{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:18:40Z","timestamp":1783455520929,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/jbhi.2025.3647877","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:46:43Z","timestamp":1766602003000},"page":"5692-5705","source":"Crossref","is-referenced-by-count":1,"title":["Tailored to Fit Sepsis Individuals: Medical Knowledge Aware Reinforcement Learning Model Offers Optimized Therapeutic Strategies"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3758-421X","authenticated-orcid":false,"given":"Xue","family":"Feng","sequence":"first","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2905-6104","authenticated-orcid":false,"given":"Siyi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7752-4839","authenticated-orcid":false,"given":"Luping","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2718-595X","authenticated-orcid":false,"given":"Huaiping","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, York University, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0056-663X","authenticated-orcid":false,"given":"Guolong","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Intensive Care Unit, Zhejiang Hospital, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6752-2829","authenticated-orcid":false,"given":"Yanfei","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Intensive Care Unit, Zhejiang Hospital, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9107-5785","authenticated-orcid":false,"given":"Gangmin","family":"Ning","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.100l\/jama.2016.0287"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0289"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0288"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)32989-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000005337"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41581-018-0005-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-022-04071-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-018-2279-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04507-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0885066619871452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocz106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00755-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0253-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0310-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-019-05872-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2196\/15182"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18031117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2196\/18477"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13184624"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2196\/28781"},{"key":"ref23","article-title":"A reinforcement learning approach to weaning of mechanical ventilation in intensive care units","volume-title":"Proc. 33rd Conf. Uncertainty Artif. Intell.","author":"Prasad","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00388-6"},{"key":"ref25","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: A deep reinforcement learning approach","volume-title":"Proc. 2nd Mach. Learn. Healthcare Conf.","author":"Raghu","year":"2017"},{"key":"ref26","article-title":"Deep reinforcement learning for sepsis treatment","author":"Raghu","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1159\/000492670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref30","first-page":"3512","article-title":"RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst.","author":"Choi","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102901"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00084"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098126"},{"key":"ref34","first-page":"4552","article-title":"Mime: Multilevel medical embedding of electronic health records for predictive healthcare","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Choi","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271701"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000005191"},{"key":"ref37","article-title":"Clinical classifications software (CCS) for ICD-9-CM","year":"2010"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0175508"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref42","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483478"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref45","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00529-x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.03.018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.04.007"},{"key":"ref50","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Thomas","year":"2016"},{"key":"ref51","first-page":"1447","article-title":"More robust doubly robust off-policy evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Farajtabar","year":"2018"},{"key":"ref52","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang","year":"2016"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11595905\/11314698.pdf?arnumber=11314698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:41Z","timestamp":1783453541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3647877","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}