{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:32:10Z","timestamp":1792081930815,"version":"4.4.0"},"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["23K15152"],"award-info":[{"award-number":["23K15152"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Ischemic heart disease is a leading cause of death worldwide, and its importance is increasing with the aging population. The aim of this study was to evaluate the accuracy of SurvTrace, a survival analysis model using the Transformer\u2014a state-of-the-art deep learning method\u2014for predicting recurrent cardiovascular events and stratifying high-risk patients. The model\u2019s performance was compared to that of a conventional scoring system utilizing real-world data from cardiovascular patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study consecutively enrolled patients who underwent percutaneous coronary intervention (PCI) at the Department of Cardiovascular Medicine, University of Tokyo Hospital, between 2005 and 2019. Each patient\u2019s initial PCI at our hospital was designated as the index procedure, and a composite of major adverse cardiovascular events (MACE) was monitored for up to two years post-index event. Data regarding patient background, clinical presentation, medical history, medications, and perioperative complications were collected to predict MACE. The performance of two models\u2014a conventional scoring system proposed by Wilson et al. and the Transformer-based model SurvTrace\u2014was evaluated using Harrell\u2019s c-index, Kaplan\u2013Meier curves, and log-rank tests.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 3938 cases were included in the study, with 394 used as the test dataset and the remaining 3544 used for model training. SurvTrace exhibited a mean c-index of 0.72 (95% confidence intervals (CI): 0.69\u20130.76), which indicated higher prognostic accuracy compared with the conventional scoring system\u2019s 0.64 (95% CI: 0.64\u20130.64). Moreover, SurvTrace demonstrated superior risk stratification ability, effectively distinguishing between the high-risk group and other risk categories in terms of event occurrence. In contrast, the conventional system only showed a significant difference between the low-risk and high-risk groups.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study based on real-world cardiovascular patient data underscores the potential of the Transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0304423","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T13:27:19Z","timestamp":1718717239000},"page":"e0304423","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["The potential of the transformer-based survival analysis model, SurvTrace, for predicting recurrent cardiovascular events and stratifying high-risk patients with ischemic heart disease"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-8244","authenticated-orcid":true,"given":"Hiroki","family":"Shinohara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2908-6875","authenticated-orcid":true,"given":"Satoshi","family":"Kodera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0458-0781","authenticated-orcid":true,"given":"Yugo","family":"Nagae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4873-9029","authenticated-orcid":true,"given":"Takashi","family":"Hiruma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masataka","family":"Sato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinnosuke","family":"Sawano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Kamon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koichi","family":"Narita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazutoshi","family":"Hirose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Kiriyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akihito","family":"Saito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3252-3861","authenticated-orcid":true,"given":"Mizuki","family":"Miura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Minatsuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1324-6424","authenticated-orcid":true,"given":"Hironobu","family":"Kikuchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4818-3347","authenticated-orcid":true,"given":"Norifumi","family":"Takeda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-9607","authenticated-orcid":true,"given":"Hiroshi","family":"Akazawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Morita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Issei","family":"Komuro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"pone.0304423.ref001","article-title":"Causes of Death.","author":"H Ritchie","year":"2018","journal-title":"Publ Online OurWorldInDataOrg"},{"key":"pone.0304423.ref002","first-page":"135","article-title":"Heart Disease and Stroke Statistics\u20142017 Update: A Report From the American Heart Association","author":"EJ Benjamin","year":"2017","journal-title":"Circulation"},{"key":"pone.0304423.ref003","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.5551\/jat.Er19356","article-title":"Predicting Coronary Heart Disease Using Risk Factor Categories for a Japanese Urban Population, and Comparison with the Framingham Risk Score: The Suita Study","volume":"23","author":"K Nishimura","year":"2016","journal-title":"J Atheroscler Thromb"},{"key":"pone.0304423.ref004","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1016\/j.amjmed.2012.01.014","article-title":"An International Model to Predict Recurrent Cardiovascular Disease","volume":"125","author":"PWF Wilson","year":"2012","journal-title":"Am J Med"},{"key":"pone.0304423.ref005","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1007\/s00467-021-05321-3","article-title":"Posterior Urethral Valves Outcomes Prediction (PUVOP): a machine learning tool to predict clinically relevant outcomes in boys with posterior urethral valves.","volume":"37","author":"JC Kwong","year":"2022","journal-title":"Pediatr Nephrol"},{"key":"pone.0304423.ref006","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.gastha.2021.09.003","article-title":"Machine Learning\u2013Based Personalized Prediction of Hepatocellular Carcinoma Recurrence After Radiofrequency Ablation.","volume":"1","author":"M Sato","year":"2022","journal-title":"Gastro Hep Adv"},{"key":"pone.0304423.ref007","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1186\/s12885-022-09217-9","article-title":"Deep-learning model for predicting the survival of rectal adenocarcinoma patients based on a surveillance, epidemiology, and end results analysis","volume":"22","author":"H Yu","year":"2022","journal-title":"BMC Cancer"},{"key":"pone.0304423.ref008","volume-title":"Proc. 13th ACM Int. Conf. Bioinformatics, Comput. Biol. Heal. Informatics","author":"Z Wang","year":"2022"},{"key":"pone.0304423.ref009","volume-title":"Adv. Neural Inf. Process","author":"A Vaswani","year":"2017"},{"key":"pone.0304423.ref010","first-page":"9","article-title":"Language Models are Unsupervised Multitask Learners, 2019.","volume":"1.8","author":"A Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"pone.0304423.ref011","first-page":"1877","volume-title":"Adv. Neural Inf. Process. Syst","author":"T Brown","year":"2020"},{"key":"pone.0304423.ref012","first-page":"155A","article-title":"A simplified equation to predict glomerular filtration rate from serum creatinine","volume":"11","author":"AS Levey","year":"2000","journal-title":"J Am Soc Nephrol"},{"key":"pone.0304423.ref013","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1016\/j.cjca.2020.11.010","article-title":"Missing Data in Clinical Research: A Tutorial on Multiple Imputation","volume":"37","author":"PC Austin","year":"2021","journal-title":"Can J Cardiol"},{"key":"pone.0304423.ref014","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0140-6736(22)02079-7","article-title":"Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts","volume":"401","author":"IS Forrest","year":"2023","journal-title":"Lancet"},{"key":"pone.0304423.ref015","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1016\/j.jacc.2018.08.1038","article-title":"Fourth Universal Definition of Myocardial Infarction (2018).","volume":"72","author":"K Thygesen","year":"2018","journal-title":"J Am Coll Cardiol"},{"key":"pone.0304423.ref016","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1056\/NEJMoa1915922","article-title":"Initial Invasive or Conservative Strategy for Stable Coronary Disease","volume":"382","author":"DJ Maron","year":"2020","journal-title":"N Engl J Med"},{"key":"pone.0304423.ref017","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1001\/jama.1982.03320430047030","article-title":"Evaluating the yield of medical tests","volume":"247","author":"FE Harrell","year":"1982","journal-title":"JAMA"},{"key":"pone.0304423.ref018","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1093\/ehjdh\/ztab093","article-title":"Can machine learning bring cardiovascular risk assessment to the next level? A methodological study using FOURIER trial data","volume":"3","author":"A Rousset","year":"2022","journal-title":"Eur Hear J\u2014Digit Heal"},{"key":"pone.0304423.ref019","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric Estimation from Incomplete Observations","volume":"53","author":"EL Kaplan","year":"1958","journal-title":"J Am Stat Assoc"},{"key":"pone.0304423.ref020","first-page":"163","article-title":"Evaluation of survival data and two new rank order statistics arising in its consideration","volume":"50","author":"N. Mantel","year":"1966","journal-title":"Cancer Chemother Reports"},{"key":"pone.0304423.ref021","volume-title":"Adv. Neural Inf. Process. Syst.,","author":"SM Lundberg","year":"2017"},{"key":"pone.0304423.ref022","first-page":"1907","author":"T Akiba","year":"2019","journal-title":"Optuna: A Next-generation Hyperparameter Optimization Framework"},{"key":"pone.0304423.ref023","first-page":"12","volume-title":"Multiple imputation for missing data: Concepts and new development (Version 9.0).","author":"YC Yuan","year":"2010"},{"key":"pone.0304423.ref024","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/j.jcmg.2022.12.008","article-title":"Machine Learning to Optimize the Echocardiographic Follow-Up of Aortic Stenosis.","volume":"16","author":"A S\u00e1nchez-Puente","year":"2023","journal-title":"JACC Cardiovasc Imaging"},{"key":"pone.0304423.ref025","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records.","volume":"5","author":"X Yang","year":"2022","journal-title":"Npj Digit Med"},{"key":"pone.0304423.ref026","article-title":"Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models","author":"A Bisercic","year":"2023","journal-title":"arXiv:2306.05052v1 [Preprint]."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0304423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T13:27:37Z","timestamp":1718717257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0304423"}},"subtitle":[],"editor":[{"given":"Marcelo Arruda","family":"Nakazone","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":26,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0304423","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,18]]}}}