JAMIA Open最新文献

{"title":"Correction to: Use and characteristics of free/libre and open source electronic health records: an overview of reviews.","authors":"","doi":"10.1093/jamiaopen/ooag174","DOIUrl":"https://doi.org/10.1093/jamiaopen/ooag174","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.1093/jamiaopen/ooag100.].</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag174"},"PeriodicalIF":4.7,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13528623/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148866650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Attitudes, perceptions, and UTAUT-based factors influencing the acceptance of medical artificial intelligence among Chinese oncology healthcare professionals: a national cross-sectional survey.","authors":"Zhaoyu Wang, Qianqian Dai, Maoshu Yang, Shiwu Shi, Jiaojiao Liao, Zhaoji Li, Xiaoqiu Dai, Liyuan Tao","doi":"10.1093/jamiaopen/ooag154","DOIUrl":"10.1093/jamiaopen/ooag154","url":null,"abstract":"<p><strong>Objectives: </strong>To conduct a nationwide survey among professionals working in oncology departments in China to investigate their attitudes, perceptions, and experiences regarding medical artificial intelligence (AI), and to explore and compare the factors influencing AI behavioral intention (BI; willingness to adopt AI) between physicians and nurses using the Unified Theory of Acceptance and Use of Technology (UTAUT).</p><p><strong>Materials and methods: </strong>A nationwide cross-sectional survey was conducted among professionals in oncology departments across China. Sociodemographic characteristics, awareness, perceptions, and user experiences related to medical AI were collected. The UTAUT was specifically applied to the third section of the survey to evaluate participants' perceptions. Based on this framework, structural equation modeling (SEM) was performed to examine associations between BI and 6 latent constructs: performance expectancy (PE), effort expectancy (EE), social influence (SI), facilitating conditions (FC), perceived risk (PR), and trust (TR) based on the UTAUT. Subgroup SEM analyses were then conducted for physicians and nurses.</p><p><strong>Results: </strong>Six hundred ten valid responses were included in the final analysis, consisting of 188 (30.8%) physicians and 422 (69.2%) nurses. Only 17.7% reported having both heard of and used medical AI, while 67.7% had heard of it but never used it. SEM results showed that TR (confidence in system reliability; β = .668, <i>P</i> < .001) had the strongest effect on BI, followed by effort EE (perceived ease of use; β = .155, <i>P</i> = .026). Subgroup analyses revealed that for physicians, both EE (β = .257, <i>P</i> = .038) and TR (β = .486, <i>P</i> < .001) significantly influenced BI, while among nurses, only TR (β = .729, <i>P</i> < .001) showed a significant effect.</p><p><strong>Conclusions: </strong>There is a significant \"awareness-usage gap\" among Chinese oncology professionals, with high awareness but low practical integration of medical AI. This nationwide study indicates that TR and EE are associated with the intention to use AI. To bridge this gap, hospital management should implement differentiated training and local validation protocols that address the unique technical and ethical concerns of physicians and nurses, respectively.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag154"},"PeriodicalIF":4.7,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13505628/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148819677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptation of a fair individualized polysocial risk score for hospitalization risk prediction.","authors":"Qinglin Gou, Yu Hu, Xing He, Megan E Gregory, Jennifer H LeLaurin, Ramzi G Salloum, Jiang Bian, Jingchuan Guo, Yu Huang","doi":"10.1093/jamiaopen/ooag161","DOIUrl":"10.1093/jamiaopen/ooag161","url":null,"abstract":"<p><strong>Objectives: </strong>We adapted the individualized polysocial risk score (iPsRS), a machine learning model originally developed for patients with type 2 diabetes, to evaluate its generalizability in predicting 1-year hospitalization risk in a disease-agnostic adult cohort, with attention to fairness and explainability.</p><p><strong>Materials and methods: </strong>The study utilized de-identified electronic health record data from a retrospective cohort of 17 857 adult patients at the University of Florida Health. The original iPsRS framework was reimplemented using XGBoost and Logistic Regression models. These models were trained and fine-tuned using 13 individual-level social determinants of health (SDoH) predictors to predict all-cause hospitalization within 1 year. Models were fine-tuned at 5 levels (0%, 10%, 20%, 50%, and 70%) with 3 sampling strategies (none, oversampling, and undersampling). Model performance was primarily evaluated using the AUROC. Interpretability was assessed through SHapley Additive exPlanations and a causal structure learning algorithm, while fairness was analyzed by examining false negative rate disparities across age, sex, and racial/ethnic subgroups.</p><p><strong>Results: </strong>After fine-tuning, the adapted iPsRS demonstrated moderate predictive performance, achieving an AUROC of up to 0.671 with XGBoost and Normal sampling. SHapley Additive exPlanations analysis on the evaluation split showed age, food insecurity, marital status, and financial constraints emerged as consistently influential predictors. The causal structure analysis corroborated predictive findings, identifying age, race, and employment as proximal factors associated with hospitalization.</p><p><strong>Conclusion: </strong>The iPsRS was successfully adapted beyond diabetes, maintaining moderate predictive performance and meaningful risk stratification. Incorporating individual-level SDoH enables equity-aware prediction, supporting broader use of iPsRS in clinical care.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag161"},"PeriodicalIF":4.7,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13503007/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and evaluation of a multi-source machine learning model to predict critical illness and death in patients with substance misuse.","authors":"Preeti Gupta, Tim Gruenloh, Madeline Oguss, Askar Safipour Afshar, Michael Spigner, Megan Gussick, Matthew Churpek, Todd Lee, Majid Afshar, Anoop Mayampurath","doi":"10.1093/jamiaopen/ooag168","DOIUrl":"https://doi.org/10.1093/jamiaopen/ooag168","url":null,"abstract":"<p><strong>Objectives: </strong>Patients with substance misuse are at high risk for clinical deterioration, and pre-hospital encounters constitute important risk factors. We sought to incorporate these risk factors into a novel prediction model using linked electronic health record, emergency medical services (EMSs), and claims data.</p><p><strong>Materials and methods: </strong>Using 23 454 hospital encounters, we developed machine-learning models to predict mechanical ventilation, vasopressor initiation, or death within 12 hours of a vital sign or laboratory measurement. Models were compared to the modified early warning score.</p><p><strong>Results: </strong>Extreme gradient boosting achieved an area under the receiver operating characteristic curve of 0.93, significantly outperforming modified early warning score (MEWS 0.79). Notably, removing EMS and claims data did not reduce predictive performance.</p><p><strong>Discussion: </strong>The model demonstrated strong predictive performance of clinical deterioration in this high-risk population. Incorporation of pre-hospital risk factors did not improve performance beyond EHR data alone.</p><p><strong>Conclusion: </strong>Electronic health record-based machine learning models can support accurate short-term prediction of clinical deterioration among this population at risk for delayed recognition.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag168"},"PeriodicalIF":4.7,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13480433/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using natural language processing and machine learning to identify social needs in patient medical notes: model training with balanced versus real-world datasets.","authors":"Christopher Kitchen, Thomas Richards, Luis M Ahumada, Geoffrey M Gray, Ayah Zirikly, Elham Hatef","doi":"10.1093/jamiaopen/ooag170","DOIUrl":"https://doi.org/10.1093/jamiaopen/ooag170","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate natural language processing (NLP) and machine learning (ML) approaches for identifying social needs in electronic health record (EHR) notes, using balanced versus real-world imbalanced datasets.</p><p><strong>Materials and methods: </strong>A rule-based NLP framework using definite, non-negated keywords flagged social needs domains and \"Any Social Need\" in unstructured notes. Logistic regression, random forest, and XGBoost models were trained under balanced and imbalanced prevalence and evaluated using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), F1, precision, recall, and specificity, with threshold sensitivity analyses.</p><p><strong>Results: </strong>On the imbalanced test set for any social need, the rule-based model achieved F1 0.373 (precision 0.484; recall 0.303; and specificity 0.978). On the balanced test set for any social need, XGBoost and logistic models achieved AUPRC 0.719 and 0.718, F1 0.438, and precision 0.944; random forest had AUPRC 0.714, F1 0.423, and precision 0.945. Under imbalanced evaluation, XGBoost led (AUPRC 0.319, F1 0.312, precision 0.839, recall 0.191, and specificity 0.998), followed by logistic (AUPRC 0.312 and F1 0.289) and random forest (AUPRC 0.305 and F1 0.282).</p><p><strong>Discussion: </strong>Balanced training inflated apparent performance, while under realistic class imbalance the ML models traded recall for very high precision, with XGBoost performing best but still lagging in sensitivity.</p><p><strong>Conclusion: </strong>These findings underscore the need to train and tune under real-world prevalence and to set thresholds based on use-case priorities (eg, maximizing precision for referrals versus improving recall for screening).</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag170"},"PeriodicalIF":4.7,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13480434/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Algorithmic fairness in machine-learning models for determining the progression or recurrence of cardiovascular disease in racialized populations: a scoping review.","authors":"Imeth Illamperuma, Bhavya Gandhi, Ronin Offman, Morgan Rosenberg","doi":"10.1093/jamiaopen/ooag138","DOIUrl":"https://doi.org/10.1093/jamiaopen/ooag138","url":null,"abstract":"<p><strong>Objective: </strong>To examine how algorithmic fairness is measured, operationalized, and reported in machine learning (ML) models designed to predict or support secondary prevention of cardiovascular disease (CVD) outcomes including progression, recurrence, readmission, and post-index mortality in racialized populations.</p><p><strong>Materials and methods: </strong>This scoping review was conducted in accordance with PRISMA-ScR guidelines and registered with the Open Science Framework (OSF registration: https://doi.org/10.17605/OSF.IO/9W67V). Systematic searches of OVID MEDLINE, EMBASE, Scopus, and CENTRAL were performed to identify studies evaluating fairness in ML models applied to secondary cardiovascular outcomes.</p><p><strong>Results: </strong>Of 2669 records screened, three retrospective cohort studies met inclusion criteria. All studies used large-scale electronic health record data from the United States and evaluated model performance across racial subgroups. Only one study implemented fairness-aware model development, reporting improvements of approximately 5%-12% in equity-related metrics, accompanied by modest trade-offs in calibration and sensitivity. The remaining studies assessed fairness post hoc and demonstrated limited ability to mitigate subgroup performance differences.</p><p><strong>Discussion: </strong>Most full-text studies excluded during screening addressed fairness in predicting primary CVD incidence rather than secondary outcomes, highlighting a substantial gap in the literature. Across included studies, observed fairness limitations appeared to be driven largely by upstream structural and data-generating factors such as representation, care patterns, and documentation rather than algorithmic design alone.</p><p><strong>Conclusion: </strong>Evidence on algorithmic fairness in ML models for secondary cardiovascular outcomes remains sparse. Improved reporting of subgroup performance, missingness, and calibration, alongside integration of fairness throughout model development, is necessary before equitable clinical deployment.</p><p><strong>Study registration: </strong>Open Science Framework: https://doi.org/10.17605/OSF.IO/9W67V.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag138"},"PeriodicalIF":4.7,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13472678/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148762597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Confronting complexity: toward equitable healthcare technology design and evaluation for socioeconomically marginalized patients.","authors":"Tiffany C Veinot, Alicia K Stone, Sage Davis, Rupa S Valdez, Lorraine R Buis, Vaishnav Kameswaran, Marcy G Antonio, Graciela Lagraba, Tawanna R Dillahunt","doi":"10.1093/jamiaopen/ooag076","DOIUrl":"https://doi.org/10.1093/jamiaopen/ooag076","url":null,"abstract":"<p><strong>Objectives: </strong>Investigate how patients at a Federally-Qualified Health Center (FQHC) perform with, and perceive, complex telehealth tasks. Determine which complexity dimensions most affect patients' performance and perceptions, and compare this to researcher-evaluators' complexity walkthrough results.</p><p><strong>Materials and methods: </strong>A novel complexity walkthrough inspection method was implemented by researcher-evaluators (<i>n</i> = 8) to identify theory-informed complexity dimensions in 6 FQHC-required telehealth tasks. Remote user testing (<i>n</i> = 24) where FQHC patients were observed performing tasks, then completed newly-developed complexity-focused interviews and surveys. Descriptive statistics regarding complexity dimension presence, task performance, cognitive load, and perceived difficulty were integrated with qualitative data analyzed using inductive and deductive coding.</p><p><strong>Results: </strong>Patients completed 33.9% of the required subtasks without issues. Cognitive load and perceived difficulty were high for 2 tasks. Complexity dimensions of <i>ambiguity</i> (<i>unclear inputs/processes</i>; <i>new concepts/words</i>) and <i>relationship</i> (<i>context switching</i>; <i>deep navigational hierarchies</i>) most affected patient-perceived difficulty. Patients spent twice as long as walkthrough evaluators on tasks, and encountered broader complexity dimensions: <i>new concepts/words</i>, and <i>errors</i>. Many patients ended tasks early, asserting that they would abandon them outside of a study or had previously done so.</p><p><strong>Discussion: </strong>Technology-mediated task complexity may explain some telehealth uptake inequities. The complexity dimensions that challenge patients extend known usability heuristics by enhancing their equity sensitivity. Complexity walkthroughs surface design patterns that challenge patients, but complexity-focused user testing with patients reveals additional difficulties. Findings support <i>complexity reduction</i> of tasks via structuring, familiar concepts/words, feature integration, and shallow/broad navigation.</p><p><strong>Conclusion: </strong>This paper's novel, theoretically-grounded complexity-focused methods and findings may inform future equitable design and evaluation of technology-mediated tasks for socioeconomically marginalized patients.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag076"},"PeriodicalIF":4.7,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13470433/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148761689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond fax: provider perspectives on data sharing in substance use disorder care.","authors":"Martha Kaiser, Mengyi Wei, Sai Prathyusha Nookala, Reid Cooper, Deborah Ariosto, Cameron Adams, Adela Grando, Malihe Sadeghi, Anita C Murcko","doi":"10.1093/jamiaopen/ooag162","DOIUrl":"10.1093/jamiaopen/ooag162","url":null,"abstract":"<p><strong>Objectives: </strong>Substance use disorder (SUD) care continues to be hindered by persistent gaps in health information exchange (HIE). This study examined people, organizational, regulatory, and technical barriers to SUD data sharing from the provider perspective and identified key opportunities to improve care through health record interoperability.</p><p><strong>Materials and methods: </strong>Behavioral health providers (52% prescribers) representing 4 SUD treatment organizations in 14 US states participated in 11 focus groups (<i>n</i> = 31) and 5 validation interviews (<i>n</i> = 5) covering scenarios related to SUD Healthcare Effectiveness Data and Information Set (HEDIS) metrics. Thematic analysis, keyword searches, and workflow analysis [using Unified Modeling Language (UML) diagrams] were performed.</p><p><strong>Results: </strong>Incomplete data access at the point of care frequently necessitated manual exchange via fax, phone, and secure email. When available, HIE and Prescription Drug Monitoring Program (PDMP) data were helpful, but confusion regarding the release of SUD information requirements in the context of HIPAA (Health Insurance Portability and Accountability Act), 42 CFR (Code of Federal Regulations) Part 2 and state requirements was ubiquitous. UML modeling of 4 core SUD care scenarios rising from participants' HEDIS examples revealed 3 common data sharing subprocesses.</p><p><strong>Discussion: </strong>Fragmented data sharing workflows, and extensive use of non-electronic data sharing methods impact outcomes for individuals with SUD. Interoperable consent management, HIE and PDMP integration with EHRs, and harmonized privacy regulations are provider priorities.</p><p><strong>Conclusion: </strong>Mapping provider-identified barriers reveals technical, regulatory, and workflow breakdowns that limit SUD care coordination. Advancing electronic, consent-driven interoperability employing standards is critical to improving continuity of care while safeguarding patient privacy.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag162"},"PeriodicalIF":4.7,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13464495/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148723885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative effectiveness of ambient documentation tools in primary care tool-specific variations in efficiency, documentation burden, and productivity over time.","authors":"Lidia Moura, Rebecca G Mishuris, Joshua P Metlay, Mamoon Habib, Jacqueline G You, Katherine L Gallagher, Suzanne Brodney, Meghan L Rieu-Werden, Jennifer S Haas","doi":"10.1093/jamiaopen/ooag155","DOIUrl":"10.1093/jamiaopen/ooag155","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the comparative effectiveness of ambient documentation tools (ADTs) with distinct architectures (Tablet-Based Virtual Human-Assisted Ambient [Tool A], EHR-Integrated Ambient [Tool B], and Standalone Ambient [Tool C]) on provider efficiency, documentation burden, and productivity in primary care.</p><p><strong>Materials and methods: </strong>We conducted a real-world comparative-effectiveness study of 163 primary care providers in a large integrated health system (January 2024-June 2025), analyzing 59 130 provider-days. Providers who did not adopt an ADT (<i>n</i> = 13) were excluded from comparative models. Exposure groups included Tool A (<i>n</i> = 65), Tool B (<i>n</i> = 68), and Tool C (<i>n</i> = 17). Primary outcomes were pajama time (hours of after-hours EHR activity per provider-day), visit closure within 2 days (proportion of encounters signed within 48 hours), proportion of manual note composition, and a composite opportunity score reflecting EHR efficiency (scaled 0-1). Outcomes were derived from daily provider-level EHR logs. Analyses used intention-to-treat and per-protocol frameworks with provider-clustered SEs and month fixed effects.</p><p><strong>Results: </strong>Compared with Tool B, Tool A was associated with increased pajama time (+0.022 hours of after-hours EHR activity per provider-day), higher manual note composition (+0.046 absolute proportion), lower timely visit closure (-0.120 [95% CI, -0.126,-0.115]), and reduced opportunity scores (-0.035[-0.044,-0.027]). Tool C reduced after-hours work versus Tool B (-0.007 hours per provider-day) and relative to both the reference tool and pre-exposure baseline levels (-0.055 hours per provider-day), but was associated with lower timely visit closure (-0.028[-0.036, -0.020]); opportunity scores were not significantly changed (-0.007[-0.018, 0.003]). Effects for Tool C correspond to approximately 30 fewer annual after-hours hours per provider.</p><p><strong>Conclusion: </strong>Tool choice materially shapes real-world outcomes, and tool-specific comparative evaluation is essential to guide evidence-based procurement and deployment decisions.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag155"},"PeriodicalIF":4.7,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13458937/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148713901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the effect of race on machine learning models predicting hospital admissions from emergency department.","authors":"Aidan Licoppe, Lucy An, David L Buckeridge, Antony Robert, James M G Tsui","doi":"10.1093/jamiaopen/ooag157","DOIUrl":"10.1093/jamiaopen/ooag157","url":null,"abstract":"<p><strong>Objectives: </strong>Machine learning (ML) models are increasingly being developed to support healthcare delivery. However, concerns remain about their potential to perpetuate existing biases rooted in the data used to develop them. We aim to assess the impact of using race in predicting hospital admission probabilities for patients visiting the emergency department (ED).</p><p><strong>Materials and methods: </strong>Data from the MIMIC-IV ED dataset were used to train2 ML models predicting hospital admission: one included race; the other did not. Differences in predicted admission probabilities were evaluated across racial groups under multiple validation conditions.</p><p><strong>Results: </strong>Including race as a model input was associated with meaningful differences in predicted admission probabilities for White (3.2%), Black (-1.5%), and Hispanic (-3.0%) patients, while minimal differences were observed for Asian (0.2%) and Other (0.5%) patients. These differences were associated with large Cohen's <i>d</i> effect sizes in the baseline model for White (<i>d</i> = 1.00), Black (<i>d</i> = -1.23), and Hispanic (<i>d</i> = -1.35) patients. After balancing racial group prevalence, the effects persisted for White (1.22%; <i>d</i> = 1.22) and Hispanic (-1.00%; <i>d</i> = -1.00) patients.</p><p><strong>Discussion: </strong>These findings suggest that race is associated with differences in ML-based hospital admission predictions for ED patients, underscoring the need for caution when incorporating race into clinical prediction models and the importance of rigorous bias assessment.</p><p><strong>Conclusion: </strong>As race was associated with predictions, there is a crucial need to address underlying social factors and the use of broader, more equitable clinical data for ML model training.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag157"},"PeriodicalIF":4.7,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13457077/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148713941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}