{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T22:06:35Z","timestamp":1774562795071,"version":"3.50.1"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Shanghai Funding","award":["23ZR1436400"],"award-info":[{"award-number":["23ZR1436400"]}]},{"name":"Shanghai three-year","award":["2023-2025"],"award-info":[{"award-number":["2023-2025"]}]},{"name":"action plan to strengthen the public health system","award":["GWVI-11.1-05"],"award-info":[{"award-number":["GWVI-11.1-05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study aims to tackle the critical challenge of adapting deep learning (DL) models for deployment in real-world healthcare settings, specifically focusing on catastrophic forgetting due to distribution shifts between hospital and non-hospital environments. Metabolic syndrome (MetS) is susceptible to misdiagnosis by DL models due to distribution shifts. This work demonstrates the potential of continual learning (CL) to enhance model performance in MetS identification across diverse settings.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We utilized 3 healthcare datasets from 2 distinct settings: Medical Information Mart for Intensive Care (MIMIC; from a hospital setting), National Health and Nutrition Examination Survey (NHANES), and a proprietary dataset (both from non-hospital settings). We proposed a robust MetS identification pipeline with CL strategies and evaluated its effectiveness in mitigating catastrophic forgetting while maintaining high predictive performance under distribution shift.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The CL method outperformed the control (sequential training without any strategies) method. The CL method reached a cumulative area under the ROC curve (AUROC) of 0.85 and area under the precision-recall curve of 0.65 on the combined test set. Moreover, training order proved critical: models trained from hospital to non-hospital settings achieved a 7.6% improvement in AUROC, increasing from 0.79 to 0.85, compared to the reverse order.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Our results demonstrate the potential of CL for applications across healthcare settings, particularly between hospital and non-hospital settings. We also discuss the impact of training order on the results.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The proposed CL model effectively mitigates catastrophic forgetting, enhancing the overall performance of DL models. Our results underscore the prospect of CL methods in developing medical DL models and maintaining scalability across diverse healthcare settings.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf070","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T11:15:16Z","timestamp":1749640516000},"page":"1310-1319","source":"Crossref","is-referenced-by-count":1,"title":["Continual learning across population cohorts with distribution shift: insights from multi-cohort metabolic syndrome identification"],"prefix":"10.1093","volume":"32","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Public Health, Shanghai Jiao Tong University School of Medicine , Shanghai 200025,","place":["China"]}]},{"given":"Zhangdaihong","family":"Liu","sequence":"additional","affiliation":[{"name":"Oxford Suzhou Center For Advanced Research , Suzhou, Jiangsu 215124,","place":["China"]}]},{"given":"Jingjing","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Public Health, Shanghai Jiao Tong University School of Medicine , Shanghai 200025,","place":["China"]}]},{"given":"Chenglai","family":"Cai","sequence":"additional","affiliation":[{"name":"Dime Software , Wuxi, Jiangsu 214100,","place":["China"]}]},{"given":"David A","family":"Clifton","sequence":"additional","affiliation":[{"name":"Oxford Suzhou Center For Advanced Research , Suzhou, Jiangsu 215124,","place":["China"]},{"name":"Department of Engineering Science, University of Oxford , Oxford OX1 3PJ,","place":["United Kingdom"]}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Public Health, Shanghai Jiao Tong University School of Medicine , Shanghai 200025,","place":["China"]}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Public Health, Shanghai Jiao Tong University School of Medicine , Shanghai 200025,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"2025072103522342900_ocaf070-B1","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1038\/s42255-020-0212-y","article-title":"An artificial intelligence decision support system for the management of type 1 diabetes","volume":"2","author":"Tyler","year":"2020","journal-title":"Nat Metabol"},{"key":"2025072103522342900_ocaf070-B2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an ai system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"2025072103522342900_ocaf070-B3","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat Med"},{"key":"2025072103522342900_ocaf070-B4","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1038\/s41591-023-02702-z","article-title":"A deep learning system for predicting time to progression of diabetic retinopathy","volume":"30","author":"Dai","year":"2024","journal-title":"Nat Med"},{"key":"2025072103522342900_ocaf070-B5","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1038\/s41591-020-0867-7","article-title":"Predicting conversion to wet age-related macular degeneration using deep learning","volume":"26","author":"Yim","year":"2020","journal-title":"Nat Med"},{"key":"2025072103522342900_ocaf070-B6","author":"Blaas"},{"key":"2025072103522342900_ocaf070-B7","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025072103522342900_ocaf070-B8","doi-asserted-by":"crossref","first-page":"5678","DOI":"10.1038\/s41467-021-25858-z","article-title":"Dynamic memory to alleviate catastrophic forgetting in continual learning with medical imaging","volume":"12","author":"Perkonigg","year":"2021","journal-title":"Nat Commun"},{"key":"2025072103522342900_ocaf070-B9","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1016\/j.jacc.2010.05.034","article-title":"The metabolic syndrome and cardiovascular risk a systematic review and meta-analysis","volume":"56","author":"Mottillo","year":"2010","journal-title":"J Am Coll Cardiol"},{"key":"2025072103522342900_ocaf070-B10","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.ijcard.2011.12.079","article-title":"Interaction of smoking and metabolic syndrome on cardiovascular risk in a Chinese cohort","volume":"167","author":"Zhang","year":"2013","journal-title":"Int J Cardiol"},{"key":"2025072103522342900_ocaf070-B11","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1161\/CIRCULATIONAHA.105.169404","article-title":"Diagnosis and management of the metabolic syndrome: an American Heart Association\/National Heart, Lung, and Blood Institute scientific statement","volume":"112","author":"Grundy","year":"2005","journal-title":"Circulation"},{"key":"2025072103522342900_ocaf070-B12","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1016\/j.jacc.2015.06.1328","article-title":"The cardiometabolic health alliance: working toward a new care model for the metabolic syndrome","volume":"66","author":"Sperling","year":"2015","journal-title":"J Am Coll Cardiol"},{"key":"2025072103522342900_ocaf070-B13","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/1741-7015-9-48","article-title":"Metabolic syndrome: definitions and controversies","volume":"9","author":"Kassi","year":"2011","journal-title":"BMC Med"},{"key":"2025072103522342900_ocaf070-B14","doi-asserted-by":"crossref","first-page":"e005672","DOI":"10.1136\/bmjgh-2021-005672","article-title":"The gender and geography of publishing: a review of sex\/gender reporting and author representation in leading general medical and global health journals","volume":"6","author":"Merriman","year":"2021","journal-title":"BMJ Glob Health"},{"key":"2025072103522342900_ocaf070-B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11113-020-09631-6","article-title":"The critical role of racial\/ethnic data disaggregation for health equity","volume":"40","author":"Kauh","year":"2021","journal-title":"Popul Res Policy Rev"},{"key":"2025072103522342900_ocaf070-B16","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1186\/s12889-020-09940-7","article-title":"Health behaviors in major chronic diseases patients: trends and regional variations analysis, 2008\u20132017, Korea","volume":"20","author":"Jeon","year":"2020","journal-title":"BMC Public Health"},{"key":"2025072103522342900_ocaf070-B17","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s10389-017-0855-7","article-title":"Disease-specific knowledge in individuals with and without chronic conditions","volume":"26","author":"Gellert","year":"2018","journal-title":"J Public Health"},{"key":"2025072103522342900_ocaf070-B18","doi-asserted-by":"crossref","first-page":"E76","DOI":"10.5888\/pcd14.160613","article-title":"Peer reviewed: differences between younger and older us adults with multiple chronic conditions","volume":"14","author":"Adams","year":"2017","journal-title":"Prev Chronic Dis"},{"key":"2025072103522342900_ocaf070-B19","first-page":"1345","article-title":"A survey on transfer learning","volume":"22","author":"Jialin Pan","year":"2009","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2025072103522342900_ocaf070-B20","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: a review","volume":"113","author":"Parisi","year":"2019","journal-title":"Neural Netw"},{"key":"2025072103522342900_ocaf070-B21","doi-asserted-by":"crossref","first-page":"8380","DOI":"10.1038\/s41598-022-12497-7","article-title":"Leveraging clinical data across healthcare institutions for continual learning of predictive risk models","volume":"12","author":"Amrollahi","year":"2022","journal-title":"Sci Rep"},{"key":"2025072103522342900_ocaf070-B22","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s12911-024-02464-9","article-title":"Continual learning framework for a multicenter study with an application to electrocardiogram","volume":"24","author":"Kim","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025072103522342900_ocaf070-B23","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3390\/healthcare12020155","article-title":"Continual learning with deep neural networks in physiological signal data: a survey","volume":"12","author":"Li","year":"2024","journal-title":"Healthcare"},{"key":"2025072103522342900_ocaf070-B24","first-page":"2020","volume-title":"National Health and Nutrition Examination Survey Data","author":"Centers for Disease Control and Prevention (CDC)"},{"key":"2025072103522342900_ocaf070-B25","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1016\/j.jada.2007.02.017","article-title":"Nutrition assessment in the national health and nutrition examination survey 1999-2002","volume":"107","author":"Wright","year":"2007","journal-title":"J Am Diet Assoc"},{"key":"2025072103522342900_ocaf070-B26","doi-asserted-by":"crossref","first-page":"51","DOI":"10.4103\/AJIM.AJIM_80_19","article-title":"Are periodic health checkups useful or necessary?","volume":"8","author":"Kamath","year":"2020","journal-title":"APIK J Int Med"},{"key":"2025072103522342900_ocaf070-B27","doi-asserted-by":"crossref","first-page":"E28","DOI":"10.5888\/pcd21.240110","article-title":"Peer reviewed: chronic disease mapping, an important strategy and tool for health promotion","volume":"21","author":"Hacker","year":"2024","journal-title":"Prev Chronic Dis"},{"key":"2025072103522342900_ocaf070-B28","first-page":"49","author":"Johnson","year":"2020"},{"key":"2025072103522342900_ocaf070-B29","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1038\/s41597-023-02136-9","article-title":"Mimic-iv, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"2025072103522342900_ocaf070-B30","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1016\/S0140-6736(05)67402-8","article-title":"The metabolic syndrome\u2014a new worldwide definition","volume":"366","author":"Alberti","year":"2005","journal-title":"Lancet (London, England)"},{"key":"2025072103522342900_ocaf070-B31","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s40537-020-00316-7","article-title":"Multi-layered deep learning perceptron approach for health risk prediction","volume":"7","author":"Bikku","year":"2020","journal-title":"J Big Data"},{"key":"2025072103522342900_ocaf070-B32","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s12911-021-01403-2","article-title":"Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making","volume":"21","author":"Brnabic","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"2025072103522342900_ocaf070-B33","author":"Zhang","year":"2024"},{"key":"2025072103522342900_ocaf070-B34","first-page":"15920","article-title":"Dark experience for general continual learning: a strong, simple baseline","volume":"33","author":"Buzzega","year":"2020","journal-title":"Adv Neu Inform Process Syst"},{"key":"2025072103522342900_ocaf070-B35","author":"Chaudhry"},{"key":"2025072103522342900_ocaf070-B36","first-page":"3987","author":"Zenke","year":"2017"},{"key":"2025072103522342900_ocaf070-B37","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1186\/s12877-022-03672-6","article-title":"Trends and influence factors in the prevalence, intervention, and control of metabolic syndrome among us adults, 1999\u20132018","volume":"22","author":"Yang","year":"2022","journal-title":"BMC Geriatr"},{"key":"2025072103522342900_ocaf070-B38","first-page":"1","article-title":"Prevalence of metabolic syndrome in mainland China: a meta-analysis of published studies","volume":"16","author":"Ri","year":"2016","journal-title":"BMC Public Health"},{"key":"2025072103522342900_ocaf070-B39","first-page":"15","volume-title":"Metabolic Syndrome: A Comprehensive Textbook","author":"Albert Danso","year":"2024"},{"key":"2025072103522342900_ocaf070-B40","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"2025072103522342900_ocaf070-B41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-017-0110-7","article-title":"Big healthcare data: preserving security and privacy","volume":"5","author":"Abouelmehdi","year":"2018","journal-title":"J Big Data"},{"key":"2025072103522342900_ocaf070-B42","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1001\/virtualmentor.2012.14.9.stas1-1209","article-title":"Electronic health records: privacy, confidentiality, and security","volume":"14","author":"Harman","year":"2012","journal-title":"AMA J Ethics"},{"key":"2025072103522342900_ocaf070-B43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12913-019-4815-5","article-title":"Access to specialty healthcare in urban versus rural US populations: a systematic literature review","volume":"19","author":"Cyr","year":"2019","journal-title":"BMC Health Serv Res"},{"key":"2025072103522342900_ocaf070-B44","doi-asserted-by":"crossref","first-page":"737039","DOI":"10.3389\/fmolb.2021.737039","article-title":"Metabolic and lipidomic markers differentiate Covid-19 from non-hospitalized and other intensive care patients","volume":"8","author":"Schmelter","year":"2021","journal-title":"Front Mol Biosci"},{"key":"2025072103522342900_ocaf070-B45","doi-asserted-by":"crossref","first-page":"102861","DOI":"10.1016\/j.artmed.2024.102861","article-title":"Challenges and strategies for wide-scale artificial intelligence (AI) deployment in healthcare practices: a perspective for healthcare organizations","volume":"151","author":"Esmaeilzadeh","year":"2024","journal-title":"Artif Intell Med"},{"key":"2025072103522342900_ocaf070-B46","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","article-title":"Catastrophic forgetting in connectionist networks","volume":"3","author":"French","year":"1999","journal-title":"Trends Cogn Sci"},{"key":"2025072103522342900_ocaf070-B47","first-page":"109","volume-title":"Psychology of Learning and Motivation","author":"McCloskey","year":"1989"},{"key":"2025072103522342900_ocaf070-B48","author":"Kotha","year":"2024"},{"key":"2025072103522342900_ocaf070-B49","author":"Luo","year":"2023"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/8\/1310\/63470553\/ocaf070.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/8\/1310\/63470553\/ocaf070.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T07:52:35Z","timestamp":1753084355000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/8\/1310\/8160363"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":49,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6,11]]},"published-print":{"date-parts":[[2025,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf070","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,8]]},"published":{"date-parts":[[2025,6,11]]}}}