{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T11:41:24Z","timestamp":1790509284851,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"S2","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1186\/s12911-019-0763-6","type":"journal-article","created":{"date-parts":[[2019,4,8]],"date-time":"2019-04-08T20:05:34Z","timestamp":1554753934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Inverse reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units"],"prefix":"10.1186","volume":"19","author":[{"given":"Chao","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,9]]},"reference":[{"key":"763_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG. Reinforcement Learning: An Introduction. Cambridge: The MIT press; 1998."},{"key":"763_CR2","first-page":"239","volume":"2017","author":"S Parbhoo","year":"2017","unstructured":"Parbhoo S, Bogojeska J, Zazzi M, Roth V, Doshi-Velez F. Combining kernel and model based learning for hiv therapy selection. AMIA Summits Transl Sci Proc. 2017; 2017:239.","journal-title":"AMIA Summits Transl Sci Proc"},{"issue":"12","key":"763_CR3","doi-asserted-by":"publisher","first-page":"6690","DOI":"10.1002\/mp.12625","volume":"44","author":"H-H Tseng","year":"2017","unstructured":"Tseng H-H, Luo Y, Cui S, Chien J-T, Ten Haken RK, Naqa IE. Deep reinforcement learning for automated radiation adaptation in lung cancer. Med Phys. 2017; 44(12):6690\u2013705.","journal-title":"Med Phys"},{"issue":"7","key":"763_CR4","doi-asserted-by":"publisher","first-page":"0158722","DOI":"10.1371\/journal.pone.0158722","volume":"11","author":"E Daskalaki","year":"2016","unstructured":"Daskalaki E, Diem P, Mougiakakou SG. Model-free machine learning in biomedicine: Feasibility study in type 1 diabetes. PloS ONE. 2016; 11(7):0158722.","journal-title":"PloS ONE"},{"issue":"1","key":"763_CR5","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.artmed.2014.07.004","volume":"62","author":"P Escandell-Montero","year":"2014","unstructured":"Escandell-Montero P, Chermisi M, Martinez-Martinez JM, et al.Optimization of anemia treatment in hemodialysis patients via reinforcement learning. Artif Intell Med. 2014; 62(1):47\u201360.","journal-title":"Artif Intell Med"},{"issue":"1-2","key":"763_CR6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10994-010-5229-0","volume":"84","author":"SM Shortreed","year":"2011","unstructured":"Shortreed SM, Laber E, Lizotte DJ, Stroup TS, Pineau J, Murphy SA. Informing sequential clinical decision-making through reinforcement learning: an empirical study. Mach Learn. 2011; 84(1-2):109\u201336.","journal-title":"Mach Learn"},{"issue":"07","key":"763_CR7","doi-asserted-by":"publisher","first-page":"1750012","DOI":"10.1142\/S0129065717500125","volume":"27","author":"V Nagaraj","year":"2017","unstructured":"Nagaraj V, Lamperski A, Netoff TI. Seizure control in a computational model using a reinforcement learning stimulation paradigm. Int J Neural Syst. 2017; 27(07):1750012.","journal-title":"Int J Neural Syst"},{"key":"763_CR8","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.bspc.2015.05.013","volume":"22","author":"R Padmanabhan","year":"2015","unstructured":"Padmanabhan R, Meskin N, Haddad WM. Closed-loop control of anesthesia and mean arterial pressure using reinforcement learning. Biomed Signal Process Control. 2015; 22:54\u201364.","journal-title":"Biomed Signal Process Control"},{"key":"763_CR9","unstructured":"Weng W-H, Gao M, He Z, Yan S, Szolovits P. Representation and reinforcement learning for personalized glycemic control in septic patients. arXiv preprint arXiv:1712.00654. 2017."},{"key":"763_CR10","unstructured":"Ng AY, Russell SJ, et al.Algorithms for inverse reinforcement learning. In: ICML. Omnipress: 2000. p. 663\u2013670."},{"key":"763_CR11","doi-asserted-by":"crossref","unstructured":"Abbeel P, Ng AY. Apprenticeship learning via inverse reinforcement learning. In: ICML. Omnipress: 2004. p. 1.","DOI":"10.1145\/1015330.1015430"},{"key":"763_CR12","volume-title":"ICRA","author":"M Kuderer","year":"2015","unstructured":"Kuderer M, Gulati S, Burgard W. Learning driving styles for autonomous vehicles from demonstration. In: ICRA. New York: IEEE: 2015. p. 2641\u20132646."},{"key":"763_CR13","volume-title":"AAMAS","author":"K Shiarlis","year":"2016","unstructured":"Shiarlis K, Messias J, Whiteson S. Inverse reinforcement learning from failure. In: AAMAS. New York: ACM: 2016. p. 1060\u20131068."},{"key":"763_CR14","unstructured":"Li K, Burdick JW. Inverse reinforcement learning in large state spaces via function approximation. arXiv preprint arXiv:1707.09394. 2017."},{"issue":"2","key":"763_CR15","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/JPROC.2015.2501978","volume":"104","author":"AE Johnson","year":"2016","unstructured":"Johnson AE, Ghassemi MM, Nemati S, Niehaus KE, Clifton DA, Clifford GD. Machine learning and decision support in critical care. Proc IEEE. 2016; 104(2):444\u201366.","journal-title":"Proc IEEE"},{"key":"763_CR16","unstructured":"Vincent R. Reinforcement learning in models of adaptive medical treatment strategies. PhD thesis: McGill University Libraries; 2014."},{"key":"763_CR17","volume-title":"Artificial Intelligence and Statistics","author":"M Herman","year":"2016","unstructured":"Herman M, Gindele T, Wagner J, Schmitt F, Burgard W. Inverse reinforcement learning with simultaneous estimation of rewards and dynamics. In: Artificial Intelligence and Statistics. New York: ACM: 2016. p. 102\u2013110."},{"key":"763_CR18","unstructured":"Prasad N, Cheng L-F, Chivers C, Draugelis M, Engelhardt BE. A reinforcement learning approach to weaning of mechanical ventilation in intensive care units. arXiv preprint arXiv:1704.06300. 2017."},{"key":"763_CR19","doi-asserted-by":"crossref","unstructured":"Nemati S, Adams R. Identifying outcome-discriminative dynamics in multivariate physiological cohort time series. Adv State Space Methods Neural Clin Data. 2015; 283.","DOI":"10.1017\/CBO9781139941433.013"},{"key":"763_CR20","volume-title":"EMBC","author":"S Nemati","year":"2016","unstructured":"Nemati S, Ghassemi MM, Clifford GD. Optimal medication dosing from suboptimal clinical examples: A deep reinforcement learning approach. In: EMBC. New York: IEEE: 2016. p. 2978\u20132981."},{"key":"763_CR21","volume-title":"ICSTCC","author":"C Sandu","year":"2015","unstructured":"Sandu C, Popescu D, Popescu C. Post cardiac surgery recovery process with reinforcement learning. In: ICSTCC. New York: IEEE: 2015. p. 658\u2013661."},{"key":"763_CR22","unstructured":"Raghu A, Komorowski M, Ahmed I, Celi L, Szolovits P, Ghassemi M. Deep reinforcement learning for sepsis treatment. arXiv preprint arXiv:1711.09602. 2017."},{"key":"763_CR23","volume-title":"AAAI, vol 8","author":"BD Ziebart","year":"2008","unstructured":"Ziebart BD, Maas AL, Bagnell JA, Dey AK. Maximum entropy inverse reinforcement learning. In: AAAI, vol 8. Cambridge: AAAI Press: 2008. p. 1433\u20131438."},{"issue":"61801","key":"763_CR24","first-page":"1","volume":"51","author":"D Ramachandran","year":"2007","unstructured":"Ramachandran D, Amir E. Bayesian inverse reinforcement learning. Urbana. 2007; 51(61801):1\u20134.","journal-title":"Urbana"},{"key":"763_CR25","volume-title":"NIPs","author":"S Levine","year":"2011","unstructured":"Levine S, Popovic Z, Koltun V. Nonlinear inverse reinforcement learning with gaussian processes. In: NIPs. Cambridge: MIT Press: 2011. p. 19\u201327."},{"key":"763_CR26","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson AE, Pollard TJ, Shen L, Li-wei HL, Feng M, Ghassemi M, Moody B, Szolovits P, Celi LA, Mark RG. Mimic-iii, a freely accessible critical care database. Sci Data. 2016; 3:160035.","journal-title":"Sci Data"},{"issue":"Apr","key":"763_CR27","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst D, Geurts P, Wehenkel L. Tree-based batch mode reinforcement learning. J Mach Learn Res. 2005; 6(Apr):503\u201356.","journal-title":"J Mach Learn Res"},{"issue":"5","key":"763_CR28","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001; 29(5):1189\u2013232.","journal-title":"Ann Stat"},{"key":"763_CR29","unstructured":"Kangasr\u00e4\u00e4si\u00f6 A, Kaski S. Inverse reinforcement learning from incomplete observation data. arXiv preprint arXiv:1703.09700. 2017."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0763-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-019-0763-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0763-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,7]],"date-time":"2020-04-07T19:06:48Z","timestamp":1586286408000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-019-0763-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":29,"journal-issue":{"issue":"S2","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["763"],"URL":"https:\/\/doi.org\/10.1186\/s12911-019-0763-6","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]},"assertion":[{"value":"9 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"57"}}