{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T04:41:12Z","timestamp":1773549672091,"version":"3.50.1"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2022,5,31]],"date-time":"2022-05-31T00:00:00Z","timestamp":1653955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["U2COD023196"],"award-info":[{"award-number":["U2COD023196"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["UL1TR002243"],"award-info":[{"award-number":["UL1TR002243"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Deep learning models for clinical event forecasting (CEF) based on a patient\u2019s medical history have improved significantly over the past decade. However, their transition into practice has been limited, particularly for diseases with very low prevalence. In this paper, we introduce CEF-CL, a novel method based on contrastive learning to forecast in the face of a limited number of positive training instances.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>CEF-CL consists of two primary components: (1) unsupervised contrastive learning for patient representation and (2) supervised transfer learning over the derived representation. We evaluate the new method along with state-of-the-art model architectures trained in a supervised manner with electronic health records data from Vanderbilt University Medical Center and the All of Us Research Program, covering 48\u00a0000 and 16\u00a0000 patients, respectively. We assess forecasting for over 100 diagnosis codes with respect to their area under the receiver operator characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). We investigate the correlation between forecasting performance improvement and code prevalence via a Wald Test.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>CEF-CL achieved an average AUROC and AUPRC performance improvement over the state-of-the-art of 8.0%\u20139.3% and 11.7%\u201332.0%, respectively. The improvement in AUROC was negatively correlated with the number of positive training instances (P\u2009&amp;lt;\u2009.001).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>This investigation indicates that clinical event forecasting can be improved significantly through contrastive representation learning, especially when the number of positive training instances is small.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocac086","type":"journal-article","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T01:05:28Z","timestamp":1654045528000},"page":"1584-1592","source":"Crossref","is-referenced-by-count":9,"title":["Forecasting the future clinical events of a patient through contrastive learning"],"prefix":"10.1093","volume":"29","author":[{"given":"Ziqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Vanderbilt University , Nashville, Tennessee, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6719-1388","authenticated-orcid":false,"given":"Chao","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, Tennessee, USA"}]},{"given":"Xinmeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Vanderbilt University , Nashville, Tennessee, USA"}]},{"given":"Steve L","family":"Nyemba","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, Tennessee, USA"}]},{"given":"Bradley A","family":"Malin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Vanderbilt University , Nashville, Tennessee, USA"},{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, Tennessee, USA"},{"name":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, Tennessee, USA"}]}],"member":"286","published-online":{"date-parts":[[2022,5,31]]},"reference":[{"issue":"10","key":"2022081707582283800_ocac086-B1","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1093\/jamia\/ocy068","article-title":"Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review","volume":"25","author":"Xiao","year":"2018","journal-title":"J Am Med Inform Assoc"},{"issue":"141","key":"2022081707582283800_ocac086-B2","doi-asserted-by":"crossref","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J R Soc Interface"},{"issue":"3","key":"2022081707582283800_ocac086-B3","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1001\/jamainternmed.2018.7117","article-title":"Deep learning in medicine\u2014promise, progress, and challenges","volume":"179","author":"Wang","year":"2019","journal-title":"JAMA Intern Med"},{"key":"2022081707582283800_ocac086-B4","first-page":"301","article-title":"Doctor AI: predicting clinical events via recurrent neural networks","volume":"56","author":"Choi","year":"2016","journal-title":"J Mach Learn Res Workshop Conf Proc"},{"issue":"1","key":"2022081707582283800_ocac086-B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep26094","article-title":"Deep patient: an unsupervised representation to predict the future of patients from the electronic health records","volume":"6","author":"Miotto","year":"2016","journal-title":"Sci Rep"},{"key":"2022081707582283800_ocac086-B6","first-page":"30","author":"Pham","year":"2016"},{"key":"2022081707582283800_ocac086-B7","first-page":"432","author":"Cheng","year":"2016"},{"key":"2022081707582283800_ocac086-B8","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.jbi.2017.04.001","article-title":"Predicting healthcare trajectories from medical records: a deep learning approach","volume":"69","author":"Pham","year":"2017","journal-title":"J Biomed Inform"},{"key":"2022081707582283800_ocac086-B9","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behav Brain Sci"},{"key":"2022081707582283800_ocac086-B10","first-page":"191","article-title":"A review of challenges and opportunities in machine learning for health","volume":"2020","author":"Ghassemi","year":"2020","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"issue":"11","key":"2022081707582283800_ocac086-B11","doi-asserted-by":"crossref","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","article-title":"Self-supervised visual feature learning with deep neural networks: a survey","volume":"43","author":"Jing","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"2022081707582283800_ocac086-B12","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2022081707582283800_ocac086-B13","doi-asserted-by":"crossref","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","article-title":"Contrastive representation learning: a framework and review","volume":"8","author":"Le-Khac","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"2022081707582283800_ocac086-B14","doi-asserted-by":"crossref","first-page":"2","DOI":"10.3390\/technologies9010002","article-title":"A survey on contrastive self-supervised learning","volume":"9","author":"Jaiswal","year":"2020","journal-title":"Technologies (Basel)"},{"key":"2022081707582283800_ocac086-B15","author":"Li","year":"2021"},{"key":"2022081707582283800_ocac086-B16","author":"Kim","year":"2020"},{"key":"2022081707582283800_ocac086-B17","first-page":"5342","author":"O\u2019Neill","year":"2018"},{"key":"2022081707582283800_ocac086-B18","author":"Liang"},{"issue":"1","key":"2022081707582283800_ocac086-B19","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1038\/clpt.2011.371","article-title":"Operational implementation of prospective genotyping for personalized medicine: the design of the Vanderbilt PREDICT project","volume":"92","author":"Pulley","year":"2012","journal-title":"Clin Pharmacol Ther"},{"issue":"7","key":"2022081707582283800_ocac086-B20","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1056\/NEJMsr1809937","article-title":"The \u201cAll of Us\u201d research program","volume":"381","year":"2019","journal-title":"N Engl J Med"},{"issue":"3","key":"2022081707582283800_ocac086-B21","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1038\/clpt.2008.89","article-title":"Development of a large-scale de-identified DNA biobank to enable personalized medicine","volume":"84","author":"Roden","year":"2008","journal-title":"Clin Pharmacol Ther"},{"issue":"3","key":"2022081707582283800_ocac086-B22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3386252","article-title":"Generalizing from a few examples: a survey on few-shot learning","volume":"53","author":"Wang","year":"2021","journal-title":"ACM Comput Surv"},{"key":"2022081707582283800_ocac086-B23","first-page":"532","article-title":"Few-shot learning for dermatological disease diagnosis","volume":"105","author":"Prabhu","year":"2019","journal-title":"Proc Mach Learn Res"},{"key":"2022081707582283800_ocac086-B24","author":"Simonyan","year":"2015"},{"key":"2022081707582283800_ocac086-B25","first-page":"1","author":"Szegedy","year":"2015"},{"key":"2022081707582283800_ocac086-B26","first-page":"770","author":"He","year":"2016"},{"key":"2022081707582283800_ocac086-B27","first-page":"2377","author":"Srivastava","year":"2015"},{"issue":"01","key":"2022081707582283800_ocac086-B28","first-page":"614","article-title":"CONAN: complementary pattern augmentation for rare disease detection","volume":"34","author":"Cui","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2022081707582283800_ocac086-B29","first-page":"3504","author":"Choi","year":"2015"},{"key":"2022081707582283800_ocac086-B30","first-page":"1753","author":"Ye","year":"2020"},{"key":"2022081707582283800_ocac086-B31","first-page":"1903","author":"Ma","year":"2017"},{"issue":"3","key":"2022081707582283800_ocac086-B32","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun ACM"},{"key":"2022081707582283800_ocac086-B33","first-page":"1050","author":"Gal","year":"2016"},{"key":"2022081707582283800_ocac086-B34","author":"Szegedy","year":"2014"},{"issue":"1","key":"2022081707582283800_ocac086-B35","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach Learn"},{"key":"2022081707582283800_ocac086-B36","first-page":"4552","author":"Choi","year":"2018"},{"issue":"01","key":"2022081707582283800_ocac086-B37","first-page":"1069","article-title":"Affinitynet: semi-supervised few-shot learning for disease type prediction","volume":"33","author":"Ma","year":"2019","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2022081707582283800_ocac086-B38","first-page":"5628","author":"Saunshi","year":"2019"},{"key":"2022081707582283800_ocac086-B39","first-page":"879","author":"Giorgi"},{"key":"2022081707582283800_ocac086-B40","first-page":"1597","author":"Chen","year":"2020"},{"key":"2022081707582283800_ocac086-B41","author":"Oord","year":"2018"},{"issue":"10","key":"2022081707582283800_ocac086-B42","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"2","key":"2022081707582283800_ocac086-B43","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1038\/clpt.2012.66","article-title":"Optimizing drug outcomes through pharmacogenetics: a case for preemptive genotyping","volume":"92","author":"Schildcrout","year":"2012","journal-title":"Clin Pharmacol Ther"},{"key":"2022081707582283800_ocac086-B44","first-page":"5998","author":"Vaswani","year":"2017"},{"issue":"8","key":"2022081707582283800_ocac086-B45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"issue":"3","key":"2022081707582283800_ocac086-B46","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1093\/jamia\/ocaa262","article-title":"SynTEG: a framework for temporal structured electronic health data simulation","volume":"28","author":"Zhang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"2022081707582283800_ocac086-B47","first-page":"4293","author":"Li"},{"key":"2022081707582283800_ocac086-B48","first-page":"313","author":"Russin"},{"key":"2022081707582283800_ocac086-B49","first-page":"92","author":"Blum","year":"1998"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/9\/1584\/45444557\/ocac086.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/29\/9\/1584\/45444557\/ocac086.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T07:59:42Z","timestamp":1660723182000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/29\/9\/1584\/6596177"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,31]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5,31]]},"published-print":{"date-parts":[[2022,8,16]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocac086","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,9,1]]},"published":{"date-parts":[[2022,5,31]]}}}