{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:16:21Z","timestamp":1765228581569,"version":"3.46.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Korea-US Collaborative Research Fund"},{"DOI":"10.13039\/501100002647","name":"Ministry of Science and ICT and the Ministry of Health and Welfare, Republic of Korea","doi-asserted-by":"publisher","award":["RS-2024-00468417"],"award-info":[{"award-number":["RS-2024-00468417"]}],"id":[{"id":"10.13039\/501100002647","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3638417","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:00Z","timestamp":1764355440000},"page":"203145-203157","source":"Crossref","is-referenced-by-count":0,"title":["A Reinforcement Learning Framework for Personalized Anticoagulation Dosing in Critical Care: Integrating Batch-Constrained Policy Optimization and Off-Policy Evaluation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5962-5085","authenticated-orcid":false,"given":"Yooseok","family":"Lim","sequence":"first","affiliation":[{"name":"Office of Hospital Information, Seoul National University Hospital, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8890-7381","authenticated-orcid":false,"given":"In-Beom","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, Dongguk University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1060-2067","authenticated-orcid":false,"given":"Sujee","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Systems Management Engineering, Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrdp.2015.6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(98)10266-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00421226"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199105303242206"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4081\/cp.2017.953"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9149(97)00309-3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11051338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76547-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/pds.3595"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107689"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8513203"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3027443"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/ijds.2022.0015"},{"key":"ref15","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref16","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref17","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2022.100016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0579.2007.00477.x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/cts.12884"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1136\/svn-2017-000101"},{"key":"ref22","article-title":"Model-based reinforcement learning for sepsis treatment","author":"Raghu","year":"2018","journal-title":"arXiv:1811.09602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2019.8904645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-014-3406-5"},{"key":"ref25","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"},{"key":"ref26","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref27","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref28","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref29","article-title":"An empirical study of representation learning for reinforcement learning in healthcare","author":"Killian","year":"2020","journal-title":"arXiv:2011.11235"},{"key":"ref30","first-page":"119","article-title":"Semi-Markov offline reinforcement learning for healthcare","volume-title":"Proc. Conf. Health","author":"Fatemi"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599800"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3369636"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"issue":"12","key":"ref36","first-page":"1080","article-title":"ACC\/AHA guideline update for the management of ST-segment elevation myocardial infarction","volume":"79","author":"Campbell-Scherer","year":"2009","journal-title":"Amer. Family Physician"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11239-015-1315-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.4103\/aca.aca_117_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2016-11-709873"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/08998280.2001.11927781"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"ref42","article-title":"Anticoagulation safety","volume-title":"StatPearls [Internet]","author":"Amaraneni","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-119-9-199311010-00002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1160\/TH06-05-0290"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"volume-title":"Approximate Solutions to Markov Decision Processes","year":"1999","author":"Gordon","key":"ref46"},{"key":"ref47","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref48","first-page":"3014","article-title":"Weighted importance sampling for off-policy learning with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Mahmood"},{"issue":"86","key":"ref49","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","first-page":"2","article-title":"Model selection for offline reinforcement learning: Practical considerations for healthcare settings","volume-title":"Proc. Mach. Learn. Healthcare Conf.","volume":"149","author":"Tang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107784"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/ajh.25565"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199801000-00004"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11271244.pdf?arnumber=11271244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:59Z","timestamp":1765219319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3638417","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}