{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T14:07:35Z","timestamp":1789135655643,"version":"build-2803163510"},"posted":{"date-parts":[[2026,8,22]]},"group-title":"Health Informatics","reference-count":29,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["5R01AG084343-04 and 2P30AG059307-06"],"award-info":[{"award-number":["5R01AG084343-04 and 2P30AG059307-06"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Peripheral artery disease (PAD) is a major cause of cardiovascular events but remains underdiagnosed. Electronic health record (EHR)-based machine learning models show promise for earlier detection, but developing generalizable and fair models across diverse populations remains challenging.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Using the University of California Health Data Warehouse, containing EHR data from five health systems, we identified patients with and without PAD. We used unsupervised clustering to define PAD phenotypes and trained a LightGBM classifier using 14,023 features spanning demographics, comorbidities, medications, laboratory values, healthcare utilization, and diagnosis, procedure, and medication codes. We evaluated performance overall and across demographic groups and phenotypes, and assessed fairness using selection rates and subgroup differences in true- and false-positive rates.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The study included 33,739 cases and 33,739 matched controls. Clustering identified four phenotypes: patients with limited healthcare documentation (cluster 1), younger patients with severe metabolic disease (cluster 2), patients with a traditional atherosclerotic risk profile (cluster 3), and frail elderly patients with multimorbidity (cluster 4). Overall, the model demonstrated consistent performance across institutions (AUROC 0.76\u20130.79; AUC-PR 0.76\u20130.79) with well- calibrated probabilities. Performance was similar across genders, with modest variation by race and age, and was stronger in clusters 2\u20134. Cluster 2 demonstrated the highest sensitivity (TPR 0.87, 95% CI 0.87\u20130.88), while cluster 1 showed the lowest performance (TPR 0.40, 95% CI 0.39\u20130.41).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>The EHR-based PAD detection model demonstrated consistent performance across five health systems. Phenotypic clustering revealed clinically meaningful differences in model performance adding an additional consideration in ML fairness and performance evaluations.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.08.19.26360861","type":"posted-content","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T02:30:12Z","timestamp":1787452212000},"source":"Crossref","is-referenced-by-count":0,"title":["Performance and Fairness of a Peripheral Artery Disease Detection Model Across Patient Phenotypes and Health Systems"],"prefix":"10.64898","author":[{"given":"Karoline","family":"Kallis","sequence":"first","affiliation":[{"name":"Department of Surgery, Division of Vascular Surgery, University of California San Diego Health, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chyler","family":"Quitevis","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular Surgery, University of California San Diego Health, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0666-8461","authenticated-orcid":false,"given":"Mattheus","family":"Ramsis","sequence":"additional","affiliation":[{"name":"Department of Cardiology Informatics, Division of Cardiovascular Medicine, University of California San Diego Health, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nii-Kabu","family":"Kabutey","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular and Endovascular Surgery, University of California Irvine, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9119-192X","authenticated-orcid":false,"given":"Michael S.","family":"Conte","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular and Endovascular Surgery, University of California San Francisco, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2030-0337","authenticated-orcid":false,"given":"Vincent L.","family":"Rowe","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular and Endovascular Surgery, University of California Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Misty D.","family":"Humphries","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular, University of California Davis Health, Sacramento, CA, USA"}],"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 Surgery, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmoud B.","family":"Malas","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular Surgery, University of California San Diego Health, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9366-0109","authenticated-orcid":false,"given":"Elsie G.","family":"Ross","sequence":"additional","affiliation":[{"name":"Department of Surgery, Division of Vascular Surgery, University of California San Diego Health, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026091106202173000_2026.08.19.26360861v2.1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.121.318535"},{"key":"2026091106202173000_2026.08.19.26360861v2.2","doi-asserted-by":"crossref","unstructured":"Aboyans V , Canonico ME , Chastaingt L , Anand SS , Brodmann M , Couffinhal T , Criqui MH , Debus ES , Mazzolai L , McDermott MM et al: Peripheral artery disease. Nature Reviews Disease Primers 2025 11:1 2025-09-18, 11(1).","DOI":"10.1038\/s41572-025-00651-0"},{"key":"2026091106202173000_2026.08.19.26360861v2.3","doi-asserted-by":"publisher","DOI":"10.1177\/0003319719896477"},{"issue":"3","key":"2026091106202173000_2026.08.19.26360861v2.4","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1177\/1358863X251330583","article-title":"Research priorities for peripheral artery disease: A statement from the Society for Vascular Medicine","volume":"30","year":"2025","journal-title":"Vasc Med"},{"key":"2026091106202173000_2026.08.19.26360861v2.5","doi-asserted-by":"publisher","DOI":"10.1161\/cir.0000000000001052"},{"key":"2026091106202173000_2026.08.19.26360861v2.6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000628"},{"key":"2026091106202173000_2026.08.19.26360861v2.7","doi-asserted-by":"publisher","DOI":"10.1042\/ETLS20240011"},{"key":"2026091106202173000_2026.08.19.26360861v2.8","doi-asserted-by":"crossref","unstructured":"Henao R , Pencina M : Towards improving risk prediction through clustering analysis. Eur J Prev Cardiol 2025.","DOI":"10.1093\/eurjpc\/zwaf164"},{"key":"2026091106202173000_2026.08.19.26360861v2.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2024.09.062"},{"key":"2026091106202173000_2026.08.19.26360861v2.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-17180-5"},{"issue":"3","key":"2026091106202173000_2026.08.19.26360861v2.11","doi-asserted-by":"crossref","first-page":"e004741","DOI":"10.1161\/CIRCOUTCOMES.118.004741","article-title":"Predicting Future Cardiovascular Events in Patients With Peripheral Artery Disease Using Electronic Health Record Data","volume":"12","year":"2019","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"2026091106202173000_2026.08.19.26360861v2.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvs.2016.04.026"},{"issue":"8","key":"2026091106202173000_2026.08.19.26360861v2.13","doi-asserted-by":"crossref","first-page":"e18542","DOI":"10.2196\/18542","article-title":"Model-Based Algorithms for Detecting Peripheral Artery Disease Using Administrative Data From an Electronic Health Record Data System: Algorithm Development Study","volume":"8","year":"2020","journal-title":"JMIR Med Inform"},{"key":"2026091106202173000_2026.08.19.26360861v2.14","doi-asserted-by":"crossref","unstructured":"Sonderman M , Aday AW , Farber-Eger E , Mai Q , Freiberg MS , Liebovitz DM , Greenland P , McDermott MM , Beckman JA , Wells Q : Identifying Patients With Peripheral Artery Disease Using the Electronic Health Record: A Pragmatic Approach. JACC Adv 2023, 2(7).","DOI":"10.1016\/j.jacadv.2023.100566"},{"key":"2026091106202173000_2026.08.19.26360861v2.15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/637"},{"key":"2026091106202173000_2026.08.19.26360861v2.16","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa210"},{"key":"2026091106202173000_2026.08.19.26360861v2.17","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae028"},{"issue":"1","key":"2026091106202173000_2026.08.19.26360861v2.18","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41597-021-01110-7","article-title":"Hernandez-Boussard T: Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model","volume":"9","year":"2022","journal-title":"Sci Data"},{"key":"2026091106202173000_2026.08.19.26360861v2.19","doi-asserted-by":"publisher","DOI":"10.5220\/0013318600003911"},{"key":"2026091106202173000_2026.08.19.26360861v2.20","first-page":"574","article-title":"Observational Health Data Sciences and Informatics (OHDSI): Opportunities for Observational Researchers","volume":"216","year":"2015","journal-title":"Stud Health Technol Inform"},{"key":"2026091106202173000_2026.08.19.26360861v2.21","doi-asserted-by":"crossref","unstructured":"Park C , Schappe T , Peskoe S , Mohottige D , Chan NW , Bhavsar NA , Boulware LE , Pendergast J , Kirk AD , McElroy LM : A comparison of deprivation indices and application to transplant populations. American Journal of Transplantation 2023\/03\/01, 23(3).","DOI":"10.1016\/j.ajt.2022.11.018"},{"key":"2026091106202173000_2026.08.19.26360861v2.22","doi-asserted-by":"crossref","unstructured":"Jung K , Sudat SEK , Kwon N , Stewart WF , Shah NH : Predicting need for advanced illness or palliative care in a primary care population using electronic health record data. J Biomed Inform 2019, 92:103115.","DOI":"10.1016\/j.jbi.2019.103115"},{"key":"2026091106202173000_2026.08.19.26360861v2.23","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-018-0677-8"},{"key":"2026091106202173000_2026.08.19.26360861v2.24","first-page":"144","article-title":"Discovering Patient Phenotypes Using Generalized Low Rank Models","volume":"21","year":"2016","journal-title":"Pac Symp Biocomput"},{"key":"2026091106202173000_2026.08.19.26360861v2.25","doi-asserted-by":"publisher","DOI":"10.7326\/M18-1990"},{"key":"2026091106202173000_2026.08.19.26360861v2.26","unstructured":"Hardt M , Price E , Srebro N : Equality of opportunity in supervised learning. 30th Conference on Neural Information Processing Systems (NIPS 2016) 2016."},{"key":"2026091106202173000_2026.08.19.26360861v2.27","doi-asserted-by":"publisher","DOI":"10.2196\/44732"},{"key":"2026091106202173000_2026.08.19.26360861v2.28","doi-asserted-by":"crossref","unstructured":"Grant C , Cuddeback JK , Alabi O , Hicks CW , Sadik K , Ciemins EL : Perspectives on Lower Extremity Peripheral Artery Disease: A Qualitative Study of Early Diagnosis and Treatment and the Impact of Health Disparities. Population Health Management 2023 Nov 24, 26(6).","DOI":"10.1089\/pop.2023.0095"},{"key":"2026091106202173000_2026.08.19.26360861v2.29","doi-asserted-by":"crossref","unstructured":"Quan X , Xiong H , Liu X , Song P , Wang D , Chen Q , Hu X , Shi M : Diagnosis models to predict peripheral arterial disease: a systematic review and meta analysis. Scientific Reports 2025 Jul 22, 15(1).","DOI":"10.1038\/s41598-025-10459-3"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.19.26360861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T13:20:33Z","timestamp":1789132833000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.08.19.26360861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.64898\/2026.08.19.26360861","relation":{},"subject":[],"published":{"date-parts":[[2026,8,22]]},"subtype":"preprint"}}