JAMIA Open最新文献

{"title":"Challenges implementing treatment guidelines in electronic health records: the American Diabetes Association Standards of Care as a case example.","authors":"Irene Demarie, Michael E Bowen, Shubham Agarwal, Christine Mai, Kelsea Marble, Jonathan Pak, Daniel F Heitjan, Zichang Xiang, Christoph U Lehmann, Ildiko Lingvay, Mujeeb A Basit","doi":"10.1093/jamiaopen/ooag141","DOIUrl":"10.1093/jamiaopen/ooag141","url":null,"abstract":"<p><strong>Objective: </strong>Treatment guidelines can improve population health; however, their implementation within electronic health records (EHRs) can be challenging. We aimed to create an implementable framework using the American Diabetes Association (ADA) Standards of Care (SOC) for people with type 2 diabetes and cardiovascular or renal disease as an example.</p><p><strong>Materials and methods: </strong>A multidisciplinary team used agile methods to translate the text-based ADA SOC into structured elements within the EHR, including logic-driven algorithms and ontology groupers for diagnoses, laboratory values, and medications, leveraging standard terminologies such as SNOMED CT, LOINC, and RxNorm.</p><p><strong>Results: </strong>The structured elements were used to implement 3 tools in the EHR: a real-time patient registry and 2 clinical decision support (CDS) instruments. The real-time registry enables dynamic, ongoing identification of patients eligible for guideline-directed medical therapy, supports more advanced analytics, and can be filtered to evaluate treatment gaps at the population and individual provider levels. The CDS tools allow clinicians to address these gaps directly within their EHR workflows.</p><p><strong>Discussion: </strong>Transforming clinical guidelines into executable constructs within the EHR is feasible but remains complex and labor-intensive. Broader and more consistent implementation could be achieved if guideline organizations provided technical frameworks, regular updates (through addenda or shared interfaces), and collaborated with EHR vendors to support the distribution and maintenance of implementable algorithms.</p><p><strong>Conclusion: </strong>The integration of executable logic into clinical guidelines, using deterministic frameworks such as Unified Modeling Language and standardized ontologies, would simplify guideline implementation across EHR platforms.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag141"},"PeriodicalIF":4.7,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13384065/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148608408","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 validation of an algorithm to identify severe sepsis onset from electronic medical records.","authors":"Ramin Homayouni, Shane Morrell, Joel David Karsten, Riya Chhabra, Paul D Bozyk","doi":"10.1093/jamiaopen/ooag129","DOIUrl":"10.1093/jamiaopen/ooag129","url":null,"abstract":"<p><strong>Objective: </strong>To develop and evaluate an automated algorithm to identify sepsis onset, referred to as time-zero (t₀), from the electronic medical records (EMR).</p><p><strong>Materials and methods: </strong>We developed an algorithm to construct a comprehensive timeline of systemic inflammatory response syndrome (SIRS) criteria and organ dysfunction (OD) using structured data, and documentation of infection (DOI) using both structured data and unstructured clinical notes. Algorithm performance was assessed using 2030 manually abstracted adult sepsis cases from a multicenter health system in southeast Michigan.</p><p><strong>Results: </strong>On average, the algorithm DOI time was significantly earlier than abstractors (mean: -0.33 hour, 95% Cl, -0.55 to -0.11), resulting in a significantly earlier t₀ (mean: -0.60 hour, 95% CI, -0.74 to -0.45).</p><p><strong>Discussion: </strong>Automated approaches to analyzing EMR data offer a scalable framework for SEP-1 monitoring, research, and quality improvement.</p><p><strong>Conclusion: </strong>Incorporating unstructured clinical notes improves DOI detection.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag129"},"PeriodicalIF":4.7,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13379704/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148498192","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":"Machine learning on asynchronous clinical pages to predict clinical deterioration.","authors":"Isabel C Arvelo, Kipp Shipley, Adam Wright, Bryan D Steitz","doi":"10.1093/jamiaopen/ooag122","DOIUrl":"10.1093/jamiaopen/ooag122","url":null,"abstract":"<p><strong>Objectives: </strong>Clinical deterioration in hospitalized patients is often preventable, but traditional early warning scores based on structured data are limited by delayed or inconsistent documentation. We developed and evaluated a machine learning pipeline that predicts clinical deterioration using real-time pager messages exchanged between clinicians.</p><p><strong>Materials and methods: </strong>We conducted a retrospective study of adult non-ICU hospitalizations at Vanderbilt University Medical Center between January 2018 and June 2021. Using the content and frequency of messages, we trained long short-term memory models to predict rapid response activation, unplanned ICU transfer, or cardiac arrest within the next 6, 12, or 24 hours. Model performance was compared with the Epic's Deterioration Index and with a logistic regression ensemble combining predictions from both models.</p><p><strong>Results: </strong>There were 1 519 445 pages associated with 111 346 hospitalizations among 74 912 patients. Deterioration events were observed in 5114 (4.6%) hospitalizations. The model achieved moderate discriminative ability, with areas under the receiver operating characteristic curve (AUROC) of 0.684 (95% CI, 0.66-0.71), 0.724 (95% CI, 0.71-0.74), and 0.669 (95% CI, 0.65-0.68) for predicting deterioration within 6, 12, and 24 h, respectively. Predictions showed moderate correlation with EDI scores (Pearson's R, 0.297-0.323) suggesting complementary signals. The ensemble model consistently outperformed either approach alone, achieving an AUROC of 0.797 (95% CI, 0.78-0.82) for 12-h prediction.</p><p><strong>Discussion and conclusion: </strong>Clinical pages represent an underutilized data source capturing clinicians' intuition and observations before they appear in formal documentation. Machine learning on pages can augment early warning systems by providing real-time information and intuition without increasing workload.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag122"},"PeriodicalIF":4.7,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13378451/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580579","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":"DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning.","authors":"Ghodsieh Ghanbari, Joseph C Ahn, Eileen Kim, Ruth Laverde, Zach Pope, Shamim Nemati","doi":"10.1093/jamiaopen/ooag123","DOIUrl":"10.1093/jamiaopen/ooag123","url":null,"abstract":"<p><strong>Objectives: </strong>Accurate and timely prediction of physiological deterioration in hospitalized patients is essential, but existing deep learning models, which rely solely on structured electronic health record (EHR) data, generate high false-positive rates by missing crucial contextual information in clinical notes. We present DETERIO-LLM, a hybrid prediction model that selectively integrates large language models (LLMs) with a deep learning model (DETERIO) to reclassify borderline-risk alerts using narrative clinical notes.</p><p><strong>Materials and methods: </strong>This retrospective study used a cohort of 1000 inpatients (4.6% deterioration prevalence). DETERIO-LLM selectively analyzed narrative notes for alerts in the uncertainty range (scores 2.5-3.5). Performance was evaluated using sensitivity, positive predictive value (PPV), and F1 score, benchmarked against comparators including the best-established ML model, eCART.</p><p><strong>Results: </strong>DETERIO-LLM significantly improved predictive precision over all comparators. At its optimal threshold, the model achieved a PPV of 30.6% and an F1 score of 37.3%, outperforming eCART. This selective integration reduced false-positive alerts by 46.5% within the uncertainty range while maintaining comparable sensitivity.</p><p><strong>Discussion: </strong>This study demonstrates a practical, interpretable method for integrating LLM-derived contextual knowledge into existing structured EHR prediction workflows. By focusing LLM analysis on high-uncertainty alerts, DETERIO-LLM substantially improves clinical utility through a marked reduction in false-positive cases, which is critical for mitigating alert fatigue.</p><p><strong>Conclusion: </strong>Selective LLM integration with structured EHR models offers a viable, interpretable path to improving early warning systems in clinical care by leveraging narrative context to reduce alert fatigue while enhancing predictive performance.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag123"},"PeriodicalIF":4.7,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375265/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148473254","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":"Design and implementation of PharMe: a mobile application to return pharmacogenomic test results to patients.","authors":"Tamara Slosarek, Jannis Baum, Benjamin Frost, Nikola Genchev, Leon Hermann, Samuel Kunst, Charlie Meister, Matti Schmidt, Sebastian Wagner, Susan M Mashni, Christoph Lippert, Erwin P Böttinger, Aniwaa Owusu Obeng","doi":"10.1093/jamiaopen/ooag132","DOIUrl":"10.1093/jamiaopen/ooag132","url":null,"abstract":"<p><strong>Objective: </strong>Pharmacogenomics can optimize therapeutic outcomes while minimizing adverse events. However, the lack of trained healthcare professionals has impeded its widespread adoption. Current patient-facing applications are either institution-specific or vary significantly in their coverage of genetic variants, interpretation guidelines, and data privacy protection. To address these shortcomings, we developed PharMe.</p><p><strong>Materials and methods: </strong>All components were developed through co-design; experts created patient-friendly content in English from Clinical Pharmacogenomics Implementation Consortium and Food and Drug Administration guidelines.</p><p><strong>Results: </strong>PharMe returns pharmacogenomic results for 17 genes and 159 medications, including phenoconversion of CYP2D6 due to inhibitors. PharMe is facilitated by Anni, a web interface enabling consistent, multilingual annotation of guidelines with patient-friendly formulations. Initial evaluations demonstrate that PharMe is usable and stable. PharMe is available for iOS and Android in English.</p><p><strong>Discussion: </strong>PharMe and Anni use transparent, standardized guideline content, are agnostic to data sources, and can flexibly be deployed globally in different settings and institutions, while upholding data privacy. Prospectively, both could support further guidelines and data formats. Validation of clinical utility, patient comprehension, and empowerment is underway in a clinical validation study with diverse patients.</p><p><strong>Conclusion: </strong>We developed a novel, extensible, usable, and stable system to transparently return pharmacogenomic results to patients. These findings support further investigation in larger, more diverse populations and in real-world clinical settings, with the goal of informing scalable, guideline-concordant pharmacogenomics implementation.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag132"},"PeriodicalIF":4.7,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371757/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148457146","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":"Scalable extraction of social determinants of health from clinical notes in a sepsis cohort using instruction-tuned language models.","authors":"Diego Salazar, Pankaj Dipankar, Daniel Smolyak, Quynh C Nguyen","doi":"10.1093/jamiaopen/ooag135","DOIUrl":"10.1093/jamiaopen/ooag135","url":null,"abstract":"<p><strong>Objectives: </strong>Social determinants of health (SDOH) are incompletely captured in structured electronic health records (EHRs) but are frequently documented in unstructured clinical notes. We evaluated large language models (LLMs) for extracting SDOH from clinical text.</p><p><strong>Materials and methods: </strong>We constructed an adult sepsis cohort from the Medical Information Mart for Intensive Care-IV (Sequential Organ Failure Assessment ≥2) and analyzed clinical notes from 1 year prior to 30 days following suspected infection. Three instruction‑tuned, decoder‑only LLMs (Mistral‑Instruct‑7B-v0.2, DeepSeek‑R1‑Distill‑Qwen‑14B, and GPT‑oss‑20B) were evaluated using structured prompts with predefined label schemas and few‑shot examples. Performance was benchmarked against a clinically validated annotated dataset and compared with a fine‑tuned encoder‑decoder baseline. Macro‑F1 scores were reported. A gold‑standard Intensive Care Unit (ICU) sepsis subset was independently annotated by 3 reviewers to assess domain‑level performance and ensemble strategies.</p><p><strong>Results: </strong>Decoder‑only models outperformed the fine‑tuned encoder‑decoder baseline across SDOH domains. GPT‑oss achieved the highest macro‑F1 score (0.79) compared with Flan‑T5‑XXL (0.57). Prompt refinement substantially improved extraction accuracy. Ensemble majority voting increased robustness across domains, while unanimous agreement yielded high precision but limited coverage. In a subsequent mortality analysis, extracted SDOH did not independently predict 30-day mortality, which was instead associated with established clinical and demographic risk factors.</p><p><strong>Discussion: </strong>Instruction‑tuned decoder‑only LLMs can reliably extract multiclass SDOH from unstructured clinical notes without task‑specific fine‑tuning. Ensemble and agreement‑based strategies provide practical operating points for high‑precision clinical deployment.</p><p><strong>Conclusion: </strong>These findings support the feasibility of leveraging LLMs to enrich EHRs with structured SDOH data, providing a scalable approach for incorporating social context into downstream risk stratification and health outcome prediction.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag135"},"PeriodicalIF":4.7,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148457113","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":"Assessment of real-world evidence research competencies in federated research networks: a maternal health fellowship program evaluation.","authors":"Haeun Lee, Benjamin Martin, Andreea A Creanga, Evan Minty, Asieh Golozar, Cindy X Cai, Cynthia Sung, Sean O'Rilley, Khyzer Aziz, Paul Nagy","doi":"10.1093/jamiaopen/ooag128","DOIUrl":"10.1093/jamiaopen/ooag128","url":null,"abstract":"<p><strong>Background and significance: </strong>Generating real-world evidence (RWE) approaches across federated evidence networks based on real-world data requires learning new methodological skills. However, standardized frameworks for defining and assessing competencies for large-scale RWE research remain limited. This study aims to develop an assessment framework for RWE studies and evaluate the competencies of RWE research professionals.</p><p><strong>Methods: </strong>We adapted the Joint Task Force (JTF) Core Competency Framework for RWE research using the Observational Medical Outcomes Partnership (OMOP) Common Data Model. Through iterative expert review, 4 new domains were created, including Ethics and Governance, Protocol Development, Study Operations, and Data Analysis and Informatics, and 4 original JTF domains were adapted. Participants completed pre- and post-training self-assessments on a 10-point scale. Paired <i>t</i>-tests with effect sizes were used to evaluate changes in competency scores.</p><p><strong>Results: </strong>Seventeen participants from academic, data, and clinical roles completed the assessment. Mean self-reported competency scores increased by 2.5 points across the 8 competency domains, with statistically significant changes observed in all domains. The largest gain was observed in Leadership and Professionalism (mean increase 3.66; 95% CI, 2.69-4.62).</p><p><strong>Discussion: </strong>The RWE research competency assessment tool captured changes in self-reported skill proficiency, perceived readiness to conduct RWE studies, and methodological knowledge gaps. These findings suggest the potential to identify competency gaps, tailor educational interventions, and inform quality benchmarks for RWE research training programs.</p><p><strong>Conclusion: </strong>This study developed and evaluated a competency assessment framework specifically designed for RWE research using standardized healthcare data, providing a tool for training program evaluation and workforce development support.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag128"},"PeriodicalIF":4.7,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13368817/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148457091","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":"A framework for assessing algorithmic discrimination risks in training data: a case of pediatric type 1 diabetes.","authors":"Ioannis Bilionis, Ricardo C Berrios, Antonio de Arriba Muñoz, Luis Fernandez-Luque, Carlos Castillo","doi":"10.1093/jamiaopen/ooag125","DOIUrl":"10.1093/jamiaopen/ooag125","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objectives: &lt;/strong&gt;To develop a generalizable framework for identifying algorithmic discrimination risks arising from subgroup imbalances in machine learning training data, with relevance to medical informatics applications where heterogeneous real-world data can bias model behavior.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Materials and methods: &lt;/strong&gt;We introduce a discrimination risk assessment framework for training datasets, a 4-step methodology integrating: (1) controlled representation sampling, (2) ensemble-based model training, (3) multilevel subgroup disparity quantification, and (4) mitigation-oriented interpretation. The framework systematically perturbs training subgroup composition while holding evaluation sets fixed to isolate representation effects. Validation was performed across 7 publicly available pediatric type 1 diabetes datasets using sociodemographic variables and continuous glucose monitoring data to assess robustness under heterogeneous data sources.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Representation balance alone does not guarantee stable or equitable model outputs. Ensemble analyses revealed subgroup-dependent volatility, with some groups consistently contributing to model generalization, while others inducing instability despite increased representation. These findings demonstrate structural sensitivity to data composition that is not captured by standard performance-only evaluations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Discussion: &lt;/strong&gt;The framework exposes disparities and instability patterns that remain hidden under single-model or balanced-data evaluations. By quantifying representation-driven behaviors and subgroup-specific training value, it offers a diagnostic tool for understanding data-induced risks prior to model deployment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;This work provides a methodology for assessing discrimination risks in training datasets used in medical informatics. By integrating data composition effects, prediction stability, and subgroup-level disparity analysis, the framework supports more reliable and transparent development of machine learning systems across diverse clinical and nonclinical contexts.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Clinical trial registration: &lt;/strong&gt;This research did not involve any new clinical trial. All analyses were performed on data from previously registered clinical trials, as listed below: &lt;b&gt;PEDAP dataset&lt;/b&gt;: The source of the data is the PEDAP Trial Study Group. (2024). PEDAP Public Dataset (Release 4). Retrieved from https://public.jaeb.org/dataset/599. The analyses content and conclusions presented herein are solely the responsibility of the authors and have not been reviewed or approved by PEDAP Trial Study Group. &lt;i&gt;ClinicalTrials.gov&lt;/i&gt; Identifier: NCT04796779; registered March 15, 2021. &lt;b&gt;IOBP2 RCT dataset&lt;/b&gt;: The source of the data is the Insulin Only Bionic Pancreas Pivotal Trial. Retrieved from https://public.jaeb.org/dataset/579. The analyses content and conclusions presented herein are solely the re","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag125"},"PeriodicalIF":4.7,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13368804/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148457020","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":"Develop and validate a fair machine learning model to identify patients with high data-continuity in electronic health records data.","authors":"Yao An Lee, Tiange Tang, Yu Huang, Jiang Bian, Lizheng Shi, Jingchuan Guo","doi":"10.1093/jamiaopen/ooag124","DOIUrl":"10.1093/jamiaopen/ooag124","url":null,"abstract":"<p><strong>Objectives: </strong>Electronic health record (EHR) data discontinuity, defined as receiving care outside of a particular EHR system, may cause misclassification of study variables. We aimed to: (1) quantify misclassification across levels of EHR data discontinuity and identify an optimal continuity threshold, (2) develop a machine learning (ML) model to predict EHR continuity and optimize fairness across racial and ethnic groups, and (3) externally validate the EHR continuity prediction model using an independent dataset.</p><p><strong>Materials and methods: </strong>We used linked OneFlorida+ EHR-Medicaid claims data for model development and Research Action for Health Network (REACHnet) EHR-Louisiana Blue Cross Blue Shield (LABlue) claims data for external validation. A Harmonized Encounter Proportion Score (HEPS), adapted from prior continuity metrics, was applied to quantify patient-level EHR data continuity and the impact on misclassification of 42 clinical variables. Machine learning models were trained using routinely available demographic, clinical, and healthcare utilization features derived from structured EHR data.</p><p><strong>Results: </strong>Higher EHR data continuity was associated with lower rates of misclassification. A HEPS threshold of approximately 30% effectively distinguished patients with sufficient data continuity. Machine learning models demonstrated strong performance in predicting high continuity (area under the receiver operating characteristic curve [AUROC] = 0.77). Fairness assessments showed bias against Hispanic group, which was substantially improved following bias mitigation procedures. Model performance remained robust and fair in the external validation.</p><p><strong>Discussion: </strong>Our study offers a practical metric for quantifying data continuity in EHR networks. The current ML model incorporating EHR-routinely collected information can accurately identify patients with high care continuity.</p><p><strong>Conclusions: </strong>We developed a generalizable data-continuity classification tool that can be easily applied across EHR systems, strengthening the rigor of EHR-based research.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag124"},"PeriodicalIF":4.7,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13361708/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438282","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 a translational data platform to create clinical-grade genome-informed risk assessments.","authors":"Jennifer L Morse, Megan He, Hana Bangash, Wendy K Chung, Joshua Cortopassi, Sophie Forman, Adam S Gordon, Marwan Hamed, Paul A Harris, Elizabeth W Karlson, Eimear E Kenny, Krzysztof Kiryluk, Iftikhar J Kullo, Adam Lewis, Nita Limdi, Cong Liu, Priya Marathe, Kyle McGuffin, Jacqueline Odgis, Emma Perez, Jacob Petrzelka, Cynthia A Prows, Luke V Rasmussen, Ellis Thomas, Georgia L Wiesner, Travis Wilson, Jodell E Linder, Josh F Peterson","doi":"10.1093/jamiaopen/ooag118","DOIUrl":"10.1093/jamiaopen/ooag118","url":null,"abstract":"<p><strong>Objective: </strong>To describe the development and implementation of an automated platform for genomic risk prediction that integrates multiple data types.</p><p><strong>Materials and methods: </strong>Using the REDCap infrastructure, we constructed the R⁴ (Recruitment, Results, and Risk Reduction) platform to intake data from clinical sites, partner laboratories, participant surveys, and electronic health record (EHR) data across 13 institutions.</p><p><strong>Results: </strong>The R⁴ Portal successfully integrated data to generate genome-informed risk assessments (GIRAs) across 11 conditions for a 23 840 person cohort. Testing phases and quality control led to network-wide protocols ensuring consistency and accuracy.</p><p><strong>Discussion: </strong>As the science of estimating disease risk evolves, standardized and high-throughput methods of collecting and manipulating complex data are required. Platforms should be open-source, modular, and reusable, ensuring flexibility, security, and integration across healthcare environments.</p><p><strong>Conclusion: </strong>The electronic MEdical Records and GEnomics (eMERGE) network successfully generated and returned comprehensive risk profiles using logic and data specific to 11 conditions in a secure and semi-automated fashion employing a customized REDCap database.</p>","PeriodicalId":36278,"journal":{"name":"JAMIA Open","volume":"9 4","pages":"ooag118"},"PeriodicalIF":4.7,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13361706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438268","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}