{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T12:06:36Z","timestamp":1790769996391,"version":"4.1.0"},"reference-count":27,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["K23EY03263501"],"award-info":[{"award-number":["K23EY03263501"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["R01EY036893"],"award-info":[{"award-number":["R01EY036893"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["P30-EY026877"],"award-info":[{"award-number":["P30-EY026877"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate the impact of incorporating community-level social determinants of health (SDoH) on the performance and algorithmic fairness of artificial intelligence (AI) models trained to predict glaucoma progression to surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>This multicenter study included 63\u2009268 glaucoma patients across 12 centers. Using electronic health records and community-level SDoH features (Distressed Communities Index [DCI] and rural\u2013urban commuting area [RUCA] codes), we developed XGBoost models to predict progression to incisional glaucoma surgery. We compared SDoH-unaware and SDoH-aware models across an internal test set and 3 diverse external test sets, evaluating area under the receiver operating characteristic curve (AUROC) (performance) and generalized equalized odds (GEO) (fairness).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Including SDoH features resulted in negligible changes in predictive performance across the internal and all external test sets. However, the SDoH-aware model improved algorithmic fairness (achieving lower GEO scores) in the internal set (0.098 vs 0.216) and a mixed-population external site (0.172 vs 0.378). Conversely, inclusion of SDoH marginally improved at a highly urbanized, low-DCI external site (0.491 vs 0.504) and failed to improve at a rural, high-DCI external site (0.241 vs 0.228).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Incorporating SDoH features can improve algorithmic fairness regarding socioeconomic disparities without sacrificing predictive accuracy; however, these benefits do not universally transfer to external sites with demographically dissimilar cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Incorporating community-level SDoH features into glaucoma prediction models improved algorithmic fairness with respect to socioeconomic disparities, without significantly altering predictive accuracy. However, fairness benefits did not universally generalize to demographically dissimilar external cohorts. AI models require rigorous external validation across diverse populations to ensure equity prior to clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag166","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T11:53:51Z","timestamp":1788954831000},"source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the impact of social determinants of health on model performance and fairness in artificial intelligence for glaucoma progression prediction"],"prefix":"10.1093","author":[{"given":"Sean Y T","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, Byers Eye Institute, Stanford University , Palo Alto, CA 94303,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohith","family":"Ravindranath","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Byers Eye Institute, Stanford University , Palo Alto, CA 94303,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua D","family":"Stein","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology & Visual Sciences, University of Michigan Kellogg Eye Center , Ann Arbor, MI 48105,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6553-3455","authenticated-orcid":false,"given":"Tina","family":"Hernandez-Boussard","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94304,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0916-9403","authenticated-orcid":false,"given":"Sophia Y","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Byers Eye Institute, Stanford University , Palo Alto, CA 94303,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"SOURCE Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tony N","family":"Pira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manju L","family":"Subramanian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sejal","family":"Amin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul A","family":"Edwards","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divya","family":"Srikumaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fasika","family":"Woreta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey S","family":"Schultz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Shrivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baseer","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis R","family":"Pasquale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alon","family":"Harris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaidehi","family":"Dedania","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul J","family":"Bryar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dustin D","family":"French","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Hribar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Merina","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suzann","family":"Pershing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophia Y","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preethi","family":"Ganapathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed B","family":"Sallam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne E","family":"Coleman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria","family":"Tseng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Deiner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer","family":"Patnaik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prem","family":"Subramanian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saleha","family":"Munir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuqaas","family":"Munir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua D","family":"Stein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsey De","family":"Lott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian L","family":"Vanderbeek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rithambara","family":"Ramachandran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajeev","family":"Ramchandran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ore-ofe O","family":"Adesina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shivani S","family":"Kamat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kishan G","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian C","family":"Stagg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barbara","family":"Wirostko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Dirghangi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"McMillan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsham","family":"Sheybani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soshian","family":"Sarrapour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Harris-Nwanyanwu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"2026093007505133800_ocag166-B1","doi-asserted-by":"publisher","first-page":"e415","DOI":"10.1016\/S2589-7500(22)00049-8","article-title":"Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data","volume":"4","author":"Rasmy","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2026093007505133800_ocag166-B2","doi-asserted-by":"publisher","first-page":"2670","DOI":"10.1093\/jamia\/ocab211","article-title":"Predicting next-day discharge via electronic health record access logs","volume":"28","author":"Zhang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"2026093007505133800_ocag166-B3","doi-asserted-by":"publisher","first-page":"e7","DOI":"10.37765\/ajmc.2020.42147","article-title":"Predicting hospitalizations from electronic health record data","volume":"26","author":"Morawski","year":"2020","journal-title":"Am J Manag Care"},{"key":"2026093007505133800_ocag166-B4","doi-asserted-by":"publisher","first-page":"100198","DOI":"10.1016\/j.jadr.2021.100198","article-title":"Predicting outcomes of psychotherapy for depression with electronic health record data","volume":"6","author":"Coley","year":"2021","journal-title":"J Affect Disord Rep"},{"key":"2026093007505133800_ocag166-B5","first-page":"40","article-title":"Using EHRs and machine learning for heart failure survival analysis","volume":"216","author":"Panahiazar","year":"2015","journal-title":"Stud Health Technol Inform"},{"key":"2026093007505133800_ocag166-B6","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"2026093007505133800_ocag166-B7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41597-021-01110-7","article-title":"Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model","volume":"9","author":"R\u00f6\u00f6sli","year":"2022","journal-title":"Sci Data"},{"key":"2026093007505133800_ocag166-B8","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1001\/jamainternmed.2025.6929","article-title":"Public opinion on use of race in clinical algorithms","volume":"186","author":"Diao","year":"2026","journal-title":"JAMA Intern Med"},{"key":"2026093007505133800_ocag166-B9","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1001\/jamainternmed.2025.6926","article-title":"Sociodemographic characteristics in clinical algorithms","volume":"186","author":"Brender","year":"2026","journal-title":"JAMA Intern Med"},{"key":"2026093007505133800_ocag166-B10","doi-asserted-by":"publisher","first-page":"100596","DOI":"10.1016\/j.xops.2024.100596","article-title":"The impact of race, ethnicity, and sex on fairness in artificial intelligence for glaucoma prediction models","volume":"5","author":"Ravindranath","year":"2025","journal-title":"Ophthalmol Sci"},{"key":"2026093007505133800_ocag166-B11","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.ajo.2019.07.005","article-title":"Machine learning-based predictive modeling of surgical intervention in glaucoma using systemic data from electronic health records","volume":"208","author":"Baxter","year":"2019","journal-title":"Am J Ophthalmol"},{"key":"2026093007505133800_ocag166-B12","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.ajo.2021.01.008","article-title":"Predictive analytics for glaucoma using data from the all of us research program","volume":"227","author":"Baxter","year":"2021","journal-title":"Am J Ophthalmol"},{"key":"2026093007505133800_ocag166-B13","doi-asserted-by":"publisher","first-page":"1157016","DOI":"10.3389\/fmed.2023.1157016","article-title":"Predicting near-term glaucoma progression: an artificial intelligence approach using clinical free-text notes and data from electronic health records","volume":"10","author":"Jalamangala Shivananjaiah","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"2026093007505133800_ocag166-B14","doi-asserted-by":"publisher","first-page":"100127","DOI":"10.1016\/j.xops.2022.100127","article-title":"Deep learning approaches for predicting glaucoma progression using electronic health records and natural language processing","volume":"2","author":"Wang","year":"2022","journal-title":"Ophthalmol Sci"},{"key":"2026093007505133800_ocag166-B15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1167\/tvst.11.3.37","article-title":"Predicting glaucoma progression requiring surgery using clinical free-text notes and transfer learning with transformers","volume":"11","author":"Hu","year":"2022","journal-title":"Transl Vis Sci Technol"},{"key":"2026093007505133800_ocag166-B16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1167\/tvst.12.10.18","article-title":"Identifying, understanding, and addressing disparities in glaucoma care in the United States","volume":"12","author":"Davuluru","year":"2023","journal-title":"Transl Vis Sci Technol"},{"key":"2026093007505133800_ocag166-B17","author":"Francis","year":"2025"},{"key":"2026093007505133800_ocag166-B18","author":"Dobis"},{"key":"2026093007505133800_ocag166-B19","author":"CDC","year":"2024"},{"key":"2026093007505133800_ocag166-B20","author":"Current procedural terminology (CPT)"},{"key":"2026093007505133800_ocag166-B21","doi-asserted-by":"publisher","first-page":"100445","DOI":"10.1016\/j.xops.2023.100445","article-title":"Prediction models for glaucoma in a multicenter electronic health records consortium: the Sight OUtcomes Research Collaborative","volume":"4","author":"Wang","year":"2024","journal-title":"Ophthalmol Sci"},{"key":"2026093007505133800_ocag166-B22","author":"Hardt"},{"key":"2026093007505133800_ocag166-B23","doi-asserted-by":"publisher","first-page":"e0000023","DOI":"10.1371\/journal.pdig.0000023","article-title":"Generalizability challenges of mortality risk prediction models: a retrospective analysis on a multi-center database","volume":"1","author":"Singh","year":"2022","journal-title":"PLOS Digit Health"},{"key":"2026093007505133800_ocag166-B24","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","article-title":"Algorithmic fairness in artificial intelligence for medicine and healthcare","volume":"7","author":"Chen","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"2026093007505133800_ocag166-B25","doi-asserted-by":"publisher","author":"Yang","DOI":"10.1145\/3600211.3604719"},{"key":"2026093007505133800_ocag166-B26","doi-asserted-by":"publisher","first-page":"e2016852","DOI":"10.1001\/jamanetworkopen.2020.16852","article-title":"Comparison of community-level and patient-level social risk data in a network of community health centers","volume":"3","author":"Cottrell","year":"2020","journal-title":"JAMA Netw Open"},{"key":"2026093007505133800_ocag166-B27","first-page":"43:1","article-title":"Inherent trade-offs in the fair determination of risk scores","volume":"67","author":"Kleinberg","year":"2017","journal-title":"Innov Theor Comput Sci"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag166\/71518559\/ocag166.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag166\/71518559\/ocag166.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:51:10Z","timestamp":1790769070000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article\/doi\/10.1093\/jamia\/ocag166\/8853717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag166","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"ocag166"}}