{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T01:11:19Z","timestamp":1776215479429,"version":"3.50.1"},"reference-count":23,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T00:00:00Z","timestamp":1741392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R35GM138353"],"award-info":[{"award-number":["R35GM138353"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["RF1AG07744"],"award-info":[{"award-number":["RF1AG07744"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000861","name":"Burroughs Wellcome Fund","doi-asserted-by":"publisher","award":["1019816"],"award-info":[{"award-number":["1019816"]}],"id":[{"id":"10.13039\/100000861","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013961","name":"Robertson Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013961","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alfred E. Mann Foundation"},{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["INV-037517"],"award-info":[{"award-number":["INV-037517"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) models utilizing electronic health record data for disease prediction can enhance risk stratification but may lack specificity, which is crucial for reducing the economic and psychological burdens associated with false positives. This study aims to evaluate the impact of confounders on the specificity of single-outcome prediction models and assess the effectiveness of a multi-class architecture in mitigating outcome conflation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We evaluated a state-of-the-art model predicting pancreatic cancer from disease code sequences in an independent cohort of 2.3 million patients and compared this single-outcome model with a multi-class model designed to predict multiple cancer types simultaneously. Additionally, we conducted a clinical simulation experiment to investigate the impact of confounders on the specificity of single-outcome prediction models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>While we were able to independently validate the pancreatic cancer prediction model, we found that its prediction scores were also correlated with ovarian cancer, suggesting conflation of outcomes due to underlying confounders. Building on this observation, we demonstrate that the specificity of single-outcome prediction models is impaired by confounders using a clinical simulation experiment. Introducing a multi-class architecture improves specificity in predicting cancer types compared to the single-outcome model while preserving performance, mitigating the conflation of outcomes in both the real-world and simulated contexts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Our results highlight the risk of outcome conflation in single-outcome AI prediction models and demonstrate the effectiveness of a multi-class approach in mitigating this issue.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The number of predicted outcomes needs to be carefully considered when employing AI disease risk prediction models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf033","type":"journal-article","created":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T15:22:22Z","timestamp":1739200942000},"page":"920-927","source":"Crossref","is-referenced-by-count":2,"title":["Mitigation of outcome conflation in predicting patient outcomes using electronic health records"],"prefix":"10.1093","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-3527","authenticated-orcid":false,"given":"S Momsen","family":"Reincke","sequence":"first","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Pediatrics, Stanford University School of Medicine , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1630-1564","authenticated-orcid":false,"given":"Camilo","family":"Espinosa","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Pediatrics, Stanford University School of Medicine , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1194-7510","authenticated-orcid":false,"given":"Philip","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9010-7423","authenticated-orcid":false,"given":"Tomin","family":"James","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Pediatrics, Stanford University School of Medicine , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1046-125X","authenticated-orcid":false,"given":"Elo\u00efse","family":"Berson","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Pathology, Stanford University , Stanford, CA 94305,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6117-8764","authenticated-orcid":false,"given":"Nima","family":"Aghaeepour","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Pediatrics, Stanford University School of Medicine , Stanford, CA 94305,","place":["United States"]},{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,3,8]]},"reference":[{"key":"2026041420160644600_ocaf033-B1","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/s41591-023-02332-5","article-title":"A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories","volume":"29","author":"Placido","year":"2023","journal-title":"Nat Med"},{"key":"2026041420160644600_ocaf033-B2","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","article-title":"A clinically applicable approach to continuous prediction of future acute kidney injury","volume":"572","author":"Toma\u0161ev","year":"2019","journal-title":"Nature"},{"key":"2026041420160644600_ocaf033-B3","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-023-06160-y","article-title":"Health system-scale language models are all-purpose prediction engines","volume":"619","author":"Jiang","year":"2023","journal-title":"Nature"},{"key":"2026041420160644600_ocaf033-B4","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digital Med"},{"key":"2026041420160644600_ocaf033-B5","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1038\/s41591-022-01894-0","article-title":"Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis","volume":"28","author":"Adams","year":"2022","journal-title":"Nat Med"},{"key":"2026041420160644600_ocaf033-B6","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1007\/s40264-023-01325-0","article-title":"Use of electronic health record data for drug safety signal identification: a scoping review","volume":"46","author":"Davis","year":"2023","journal-title":"Drug Saf"},{"key":"2026041420160644600_ocaf033-B7","doi-asserted-by":"crossref","first-page":"eadc9854","DOI":"10.1126\/scitranslmed.adc9854","article-title":"Data-driven longitudinal characterization of neonatal health and morbidity","volume":"15","author":"De Francesco","year":"2023","journal-title":"Sci Transl Med"},{"key":"2026041420160644600_ocaf033-B8","doi-asserted-by":"crossref","first-page":"eade7692","DOI":"10.1126\/sciadv.ade7692","article-title":"Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries","volume":"9","author":"Espinosa","year":"2023","journal-title":"Sci. Adv"},{"key":"2026041420160644600_ocaf033-B9","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"2026041420160644600_ocaf033-B10","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"2026041420160644600_ocaf033-B11","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern Med"},{"key":"2026041420160644600_ocaf033-B12","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/S0140-6736(23)02830-1","article-title":"GRAIL-Galleri: why the special treatment?","volume":"403","author":"Turnbull","year":"2024","journal-title":"Lancet."},{"key":"2026041420160644600_ocaf033-B13","doi-asserted-by":"crossref","first-page":"e396","DOI":"10.1016\/S2589-7500(24)00062-1","article-title":"Multi-cancer risk stratification based on national health data: a retrospective modelling and validation study","volume":"6","author":"Jung","year":"2024","journal-title":"Lancet Digit Health"},{"key":"2026041420160644600_ocaf033-B14","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.neo.2017.11.005","article-title":"Symptom signatures and diagnostic timeliness in cancer patients: a review of current evidence","volume":"20","author":"Koo","year":"2018","journal-title":"Neoplasia."},{"key":"2026041420160644600_ocaf033-B15","doi-asserted-by":"publisher","author":"Stanford Center for Population Health Sciences. MarketScan databases. Redivis","year":"2023","DOI":"10.57761\/kg3j-nh50"},{"key":"2026041420160644600_ocaf033-B16","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1093\/jamia\/ocaa088","article-title":"MINIMAR (MINimum Information for Medical AI Reporting): developing reporting standards for artificial intelligence in health care","volume":"27","author":"Hernandez-Boussard","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2026041420160644600_ocaf033-B17","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1038\/s41591-020-1041-y","article-title":"Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist","volume":"26","author":"Norgeot","year":"2020","journal-title":"Nat Med"},{"key":"2026041420160644600_ocaf033-B18","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41575-021-00457-x","article-title":"Pancreatic cancer epidemiology: understanding the role of lifestyle and inherited risk factors","volume":"18","author":"Klein","year":"2021","journal-title":"Nat Rev Gastroenterol Hepatol"},{"key":"2026041420160644600_ocaf033-B19","doi-asserted-by":"crossref","first-page":"16061","DOI":"10.1038\/nrdp.2016.61","article-title":"Ovarian cancer","volume":"2","author":"Matulonis","year":"2016","journal-title":"Nat Rev Dis Primers."},{"key":"2026041420160644600_ocaf033-B20","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1145\/3178876.3186050","author":"Zou","year":"2018"},{"key":"2026041420160644600_ocaf033-B21","doi-asserted-by":"publisher","author":"Wang","year":"2014","DOI":"10.1109\/ICPR.2014.47"},{"key":"2026041420160644600_ocaf033-B22","doi-asserted-by":"publisher","author":"Hu","DOI":"10.48550\/arxiv.2205.09797"},{"key":"2026041420160644600_ocaf033-B23","doi-asserted-by":"publisher","author":"Makino","DOI":"10.48550\/arxiv.2202.04136"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/5\/920\/62347269\/ocaf033.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/5\/920\/62347269\/ocaf033.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:28:48Z","timestamp":1776212928000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/5\/920\/8064347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,8]]},"references-count":23,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,3,8]]},"published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf033","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,5]]},"published":{"date-parts":[[2025,3,8]]}}}