{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:53:44Z","timestamp":1783526024833,"version":"3.55.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2129097"],"award-info":[{"award-number":["2129097"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/jbhi.2024.3377214","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T17:59:48Z","timestamp":1710439188000},"page":"3114-3122","source":"Crossref","is-referenced-by-count":11,"title":["Reinforced Sequential Decision-Making for Sepsis Treatment: The PosNegDM Framework With Mortality Classifier and Transformer"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2765-5763","authenticated-orcid":false,"given":"Dipesh","family":"Tamboli","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7708-5247","authenticated-orcid":false,"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3004-7726","authenticated-orcid":false,"given":"Kiran Pranesh","family":"Jotheeswaran","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5083-1713","authenticated-orcid":false,"given":"Denny","family":"Yu","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9131-4723","authenticated-orcid":false,"given":"Vaneet","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3952","article-title":"Invariant causal imitation learning for generalizable policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bica","year":"2021"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref3","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC49870.2020.9289148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-021-06506-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-020-06151-x"},{"key":"ref7","year":"2023","journal-title":"Centers for Disease Control Prevention"},{"key":"ref8","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu","year":"2018"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"ref11","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref14","article-title":"A conservative Q-learning approach for handling distribution shift in sepsis treatment strategies","author":"Kaushik","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15644-1_2"},{"key":"ref18","article-title":"Improving sepsis treatment strategies by combining deep and kernel-based reinforcement learning","volume-title":"Proc. AMIA Annu. Symp.","author":"Peng","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref20","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: A deep reinforcement learning approach","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Raghu","year":"2017"},{"key":"ref21","article-title":"Model-based reinforcement learning for sepsis treatment","author":"Raghu","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105860"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21037\/tp-20-310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000005430"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4271\/12-04-03-0023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50055-3"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193494"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0217541"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380248"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20627-6_11"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6221020\/10521573\/10472521-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221020\/10521573\/10472521.pdf?arnumber=10472521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T20:22:15Z","timestamp":1743798135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":32,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2024.3377214","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}