code co-occurrences within temporal windows and constructed a Positive Pointwise Mutual Information (PPMI) matrix spanning ICD-10 and ATC codes. Singular Value Decomposition (SVD) was applied to derive a low-dimensional embedding space. Evaluation combined UMAP visualization, nearest-neighbor retrieval, and a code-level classification task based on ICD chapters and ATC classes.</p><p><strong>Results: </strong>The embeddings reflected the hierarchical organization of ICD-10 and ATC and revealed associations across coding systems, including clinically relevant diagnosis-treatment relationships. The classification task achieved mean AUCs of 0.93 for ICD-10 and 0.90 for ATC, indicating strong grouping of semantically related codes.</p><p><strong>Discussion: </strong>The embeddings provide a reusable, code-level semantic representation that can support code retrieval, reduce manual code grouping, and be aggregated into patient-level features without training a task-specific model.</p><p><strong>Conclusion: </strong>We release the first openly available joint ICD-10-ATC embedding space derived from real-world claims data, providing a reusable resource for biomedical informatics research.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1571-1581"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580744/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148450264","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":"Augmenting clinical decision-making with large language models: evaluation across general and specialty tasks.","authors":"Yuechen Tao, Xiushi Lin, He Sun, Wenrui Bao, Xiaobo Zhu, Shiwei Wu, Yixiao Liu, Ziang Li, Jialong Wu, Zhenkun Zhao, Lei Qiu, Qianyang Ni, Song Zhang, Zhenchao Tang, Zuobin Ying, Yu An, Jie Tian, Zhenyu Liu, Jian Lu","doi":"10.1093/jamia/ocag053","DOIUrl":"10.1093/jamia/ocag053","url":null,"abstract":"<p><strong>Objective: </strong>Large language models (LLMs) have shown promise in clinical applications, yet prior studies mainly evaluated their standalone performance on benchmarks or examinations. This study assesses how LLMs support clinicians across specialties, disease contexts, experience levels and decision-making stages.</p><p><strong>Methods: </strong>We evaluated 3 LLMs (Deepseek-R1, GPT-4o-mini and LLaMA-4) using 2 task types: (1) general-disease tasks spanning specialties and disease incidence levels, and (2) prostate disease scenario covering the clinical workflow, including diagnosis, treatment planning, postoperative rehabilitation and prognosis. Clinicians with different seniority completed tasks independently and repeated them after reviewing LLM-generated responses. Performance was rated by experts using a 5-point Likert scale, and differences were analyzed with the Wilcoxon signed-rank test.</p><p><strong>Results: </strong>LLM assistance significantly improved clinician performance across general disease tasks (P < .05). In the specialty scenario, junior clinicians' scores increased by 0.579-0.723 (15.9%-20.8%) across 4 clinical stages, whereas senior clinicians' improvements ranged from 0.053-0.303 (1.3%-7.5%). With LLM support, junior clinicians surpassed senior clinicians' unaided performance in postoperative rehabilitation and prognosis stages (P < .05) and achieved comparable performance in diagnosis and treatment stages (P > .05). Performance varied among models, with Deepseek-R1 performing best in diagnostic tasks.</p><p><strong>Discussion: </strong>These findings suggest that LLM assistance may provide greater benefit to less-experienced clinicians and are particularly effective in downstream decision-making stages, indicating a potential role in mitigating experience-related performance disparities.</p><p><strong>Conclusions: </strong>LLMs may serve as supportive clinical-decision support tools across diseases, specialties, clinician experience levels, and workflow stages, with observed improvements in decision quality and reduced performance disparities.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":"1660-1670"},"PeriodicalIF":7.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13580730/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148254144","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}