{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T14:38:53Z","timestamp":1790174333285,"version":"4.1.0"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that disproportionately affects women and racial\/ethnic minority groups. Predicting disease flares is essential for improving patient outcomes, yet few studies integrate both clinical and social determinants of health (SDoH). We therefore developed FLAME (FLAre Machine learning prediction of SLE), a machine learning pipeline that uses electronic health records (EHRs) and contextual-level SDoH to predict 3-month flare risk, emphasizing explainability and fairness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective cohort study of 28\u2009433 patients with SLE from the University of Florida Health (2011-2022), linked to 675 contextual-level SDoH variables. We used XGBoost and logistic regression models to predict 3-month flare risk, evaluating model performance using the area under the receiver operating characteristic (AUROC). We applied SHapley Additive exPlanations (SHAP) values and causal structure learning to identify key predictors. Fairness was assessed using the equality of opportunity metric, measured by the false-negative rate across racial\/ethnic groups.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The FLAME model, incorporating clinical and contextual-level SDoH, achieved an AUROC of 0.66. The clinical-only model performed slightly better (AUROC of 0.67), while the SDoH-only model had lower performance (AUROC of 0.54). SHAP analysis identified headache, organic brain syndrome, and pyuria as key predictors. Causal learning revealed interactions between clinical factors and contextual-level SDoH. Fairness assessments showed no significant biases across groups.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>FLAME offers a fair and interpretable approach to predicting SLE flares, providing meaningful insights that may guide future clinical interventions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>FLAME shows promise as an EHR-based tool to support personalized, equitable, and holistic SLE care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooaf072","type":"journal-article","created":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T07:51:22Z","timestamp":1751701882000},"source":"Crossref","is-referenced-by-count":14,"title":["A fair machine learning model to predict flares of systemic lupus erythematosus"],"prefix":"10.1093","volume":"8","author":[{"given":"Yongqiu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Health Outcomes and Biomedical Informatics, University of Florida , Gainesville, FL, 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixia","family":"Yao","sequence":"additional","affiliation":[{"name":"Polygon Health Analytics LLC , Chalfont, PA, 18914,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao An","family":"Lee","sequence":"additional","affiliation":[{"name":"Pharmaceutical Outcomes & Policy, University of Florida , Gainesville, FL, 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, Indiana University School of Medicine , IN, 46202,","place":["United States"]},{"name":"Center for Biomedical Informatics, Regenstrief Institute , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter A","family":"Merkel","sequence":"additional","affiliation":[{"name":"Division of Rheumatology, Department of Medicine, University of Pennsylvania , Philadelphia, PA, 19104,","place":["United States"]},{"name":"Division of Epidemiology, Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania , Philadelphia, PA, 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ernest","family":"Vina","sequence":"additional","affiliation":[{"name":"Division of Rheumatology, College of Medicine, University of Arizona , Tucson, AZ, 85721,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya-Yun","family":"Yeh","sequence":"additional","affiliation":[{"name":"Pharmaceutical Outcomes & Policy, University of Florida , Gainesville, FL, 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Li","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of Maryland , Baltimore, MD, 21201,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John M","family":"Allen","sequence":"additional","affiliation":[{"name":"Department of Pharmacy Practice, Purdue University College of Pharmacy , IN, 46202,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Bian","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, Indiana University School of Medicine , IN, 46202,","place":["United States"]},{"name":"Center for Biomedical Informatics, Regenstrief Institute , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingchuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Pharmaceutical Outcomes & Policy, University of Florida , Gainesville, FL, 32611,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"2025072615563131200_ooaf072-B1","doi-asserted-by":"crossref","first-page":"e00004","DOI":"10.1097\/IN9.0000000000000004","article-title":"Sex bias in systemic lupus erythematosus: a molecular insight","volume":"4","author":"Bose","year":"2022","journal-title":"Immunometabolism (Cobham)"},{"key":"2025072615563131200_ooaf072-B2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.7861\/clinmedicine.17-1-78","article-title":"Systemic lupus erythematosus","volume":"17","author":"Shaikh","year":"2017","journal-title":"Clin Med (Lond)"},{"key":"2025072615563131200_ooaf072-B3","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1002\/art.41632","article-title":"Prevalence of systemic lupus erythematosus in the United States: estimates from a meta-analysis of the Centers for Disease Control and Prevention national lupus registries","volume":"73","author":"Izmirly","year":"2021","journal-title":"Arthritis Rheumatol"},{"key":"2025072615563131200_ooaf072-B4","first-page":"240","article-title":"Lupus: an overview of the disease and management options","volume":"37","author":"Maidhof","year":"2012","journal-title":"P T"},{"key":"2025072615563131200_ooaf072-B5","doi-asserted-by":"crossref","first-page":"1996","DOI":"10.1002\/art.40191","article-title":"The incidence and prevalence of systemic lupus erythematosus in San Francisco county, California: the California lupus surveillance project","volume":"69","author":"Dall\u2019Era","year":"2017","journal-title":"Arthritis Rheumatol"},{"key":"2025072615563131200_ooaf072-B6","doi-asserted-by":"crossref","first-page":"3299","DOI":"10.1007\/s10067-022-06268-y","article-title":"Health disparities in systemic lupus erythematosus\u2014a narrative review","volume":"41","author":"Hasan","year":"2022","journal-title":"Clin Rheumatol"},{"key":"2025072615563131200_ooaf072-B7","doi-asserted-by":"crossref","first-page":"i10","DOI":"10.1093\/rheumatology\/keac613","article-title":"The impact of social determinants of health on the presentation, management and outcomes of systemic lupus erythematosus","volume":"62","author":"Williams","year":"2023","journal-title":"Rheumatology (Oxford)"},{"key":"2025072615563131200_ooaf072-B8","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1055\/s-0043-1768732","article-title":"Enriching real-world data with social determinants of health for health outcomes and health equity: successes, challenges, and opportunities","volume":"32","author":"He","year":"2023","journal-title":"Yearb Med Inform"},{"key":"2025072615563131200_ooaf072-B9","doi-asserted-by":"crossref","first-page":"2143","DOI":"10.1002\/art.37995","article-title":"Baseline predictors of systemic lupus erythematosus flares: data from the combined placebo groups in the phase III belimumab trials","volume":"65","author":"Petri","year":"2013","journal-title":"Arthritis Rheum"},{"key":"2025072615563131200_ooaf072-B10","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1177\/0961203317728810","article-title":"Predictive factors of flares in systemic lupus erythematosus patients: data from a multiethnic Latin American cohort","volume":"27","author":"Ugarte-Gil","year":"2018","journal-title":"Lupus"},{"key":"2025072615563131200_ooaf072-B11","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/rheumatology\/ket322","article-title":"Identification of clinical predictors of flare in systemic lupus erythematosus patients: a 24-month prospective cohort study","volume":"53","author":"In\u00eas","year":"2014","journal-title":"Rheumatology (Oxford)"},{"key":"2025072615563131200_ooaf072-B12","doi-asserted-by":"crossref","first-page":"127","DOI":"10.3390\/cells8020127","article-title":"Epigenetically altered T cells contribute to lupus flares","volume":"8","author":"Richardson","year":"2019","journal-title":"Cells"},{"key":"2025072615563131200_ooaf072-B13","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1080\/03007995.2022.2101804","article-title":"Development of a claims-based flare algorithm for systemic lupus erythematosus","volume":"38","author":"Goetz","year":"2022","journal-title":"Curr Med Res Opin"},{"key":"2025072615563131200_ooaf072-B14","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1111\/joim.12752","article-title":"Physician burnout: contributors, consequences and solutions","volume":"283","author":"West","year":"2018","journal-title":"J Intern Med"},{"key":"2025072615563131200_ooaf072-B15","doi-asserted-by":"crossref","first-page":"15","DOI":"10.47488\/dhrp.v1iS5.39","article-title":"Growing shortage of healthcare workers poses an existential threat to the public health system: strategies to mitigate this challenge in the face of COVID-19 pandemic","volume":"1","author":"Rao","year":"2021","journal-title":"DHR Proc"},{"key":"2025072615563131200_ooaf072-B16","first-page":"123","volume-title":"Assessing the Need for a Comprehensive National Health System in the United States","author":"Harp","year":"2023"},{"key":"2025072615563131200_ooaf072-B17","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1002\/acr2.11590","article-title":"Disparities in lupus and the role of social determinants of health: current state of knowledge and directions for future research","volume":"5","author":"Buie","year":"2023","journal-title":"ACR Open Rheumatol"},{"key":"2025072615563131200_ooaf072-B18","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1002\/acr.25359","article-title":"Multiplicative impact of adverse social determinants of health on outcomes in lupus nephritis: a meta-analysis and systematic review","volume":"76","author":"Garg","year":"2024","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"2025072615563131200_ooaf072-B19","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1056\/NEJMp2200089","article-title":"Real-world evidence\u2014where are we now?","volume":"386","author":"Concato","year":"2022","journal-title":"N Engl J Med"},{"key":"2025072615563131200_ooaf072-B20","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1056\/NEJMsb1609216","article-title":"Real-world evidence\u2014what is it and what can it tell us?","volume":"375","author":"Sherman","year":"2016","journal-title":"N Engl J Med"},{"key":"2025072615563131200_ooaf072-B21","doi-asserted-by":"crossref","first-page":"e36388","DOI":"10.2196\/36388","article-title":"Evaluation and mitigation of racial bias in clinical machine learning models: scoping review","volume":"10","author":"Huang","year":"2022","journal-title":"JMIR Med Inform"},{"key":"2025072615563131200_ooaf072-B22","doi-asserted-by":"publisher","first-page":"104250","DOI":"10.1016\/j.ebiom.2022.104250","article-title":"Algorithmic fairness in computational medicine","volume":"84","author":"Xu","year":"2022","journal-title":"eBioMedicine"},{"key":"2025072615563131200_ooaf072-B23","doi-asserted-by":"crossref","first-page":"2236","DOI":"10.1002\/sim.1415","article-title":"1. Causation, prediction, and search. 2nd edn. Peter Spirtes, Clark Glymour and Richard Scheines, MIT Press, Cambridge, MA, 2000. No. of pages: 543. ISBN 0-262-19440-6","volume":"22","author":"Koster","year":"2003","journal-title":"Stat Med"},{"key":"2025072615563131200_ooaf072-B24","doi-asserted-by":"crossref","first-page":"K62","DOI":"10.1016\/j.vaccine.2013.06.104","article-title":"A systematic review of validated methods for identifying systemic lupus erythematosus (SLE) using administrative or claims data","volume":"31","author":"Moores","year":"2013","journal-title":"Vaccine."},{"key":"2025072615563131200_ooaf072-B25","doi-asserted-by":"crossref","first-page":"e000357","DOI":"10.1136\/lupus-2019-000357","article-title":"Real-world treatment patterns, healthcare resource utilisation and costs in patients with systemic lupus erythematosus treated with belimumab: a retrospective analysis of claims data in the USA","volume":"7","author":"Bell","year":"2020","journal-title":"Lupus Sci Med"},{"key":"2025072615563131200_ooaf072-B26","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1002\/acr.24522","article-title":"Developing and validating methods to assemble systemic lupus erythematosus births in the electronic health record","volume":"74","author":"Barnado","year":"2022","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"2025072615563131200_ooaf072-B27","doi-asserted-by":"publisher","DOI":"10.3390\/vaccines12121399","article-title":"Flares and predicting factors of flares in patients with systemic lupus erythematosus associated with different doses and types of COVID-19 vaccines","volume":"12","author":"Louthrenoo","year":"2024","journal-title":"Vaccines (Basel)"},{"key":"2025072615563131200_ooaf072-B28","doi-asserted-by":"crossref","first-page":"e001131","DOI":"10.1136\/lupus-2023-001131","article-title":"Intercurrent infection as a risk factor for disease flares in patients with systemic lupus erythematosus","volume":"11","author":"El Hadiyen","year":"2024","journal-title":"Lupus Sci Med"},{"key":"2025072615563131200_ooaf072-B29","first-page":"288","article-title":"Systemic lupus erythematosus disease activity index 2000","volume":"29","author":"Gladman","year":"2002","journal-title":"J Rheumatol"},{"key":"2025072615563131200_ooaf072-B30","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1002\/art.24741","article-title":"Frequency and determinants of flare and persistently active disease in systemic lupus erythematosus","volume":"61","author":"Nikpour","year":"2009","journal-title":"Arthritis Rheum"},{"key":"2025072615563131200_ooaf072-B31","volume-title":"Introduction to Statistics and Data Analysis: For the Behavioral Sciences","author":"Lockhart","year":"1998"},{"key":"2025072615563131200_ooaf072-B32","author":"Date: PNV","year":"2025"},{"key":"2025072615563131200_ooaf072-B33","first-page":"4765","author":"Lundberg"},{"key":"2025072615563131200_ooaf072-B34","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1080\/10618600.2014.900500","article-title":"Learning the structure of mixed graphical models","volume":"24","author":"Lee","year":"2015","journal-title":"J Comput Graph Stat"},{"key":"2025072615563131200_ooaf072-B35","first-page":"48","article-title":"Evaluation of causal structure learning methods on mixed data types","volume":"92","author":"Raghu","year":"2018","journal-title":"Proc Mach Learn Res"},{"key":"2025072615563131200_ooaf072-B36","first-page":"3921","article-title":"Order-independent constraint-based causal structure learning","volume":"15","author":"Colombo","year":"2014","journal-title":"J Mach Learn Res"},{"key":"2025072615563131200_ooaf072-B37","volume-title":"Causation, Prediction, and Search","author":"Spirtes"},{"key":"2025072615563131200_ooaf072-B38","author":"Patient flow with Sankey diagrams or Circos plots","year":"2025"},{"key":"2025072615563131200_ooaf072-B39","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1089\/big.2016.0047","article-title":"Fair prediction with disparate impact: a study of bias in recidivism prediction instruments","volume":"5","author":"Chouldechova","year":"2017","journal-title":"Big Data"},{"key":"2025072615563131200_ooaf072-B40","doi-asserted-by":"crossref","first-page":"2435","DOI":"10.1001\/archinte.164.22.2435","article-title":"Diagnostic accuracy for lupus and other systemic autoimmune diseases in the primary care setting","volume":"164","author":"Narain","year":"2004","journal-title":"Arch Intern Med"},{"key":"2025072615563131200_ooaf072-B41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41666-020-00082-4","article-title":"Federated learning for healthcare informatics","volume":"5","author":"Xu","year":"2021","journal-title":"J Healthc Inform Res"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/4\/ooaf072\/63856062\/ooaf072.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/4\/ooaf072\/63856062\/ooaf072.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T19:56:41Z","timestamp":1753559801000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooaf072\/8214041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf072","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,8]]},"published":{"date-parts":[[2025,7,3]]},"article-number":"ooaf072"}}