{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T07:26:07Z","timestamp":1795245967996,"version":"4.10.3"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T00:00:00Z","timestamp":1707782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Deep-learning techniques, particularly the Transformer model, have shown great potential in enhancing the prediction performance of longitudinal health records. Previous methods focused on fixed-time risk prediction, however, time-to-event prediction is often more appropriate for clinical scenarios. Here, we present STRAFE, a generalizable survival analysis Transformer-based architecture for electronic health records.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>The input for STRAFE is a sequence of visits with SNOMED-CT codes in OMOP-CDM format. A Transformer-based architecture was developed to calculate probabilities of the occurrence of the event in each of 48 months. Performance was evaluated using a real-world claims dataset of over 130\u00a0000 individuals with stage 3 chronic kidney disease (CKD).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>STRAFE showed improved mean absolute error (MAE) compared to other time-to-event algorithms in predicting the time to deterioration to stage 5 CKD. Additionally, STRAFE showed an improved area under the receiver operating curve compared to binary outcome algorithms. We show that STRAFE predictions can improve the positive predictive value of high-risk patients by 3-fold. Finally, we suggest a novel visualization approach to predictions on a per-patient basis.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Time-to-event predictions are the most appropriate approach for clinical predictions. Our deep-learning algorithm outperformed not only other time-to-event prediction algorithms but also fixed-time algorithms, possibly due to its ability to train on censored data. We demonstrated possible clinical usage by identifying the highest-risk patients.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>The ability to accurately identify patients at high risk and prioritize their needs can result in improved health outcomes, reduced costs, and more efficient use of resources.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae025","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:03:47Z","timestamp":1707847427000},"page":"980-990","source":"Crossref","is-referenced-by-count":21,"title":["Transformer-based time-to-event prediction for chronic kidney disease deterioration"],"prefix":"10.1093","volume":"31","author":[{"given":"Moshe","family":"Zisser","sequence":"first","affiliation":[{"name":"Faculty of Data and Decision Sciences, Technion-Israel Institute of Technology , Haifa, 3200003, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dvir","family":"Aran","sequence":"additional","affiliation":[{"name":"Faculty of Biology, Technion-Israel Institute of Technology , Haifa, 3200003, Israel"},{"name":"The Taub Faculty of Computer Science, Technion-Israel Institute of Technology , Haifa, 3200003, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,2,13]]},"reference":[{"issue":"1","key":"2024040320011900900_ocae025-B1","first-page":"11","article-title":"Policy implications of big data in the health sector","volume":"96","author":"Vayena","year":"2017","journal-title":"Bulletin of the World Health Organisation"},{"issue":"1","key":"2024040320011900900_ocae025-B2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/2047-2501-2-3","article-title":"Big data analytics in healthcare: promise and potential","volume":"2","author":"Raghupathi","year":"2014","journal-title":"Health Inf. Sci. Syst"},{"key":"2024040320011900900_ocae025-B3","author":"Vaswani","year":"2017"},{"key":"2024040320011900900_ocae025-B4","author":"Moerschbacher","year":"2021"},{"key":"2024040320011900900_ocae025-B5","first-page":"31","author":"Zeng","year":"2022"},{"key":"2024040320011900900_ocae025-B6","author":"Rao","year":"2021"},{"key":"2024040320011900900_ocae025-B7","author":"Kodialam","year":"2020"},{"key":"2024040320011900900_ocae025-B8","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.chemolab.2016.03.004","article-title":"Diagnosis of patients with chronic kidney disease by using two fuzzy classifiers","volume":"153","author":"Chen","year":"2016","journal-title":"Chemom Intell Lab Syst"},{"key":"2024040320011900900_ocae025-B9","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1007\/978-981-10-4166-2_89","volume-title":"Cmbebih 2017","author":"Subasi","year":"2017"},{"issue":"12","key":"2024040320011900900_ocae025-B10","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.1007\/s11255-016-1346-4","article-title":"Clinical risk assessment of patients with chronic kidney disease by using clinical data and multivariate models","volume":"48","author":"Chen","year":"2016","journal-title":"Int Urol Nephrol"},{"key":"2024040320011900900_ocae025-B11","author":"Dutta","year":"2020"},{"issue":"1","key":"2024040320011900900_ocae025-B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00779-020-01492-2","article-title":"Synergic deep learning model\u2013based automated detection and classification of brain intracranial hemorrhage images in wearable networks","volume":"26","author":"Anupama","year":"2020","journal-title":"Pers Ubiquitous Comput"},{"issue":"47-48","key":"2024040320011900900_ocae025-B13","doi-asserted-by":"crossref","first-page":"35425","DOI":"10.1007\/s11042-019-07839-z","article-title":"Kdsae: chronic kidney disease classification with multimedia data learning using deep stacked autoencoder network","volume":"79","author":"Khamparia","year":"2020","journal-title":"Multimed Tools Appl"},{"key":"2024040320011900900_ocae025-B14","author":"Wang","year":"2020"},{"issue":"2","key":"2024040320011900900_ocae025-B15","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/BF00941622","article-title":"Charting the process of change: a primer on survival analysis","volume":"21","author":"Luke","year":"1993","journal-title":"Am J Community Psychol"},{"key":"2024040320011900900_ocae025-B16","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/978-3-030-01424-7_3","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"Giunchiglia","year":"2018"},{"issue":"1","key":"2024040320011900900_ocae025-B17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11842","article-title":"Deephit: a deep learning approach to survival analysis with competing risks","volume":"32","author":"Lee","year":"2018","journal-title":"AAAI"},{"key":"2024040320011900900_ocae025-B18","author":"Ren","year":"2018"},{"key":"2024040320011900900_ocae025-B19","author":"Huang"},{"key":"2024040320011900900_ocae025-B20","first-page":"132","author":"Hu"},{"issue":"3","key":"2024040320011900900_ocae025-B21","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann Appl Stat"},{"issue":"8","key":"2024040320011900900_ocae025-B22","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":"4","key":"2024040320011900900_ocae025-B23","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1093\/biomet\/92.4.965","article-title":"Concordance probability and discriminatory power in proportional hazards regression","volume":"92","author":"G\u00f6nen","year":"2005","journal-title":"Biometrika"},{"key":"2024040320011900900_ocae025-B24","author":"Mikolov","year":"2013"},{"issue":"282","key":"2024040320011900900_ocae025-B25","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric estimation from incomplete observations","volume":"53","author":"Kaplan","year":"1958","journal-title":"J Am Stat Assoc"},{"key":"2024040320011900900_ocae025-B26","volume-title":"The Book of OHDSI: Observational Health Data Sciences and Informatics","author":"OHDSI","year":"2019"},{"key":"2024040320011900900_ocae025-B27","article-title":"Gensim\u2013python framework for vector space modelling","volume-title":"NLP Centre, Faculty of Informatics, Masaryk University, Brno, Czech Republic","author":"Rehurek","year":"2011"},{"key":"2024040320011900900_ocae025-B28","author":"Kingma","year":"2014"},{"issue":"212","key":"2024040320011900900_ocae025-B29","first-page":"1","article-title":"scikit-survival: a library for time-to-event analysis built on top of scikit-learn","volume":"21","author":"P\u00f6lsterl","year":"2020","journal-title":"J Mach Learn Res"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/4\/980\/57148436\/ocae025.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/4\/980\/57148436\/ocae025.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T20:01:45Z","timestamp":1712174505000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/4\/980\/7607207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,13]]},"references-count":29,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2,13]]},"published-print":{"date-parts":[[2024,4,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae025","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,2,13]]}}}