{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T03:16:13Z","timestamp":1780974973533,"version":"3.54.1"},"reference-count":19,"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\/s12911-019-0755-6","type":"journal-article","created":{"date-parts":[[2019,4,9]],"date-time":"2019-04-09T00:05:34Z","timestamp":1554768334000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Incorporating causal factors into reinforcement learning for dynamic treatment regimes in HIV"],"prefix":"10.1186","volume":"19","author":[{"given":"Chao","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinzhao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqi","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,9]]},"reference":[{"key":"755_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":"755_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":"755_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":"755_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":"1-2","key":"755_CR5","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. Machine learning. 2011; 84(1-2):109\u201336.","journal-title":"Machine learning"},{"key":"755_CR6","unstructured":"Weng W-H, Gao M, He Z, Yan S, Szolovits P. Representation and reinforcement learning for personalized glycemic control in septic patients. 2017. arXiv preprint arXiv:1712.00654."},{"key":"755_CR7","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.engappai.2018.09.007","volume":"76","author":"D Hein","year":"2018","unstructured":"Hein D, Udluft S, Runkler TA. Interpretable policies for reinforcement learning by genetic programming. Eng Appl Artif Intell. 2018; 76:158\u201369.","journal-title":"Eng Appl Artif Intell"},{"issue":"2","key":"755_CR8","doi-asserted-by":"publisher","first-page":"223","DOI":"10.3934\/mbe.2004.1.223","volume":"1","author":"BM Adams","year":"2004","unstructured":"Adams BM, Banks HT, Kwon H-D, Tran HT. Dynamic multidrug therapies for hiv: Optimal and sti control approaches. Math Biosci Eng. 2004; 1(2):223\u201341.","journal-title":"Math Biosci Eng"},{"key":"755_CR9","volume-title":"45th IEEE Conference on Decision and Control","author":"D Ernst","year":"2006","unstructured":"Ernst D, Stan G-B, Goncalves J, Wehenkel L. Clinical data based optimal sti strategies for hiv: a reinforcement learning approach. In: 45th IEEE Conference on Decision and Control. New York: IEEE: 2006. p. 667\u201372."},{"key":"755_CR10","unstructured":"Parbhoo S. A reinforcement learning design for hiv clinical trials. 2014. PhD thesis."},{"issue":"7","key":"755_CR11","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1007\/s13042-017-0639-y","volume":"9","author":"H Gholizade-Narm","year":"2018","unstructured":"Gholizade-Narm H, Noori A. Control the population of free viruses in nonlinear uncertain hiv system using q-learning. Int J Mach Learn Cybern. 2018; 9(7):1169\u201379.","journal-title":"Int J Mach Learn Cybern"},{"key":"755_CR12","volume-title":"AAAI Workshop: Modern Artificial Intelligence for Health Analytics.","author":"VN Marivate","year":"2014","unstructured":"Marivate VN, Chemali J, Brunskill E, Littman ML. Quantifying uncertainty in batch personalized sequential decision making. In: AAAI Workshop: Modern Artificial Intelligence for Health Analytics.Cambridge: The AAAI Press: 2014."},{"key":"755_CR13","doi-asserted-by":"crossref","unstructured":"Killian T, Konidaris G, Doshi-Velez F. Transfer learning across patient variations with hidden parameter markov decision processes. 2016. arXiv preprint arXiv:1612.00475.","DOI":"10.1609\/aaai.v31i1.11065"},{"key":"755_CR14","volume-title":"Reinforcement learning. vol 12. Adapt Learn Optim","author":"M Wiering","year":"2012","unstructured":"Wiering M, Van Otterlo M. Reinforcement learning. vol 12. Adapt Learn Optim. Berlin: Springer; 2012."},{"issue":"3-4","key":"755_CR15","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins CJ, Dayan P. Q-learning. Mach Learn. 1992; 8(3-4):279\u201392.","journal-title":"Mach Learn"},{"key":"755_CR16","volume-title":"AAAI.","author":"CA Merck","year":"2016","unstructured":"Merck CA, Kleinberg S. Causal explanation under indeterminism: A sampling approach. In: AAAI.Cambridge: The AAAI Press: 2016. p. 1037\u201343."},{"issue":"3-4","key":"755_CR17","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn. 1992; 8(3-4):229\u201356.","journal-title":"Mach Learn"},{"key":"755_CR18","volume-title":"AAAI.","author":"K Kawaguchi","year":"2016","unstructured":"Kawaguchi K. Bounded optimal exploration in mdp. In: AAAI.Cambridge: The AAAI Press: 2016. p. 1758\u201364."},{"key":"755_CR19","volume-title":"AAAI.","author":"J Pazis","year":"2013","unstructured":"Pazis J, Parr R. Pac optimal exploration in continuous space markov decision processes. In: AAAI.Cambridge: The AAAI Press: 2013."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0755-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-019-0755-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0755-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T14:24:18Z","timestamp":1663251858000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-019-0755-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":19,"journal-issue":{"issue":"S2","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["755"],"URL":"https:\/\/doi.org\/10.1186\/s12911-019-0755-6","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":"60"}}