{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T03:16:18Z","timestamp":1780974978098,"version":"3.54.1"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Chinese Academy of Medical Sciences & Peking Union Medical College","award":["2018-I2M-AI-016"],"award-info":[{"award-number":["2018-I2M-AI-016"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Coronary heart disease (CHD) has become the leading cause of death and one of the most serious epidemic diseases worldwide. CHD is characterized by urgency, danger and severity, and dynamic treatment strategies for CHD patients are needed. We aimed to build and validate an AI model for dynamic treatment recommendations for CHD patients with the goal of improving patient outcomes and learning best practices from clinicians to help clinical decision support for treating CHD patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We formed the treatment strategy as a sequential decision problem, and applied an AI supervised reinforcement learning-long short-term memory (SRL-LSTM) framework that combined supervised learning (SL) and reinforcement learning (RL) with an LSTM network to track patients\u2019 states to learn a recommendation model that took a patient\u2019s diagnosis and evolving health status as input and provided a treatment recommendation in the form of whether to take specific drugs. The experiments were conducted by leveraging a real-world intensive care unit (ICU) database with 13,762 admitted patients diagnosed with CHD. We compared the performance of the applied SRL-LSTM model and several state-of-the-art SL and RL models in reducing the estimated in-hospital mortality and the Jaccard similarity with clinicians\u2019 decisions. We used a random forest algorithm to calculate the feature importance of both the clinician policy and the AI policy to illustrate the interpretability of the AI model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our experimental study demonstrated that the AI model could help reduce the estimated in-hospital mortality through its RL function and learn the best practice from clinicians through its SL function. The similarity between the clinician policy and the AI policy regarding the surviving patients was high, while for the expired patients, it was much lower. The dynamic treatment strategies made by the AI model were clinically interpretable and relied on sensible clinical features extracted according to monitoring indexes and risk factors for CHD patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We proposed a pipeline for constructing an AI model to learn dynamic treatment strategies for CHD patients that could improve patient outcomes and mimic the best practices of clinicians. And a lot of further studies and efforts are needed to make it practical.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12911-022-01774-0","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T03:02:46Z","timestamp":1644894166000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven study"],"prefix":"10.1186","volume":"22","author":[{"given":"Haihong","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"1774_CR1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjqcco\/qcaa076","author":"H Dai","year":"2020","unstructured":"Dai H, Much AA, Maor E, et al. Global, regional, and national burden of ischemic heart disease and its attributable risk factors, 1990\u20132017: results from the global Burden of Disease Study 2017. Eur Heart J Qual Care Clin Outcomes. 2020. https:\/\/doi.org\/10.1093\/ehjqcco\/qcaa076.","journal-title":"Eur Heart J Qual Care Clin Outcomes"},{"issue":"10","key":"1774_CR2","doi-asserted-by":"publisher","first-page":"e56","DOI":"10.1161\/CIR.0000000000000659","volume":"139","author":"EJ Benjamin","year":"2019","unstructured":"Benjamin EJ, Muntner P, Alonso A, et al. Heart disease and stroke statistics\u20142019 update: a report from the American Heart Association. Circulation. 2019;139(10):e56\u2013528. https:\/\/doi.org\/10.1161\/CIR.0000000000000659.","journal-title":"Circulation"},{"key":"1774_CR3","volume-title":"Annual report on cardiovascular health and diseases in China 2019","author":"National Center for Cardiovascular Diseases, China","year":"2020","unstructured":"National Center for Cardiovascular Diseases, China. Annual report on cardiovascular health and diseases in China 2019. Beijing: Science Press; 2020."},{"key":"1774_CR4","volume-title":"Fuwai manual of cardiovascular critical care medicine","author":"J Zhu","year":"2019","unstructured":"Zhu J. Fuwai manual of cardiovascular critical care medicine. Beijing: People\u2019s Medical Publishing House; 2019."},{"issue":"3","key":"1774_CR5","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1093\/eurheartj\/ehz425","volume":"41","author":"J Knuuti","year":"2020","unstructured":"Knuuti J, Wijns W, Saraste A, et al. 2019 ESC guidelines for the diagnosis and management of chronic coronary syndromes. Eur Heart J. 2020;41(3):407\u201377. https:\/\/doi.org\/10.1093\/eurheartj\/ehz425.","journal-title":"Eur Heart J"},{"issue":"2","key":"1774_CR6","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s12350-017-1055-0","volume":"25","author":"J Joseph","year":"2018","unstructured":"Joseph J, Velasco A, Hage FG, et al. Guidelines in review: comparison of ESC and ACC\/AHA guidelines for the diagnosis and management of patients with stable coronary artery disease. J Nucl Cardiol. 2018;25(2):509\u201315. https:\/\/doi.org\/10.1007\/s12350-017-1055-0.","journal-title":"J Nucl Cardiol"},{"issue":"06","key":"1774_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.12037\/YXQY.2018.06-01","volume":"10","author":"Committee of Experts on Rational Drug Use of National Health Commission of the P.R. China, Chinese Pharmacists Association","year":"2018","unstructured":"Committee of Experts on Rational Drug Use of National Health Commission of the P.R. China, Chinese Pharmacists Association. Guidelines for rational drug use for coronary heart disease (Second edition). Chin J Front Med (Electron Ed). 2018;10(06):1\u2013130. https:\/\/doi.org\/10.12037\/YXQY.2018.06-01.","journal-title":"Chin J Front Med (Electron Ed)"},{"issue":"26","key":"1774_CR8","doi-asserted-by":"publisher","first-page":"3294","DOI":"10.1002\/sim.3720","volume":"28","author":"Y Zhao","year":"2009","unstructured":"Zhao Y, Kosorok MR, Zeng D. Reinforcement learning design for cancer clinical trials. Stat Med. 2009;28(26):3294\u2013315. https:\/\/doi.org\/10.1002\/sim.3720.","journal-title":"Stat Med"},{"issue":"4","key":"1774_CR9","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1111\/j.1541-0420.2011.01572.x","volume":"67","author":"Y Zhao","year":"2011","unstructured":"Zhao Y, Zeng D, Socinski MA, et al. Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer. Biometrics. 2011;67(4):1422\u201333. https:\/\/doi.org\/10.1111\/j.1541-0420.2011.01572.x.","journal-title":"Biometrics"},{"issue":"10","key":"1774_CR10","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1145\/3394486.3403286","volume":"26","author":"G Fang","year":"2019","unstructured":"Fang G, Annis IE, Elston-Lafata J, et al. Applying machine learning to predict real-world individual treatment effects: insights from a virtual patient cohort. J Am Med Inform Assoc. 2019;26(10):977\u201388. https:\/\/doi.org\/10.1145\/3394486.3403286.","journal-title":"J Am Med Inform Assoc"},{"key":"1774_CR11","doi-asserted-by":"publisher","DOI":"10.1002\/dac.4058","author":"D Sharma","year":"2019","unstructured":"Sharma D, Aujla GS, Bajaj R. Evolution from ancient medication to human-centered healthcare 4.0: a review on healthcare recommender systems. Int J Commun Syst. 2019. https:\/\/doi.org\/10.1002\/dac.4058.","journal-title":"Int J Commun Syst"},{"issue":"1","key":"1774_CR12","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.3503","volume":"3","author":"P Fraccaro","year":"2015","unstructured":"Fraccaro P, Castelerio MA, Ainsworth J, et al. Adoption of clinical decision support in multimorbidity: a systematic review. JMIR Med Inform. 2015;3(1): e4. https:\/\/doi.org\/10.2196\/medinform.3503.","journal-title":"JMIR Med Inform"},{"key":"1774_CR13","unstructured":"Bajor JM, Lasko TA. Predicting medications from diagnostic codes with recurrent neural networks. In: International conference on learning representations, April 24\u201326, 2017; Toulon, France."},{"key":"1774_CR14","doi-asserted-by":"publisher","unstructured":"Zhang Y, Chen R, Tang J, et al. LEAP: learning to prescribe effective and safe treatment combinations for multimorbidity. In: Proceedings of the 23th ACM SIGKDD international conference on knowledge discovery & data mining 2017. pp. 1315\u201324. https:\/\/doi.org\/10.1145\/3097983.3098109.","DOI":"10.1145\/3097983.3098109"},{"key":"1774_CR15","doi-asserted-by":"publisher","unstructured":"Wang L, Zhang W, He X, et al. Supervised reinforcement learning with recurrent neural network for dynamic treatment recommendation. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining 2018. pp. 2447\u201356. https:\/\/doi.org\/10.1145\/3219819.3219961.","DOI":"10.1145\/3219819.3219961"},{"key":"1774_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bdr.2020.100174","volume":"23","author":"F Gong","year":"2021","unstructured":"Gong F, Wang M, Wang H, et al. SMR: medical knowledge graph embedding for safe medicine recommendation. Big Data Res. 2021;23:1\u20138. https:\/\/doi.org\/10.1016\/j.bdr.2020.100174.","journal-title":"Big Data Res"},{"key":"1774_CR17","doi-asserted-by":"publisher","unstructured":"Wang S. SeqMed: recommending medication combination with sequence generative adversarial nets. In: Proceedings of 2020 IEEE international conference on bioinformatics and biomedicine (BIBM); digital conference, pp. 2664\u201371. https:\/\/doi.org\/10.1109\/BIBM49941.2020.9313196.","DOI":"10.1109\/BIBM49941.2020.9313196"},{"key":"1774_CR18","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","volume":"24","author":"M Komorowski","year":"2018","unstructured":"Komorowski M, Celi LA, Badawi O, et al. The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med. 2018;24:1716\u201320. https:\/\/doi.org\/10.1038\/s41591-018-0213-5.","journal-title":"Nat Med"},{"key":"1774_CR19","unstructured":"Raghu A, Komorowski M, Ahmed I, et al. Deep reinforcement learning for sepsis treatment. In: 31st conference on neural information processing systems 2017, Long Beach, CA, USA."},{"key":"1774_CR20","unstructured":"Weng W, Gao M, He Z, et al. Representation and reinforcement learning for personalized glycemic control in septic patients. In: 31st conference on neural information processing systems 2017, Long Beach, CA, USA."},{"issue":"Suppl 2","key":"1774_CR21","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1186\/s12911-016-0314-3","volume":"16","author":"A Bucur","year":"2016","unstructured":"Bucur A, Leeuwen JV. Workflow-driven clinical decision support for personalized oncology. BMC Med Inform Decis Mak. 2016;16(Suppl 2):151\u201362. https:\/\/doi.org\/10.1186\/s12911-016-0314-3.","journal-title":"BMC Med Inform Decis Mak"},{"issue":"3","key":"1774_CR22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0213292","volume":"14","author":"X Jiang","year":"2019","unstructured":"Jiang X, Wells A, Brufsky A, et al. A clinical decision support system learned from data to personalize treatment recommendations towards preventing breast cancer metastasis. PLoS ONE. 2019;14(3): e0213292. https:\/\/doi.org\/10.1371\/journal.pone.0213292.","journal-title":"PLoS ONE"},{"issue":"3","key":"1774_CR23","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1093\/biomet\/ast014","volume":"100","author":"B Zhang","year":"2013","unstructured":"Zhang B, Tsiatis AA, Laber EB, et al. Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions. Biometrika. 2013;100(3):681\u201394. https:\/\/doi.org\/10.1093\/biomet\/ast014.","journal-title":"Biometrika"},{"issue":"2","key":"1774_CR24","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1111\/biom.12593","volume":"73","author":"R Zhu","year":"2017","unstructured":"Zhu R, Zhao YQ, Chen G, et al. Greedy outcome weighted tree learning of optimal personalized treatment rules. Biometrics. 2017;73(2):391\u2013400. https:\/\/doi.org\/10.1111\/biom.12593.","journal-title":"Biometrics"},{"key":"1774_CR25","doi-asserted-by":"publisher","unstructured":"Sun L, Liu C, Guo C, et al. Data-driven automatic treatment regimen development and recommendation. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery & data mining 2016, pp. 1865\u20131874. https:\/\/doi.org\/10.1145\/2939672.2939866.","DOI":"10.1145\/2939672.2939866"},{"issue":"4","key":"1774_CR26","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1007\/s40265-020-01435-4","volume":"81","author":"H Zheng","year":"2021","unstructured":"Zheng H, Ryzhov IO, Xie W, et al. Personalized multimorbidity management for patients with type 2 diabetes using reinforcement learning of electronic health records. Drugs. 2021;81(4):471\u201382. https:\/\/doi.org\/10.1007\/s40265-020-01435-4.","journal-title":"Drugs"},{"issue":"521","key":"1774_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/01621459.2017.1303386","volume":"113","author":"Y Wang","year":"2018","unstructured":"Wang Y, Fu H, Zeng D, et al. Learning optimal personalized treatment rules in consideration of benefit and risk: with an application to treating type 2 diabetes patients with insulin therapies. J Am Stat Assoc. 2018;113(521):1\u201313. https:\/\/doi.org\/10.1080\/01621459.2017.1303386.","journal-title":"J Am Stat Assoc"},{"key":"1774_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104122","volume":"139","author":"X Ye","year":"2020","unstructured":"Ye X, Zeng QT, Facelli JC, et al. Predicting optimal hypertension treatment pathways using recurrent neural networks. Int J Med Inform. 2020;139: e104122. https:\/\/doi.org\/10.1016\/j.ijmedinf.2020.104122.","journal-title":"Int J Med Inform"},{"key":"1774_CR29","unstructured":"Zhang P, Wang F, Hu J, et al. Towards personalized medicine: leveraging patient similarity and drug similarity analytics. In: AMIA joint summits on translational science proceedings 2014, pp. 132\u20136. PMID: 25717413"},{"key":"1774_CR30","doi-asserted-by":"publisher","unstructured":"Robins JM. Optimal structural nested models for optimal sequential decisions. In: Proceedings of the second Seattle symposium on biostatistics 2004, pp. 189\u2013326. https:\/\/doi.org\/10.1007\/978-1-4419-9076-1_11.","DOI":"10.1007\/978-1-4419-9076-1_11"},{"key":"1774_CR31","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1080\/15374416.2015.1015133","volume":"45","author":"M Gunlicks-Stoessel","year":"2016","unstructured":"Gunlicks-Stoessel M, Mufson L, Westervelt A, et al. A pilot SMART for developing an adaptive treatment strategy for adolescent depression. J Clin Child Adolesc Psychol. 2016;45:480\u201394.","journal-title":"J Clin Child Adolesc Psychol"},{"issue":"4","key":"1774_CR32","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1080\/15374416.2015.1015133","volume":"29","author":"PJ Schulte","year":"2014","unstructured":"Schulte PJ, Tsiatis AA, Laber EB, et al. Q- and A-Learning methods for estimating optimal dynamic treatment regimes. Stat Sci. 2014;29(4):640\u201361. https:\/\/doi.org\/10.1080\/15374416.2015.1015133.","journal-title":"Stat Sci"},{"issue":"449","key":"1774_CR33","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1080\/01621459.2012.695674","volume":"107","author":"Y Zhao","year":"2012","unstructured":"Zhao Y, Zeng D, Rush AJ, et al. Estimating individualized treatment rules using outcome weighted learning. J Am Stat Assoc. 2012;107(449):1106\u201318. https:\/\/doi.org\/10.1080\/01621459.2012.695674.","journal-title":"J Am Stat Assoc"},{"issue":"8","key":"1774_CR34","doi-asserted-by":"publisher","DOI":"10.2196\/10275","volume":"20","author":"V Bremer","year":"2018","unstructured":"Bremer V, Becker D, Kolovos S, et al. Predicting therapy success and costs for personalized treatment recommendations using baseline characteristics: data-driven analysis. J Med Internet Res. 2018;20(8): e10275. https:\/\/doi.org\/10.2196\/10275.","journal-title":"J Med Internet Res"},{"issue":"4","key":"1774_CR35","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1111\/biom.12354","volume":"71","author":"Y Zhang","year":"2015","unstructured":"Zhang Y, Laber EB, Tsiatis A, et al. Using decision lists to construct interpretable and parsimonious treatment regimes. Biometrics. 2015;71(4):895\u2013904. https:\/\/doi.org\/10.1111\/biom.12354.","journal-title":"Biometrics"},{"issue":"524","key":"1774_CR36","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.1080\/01621459.2017.1345743","volume":"113","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Laber EB, Davidian M, et al. Interpretable dynamic treatment regimes. J Am Stat Assoc. 2018;113(524):1541\u20139. https:\/\/doi.org\/10.1080\/01621459.2017.1345743.","journal-title":"J Am Stat Assoc"},{"issue":"17","key":"1774_CR37","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1002\/sim.4512","volume":"31","author":"D Almirall","year":"2012","unstructured":"Almirall D, Compton SN, Gunlicks-Stoessel M, et al. Designing a pilot sequential multiple assignment randomized trial for developing an adaptive treatment strategy. Stat Med. 2012;31(17):1887\u2013902. https:\/\/doi.org\/10.1002\/sim.4512.","journal-title":"Stat Med"},{"issue":"1\u20132","key":"1774_CR38","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, et al. Informing sequential clinical decision-making through reinforcement learning: an empirical study. Mach Learn. 2011;84(1\u20132):109\u201336. https:\/\/doi.org\/10.1007\/s10994-010-5229-0.","journal-title":"Mach Learn"},{"key":"1774_CR39","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2017.45","author":"Y Liu","year":"2017","unstructured":"Liu Y, Logan B, Liu N, et al. Deep reinforcement learning for dynamic treatment regimes on medical registry data. Healthc Inform. 2017. https:\/\/doi.org\/10.1109\/ICHI.2017.45.","journal-title":"Healthc Inform"},{"issue":"516","key":"1774_CR40","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1080\/01621459.2016.1148611","volume":"111","author":"G Chen","year":"2016","unstructured":"Chen G, Zeng D, Kosorok MR. Personalized dose finding using outcome weighted learning. J Am Stat Assoc. 2016;111(516):1509\u201321. https:\/\/doi.org\/10.1080\/01621459.2016.1148611.","journal-title":"J Am Stat Assoc"},{"issue":"517","key":"1774_CR41","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/01621459.2015.1093947","volume":"112","author":"X Zhou","year":"2017","unstructured":"Zhou X, Mayerhamblett N, Khan U, et al. Residual weighted learning for estimating individualized treatment rules. J Am Stat Assoc. 2017;112(517):169\u201387. https:\/\/doi.org\/10.1080\/01621459.2015.1093947.","journal-title":"J Am Stat Assoc"},{"key":"1774_CR42","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jbi.2018.08.004","volume":"86","author":"Z Huang","year":"2018","unstructured":"Huang Z, Ge Z, Dong W, et al. Probabilistic modeling personalized treatment pathways using electronic health records. J Biomed Inform. 2018;86:33\u201348. https:\/\/doi.org\/10.1016\/j.jbi.2018.08.004.","journal-title":"J Biomed Inform"},{"issue":"1","key":"1774_CR43","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.artmed.2012.06.002","volume":"56","author":"Z Huang","year":"2012","unstructured":"Huang Z, Lu X, Duan H. On mining clinical pathway patterns from medical behaviors. Artif Intell Med. 2012;56(1):35\u201350.","journal-title":"Artif Intell Med"},{"key":"1774_CR44","doi-asserted-by":"publisher","DOI":"10.1017\/S1471068416000429","author":"Z Chen","year":"2016","unstructured":"Chen Z, Marple K, Salazar E, et al. A physician advisory system for chronic heart failure management based on knowledge patterns. Theory Pract Logic Program. 2016. https:\/\/doi.org\/10.1017\/S1471068416000429.","journal-title":"Theory Pract Logic Program"},{"issue":"5","key":"1774_CR45","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1017\/S1471068417000308","volume":"17","author":"Z Chen","year":"2017","unstructured":"Chen Z, Salazar E, Marple K, et al. Improving adherence to heart failure management guidelines via abductive reasoning. Theory Pract Logic Program. 2017;17(5):764\u201379. https:\/\/doi.org\/10.1017\/S1471068417000308.","journal-title":"Theory Pract Logic Program"},{"key":"1774_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2018.2883069","volume":"6","author":"Z Chen","year":"2018","unstructured":"Chen Z, Salazar E, Marple K, et al. An AI-based heart failure treatment adviser system. IEEE J Transl Eng Health Med. 2018;6:1\u201310. https:\/\/doi.org\/10.1109\/JTEHM.2018.2883069.","journal-title":"IEEE J Transl Eng Health Med"},{"issue":"10","key":"1774_CR47","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1177\/2047487317702042","volume":"24","author":"D Hansen","year":"2017","unstructured":"Hansen D, Dendale P, Coninx K, et al. The European association of preventive cardiology exercise prescription in everyday practice and rehabilitative training (EXPERT) tool: a digital training and decision support system for optimized exercise prescription in cardiovascular disease, concept, definitions and construction methodology. Eur J Prev Cardiol. 2017;24(10):1017\u201331. https:\/\/doi.org\/10.1177\/2047487317702042.","journal-title":"Eur J Prev Cardiol"},{"key":"1774_CR48","doi-asserted-by":"publisher","unstructured":"Hauskrecht M. Dynamic decision making in stochastic partially observable medical domains: ischemic heart disease example. In: Keravnou E, Garbay C, Baud R, Wyatt J, editors. Artificial intelligence in medicine. AIME; 1997. https:\/\/doi.org\/10.1007\/BFb0029462.","DOI":"10.1007\/BFb0029462"},{"issue":"25","key":"1774_CR49","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1093\/eurheartj\/ehz056","volume":"40","author":"C Krittanawong","year":"2019","unstructured":"Krittanawong C, Johnson KW, Rosenson RS, et al. Deep learning for cardiovascular medicine: a practical primer. Eur Heart J. 2019;40(25):2058\u201373. https:\/\/doi.org\/10.1093\/eurheartj\/ehz056.","journal-title":"Eur Heart J"},{"key":"1774_CR50","doi-asserted-by":"publisher","unstructured":"He Y, Wang C, Li N, et al. Attention and memory-augmented networks for dual-view sequential learning. In: Proceedings of The 26th ACM SIGKDD conference on knowledge discovery & data mining 2020. pp. 125\u2013134. https:\/\/doi.org\/10.1145\/3394486.3403055","DOI":"10.1145\/3394486.3403055"},{"issue":"7","key":"1774_CR51","doi-asserted-by":"publisher","DOI":"10.2196\/18477","volume":"22","author":"S Liu","year":"2020","unstructured":"Liu S, See KC, Ngiam KY, et al. Reinforcement learning for clinical decision support in critical care: a comprehensive review. J Med Internet Res. 2020;22(7): e18477. https:\/\/doi.org\/10.2196\/18477.","journal-title":"J Med Internet Res"},{"key":"1774_CR52","doi-asserted-by":"publisher","unstructured":"Chakraborty B, Murphy SA. Dynamic treatment regimes. In: Proceedings of the 32nd annual meeting of the society for medical decision making 2014. pp. 447\u2013464. https:\/\/doi.org\/10.1146\/annurev-statistics-022513-115553.","DOI":"10.1146\/annurev-statistics-022513-115553"},{"key":"1774_CR53","doi-asserted-by":"publisher","unstructured":"Boominathan S, Oberst M, Zhou H, et al. Treatment policy learning in multiobjective settings with fully observed outcomes. In: Proceedings of the 26th ACM SIGKDD conference on knowledge discovery & data mining 2020. pp. 1937\u20131947. https:\/\/doi.org\/10.1145\/3394486.3403245.","DOI":"10.1145\/3394486.3403245"},{"issue":"4","key":"1774_CR54","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1111\/biom.13084","volume":"75","author":"X Huang","year":"2019","unstructured":"Huang X, Goldberg Y, Xu J. Multicategory individualized treatment regime using outcome weighted learning. Biometrics. 2019;75(4):1216\u201327. https:\/\/doi.org\/10.1111\/biom.13084.","journal-title":"Biometrics"},{"key":"1774_CR55","first-page":"48","volume":"20","author":"YQ Zhao","year":"2019","unstructured":"Zhao YQ, Laber EB, Ning Y, et al. Efficient augmentation and relaxation learning for individualized treatment rules using observational data. J Mach Learn Res. 2019;20:48.","journal-title":"J Mach Learn Res"},{"issue":"12","key":"1774_CR56","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.29323","volume":"3","author":"HC Prescott","year":"2020","unstructured":"Prescott HC, Sussman JB. Smarter use of corticosteroids in treating patients with septic shock. JAMA Netw Open. 2020;3(12): e2029323. https:\/\/doi.org\/10.1001\/jamanetworkopen.2020.29323.","journal-title":"JAMA Netw Open"},{"issue":"6","key":"1774_CR57","doi-asserted-by":"publisher","first-page":"453","DOI":"10.17226\/9728","volume":"18","author":"IO Medicine","year":"2006","unstructured":"Medicine IO. To err is human: building a safer health system. Front Health Serv Manag. 2006;18(6):453\u20134. https:\/\/doi.org\/10.17226\/9728.","journal-title":"Front Health Serv Manag"},{"key":"1774_CR58","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1023\/A:1017940631555","volume":"49","author":"O Mihatsch","year":"2002","unstructured":"Mihatsch O, Neuneier R. Risk-sensitive reinforcement learning. Mach Learn. 2002;49:267\u201390. https:\/\/doi.org\/10.1023\/A:1017940631555.","journal-title":"Mach Learn"},{"issue":"1","key":"1774_CR59","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"A Johnson","year":"2016","unstructured":"Johnson A, Pollard T, Shen L, et al. MIMIC-III, a freely accessible critical care database. Sci Data. 2016;3(1): 160035. https:\/\/doi.org\/10.1038\/sdata.2016.35.","journal-title":"Sci Data"},{"key":"1774_CR60","doi-asserted-by":"publisher","DOI":"10.13026\/C2XW26","author":"A Johnson","year":"2016","unstructured":"Johnson A, Pollard T, Mark R. MIMIC-III clinical database (version 1.4). 2016. PhysioNet. https:\/\/doi.org\/10.13026\/C2XW26."},{"issue":"23","key":"1774_CR61","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.cir.101.23.e215","volume":"101","author":"A Goldberger","year":"2000","unstructured":"Goldberger A, Amaral L, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. 2000;101(23):e215\u201320. https:\/\/doi.org\/10.1161\/01.cir.101.23.e215.","journal-title":"Circulation"},{"key":"1774_CR62","unstructured":"The British Heart Foundation. Coronary heart disease. https:\/\/www.bhf.org.uk\/informationsupport\/conditions\/coronary-heart-disease. Accessed 28 May 2020."},{"key":"1774_CR63","unstructured":"Free online searchable 2009 ICD-9-CM. http:\/\/icd9cm.chrisendres.com\/index.php?action=contents. Accessed 28 May 2020."},{"key":"1774_CR64","unstructured":"tf.keras.layers.Embedding. https:\/\/tensorflow.google.cn\/api_docs\/python\/tf\/keras\/layers\/Embedding. Accessed 26 July 2021."},{"key":"1774_CR65","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG. Reinforcement learning: an introduction. 2nd ed. Cambridge: MIT Press; 2018.","edition":"2"},{"key":"1774_CR66","unstructured":"Lillicrap T, Hunt JJ, Pritzel A, et al. Continuous control with deep reinforcement learning. In: International conference on learning representations 2017. https:\/\/arxiv.org\/pdf\/1509.02971.pdf. Accessed 9 April 2020."},{"issue":"1","key":"1774_CR67","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44\u201356. https:\/\/doi.org\/10.1038\/s41591-018-0300-7.","journal-title":"Nat Med"},{"issue":"12","key":"1774_CR68","doi-asserted-by":"publisher","first-page":"e635","DOI":"10.1016\/S2589-7500(20)30249-1","volume":"2","author":"E Tat","year":"2020","unstructured":"Tat E, Bhatt DL, Rabbat MG. Addressing bias: artificial intelligence in cardiovascular medicine. Lancet Digit Health. 2020;2(12):e635\u20136. https:\/\/doi.org\/10.1016\/S2589-7500(20)30249-1.","journal-title":"Lancet Digit Health"},{"issue":"5","key":"1774_CR69","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1016\/j.mayocp.2020.01.038","volume":"95","author":"F Lopez-Jimenez","year":"2020","unstructured":"Lopez-Jimenez F, Attia Z, Arruda-Olson AM, et al. Artificial intelligence in cardiology: present and future. Mayo Clin Proc. 2020;95(5):1015\u201339. https:\/\/doi.org\/10.1016\/j.mayocp.2020.01.038.","journal-title":"Mayo Clin Proc"},{"key":"1774_CR70","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.711401","volume":"8","author":"AW Ben","year":"2021","unstructured":"Ben AW, Pesaranghader A, Avram R, et al. Implementing machine learning in interventional cardiology: the benefits are worth the trouble. Front Cardiovasc Med. 2021;8: 711401. https:\/\/doi.org\/10.3389\/fcvm.2021.711401.","journal-title":"Front Cardiovasc Med"},{"key":"1774_CR71","unstructured":"Ross C, Swetlitz I. IBM\u2019s Watson supercomputer recommended \u2018unsafe and incorrect\u2019 cancer treatments, internal documents show. In Stat News. https:\/\/www.statnews.com\/2018\/07\/25\/ibm-watson-recommended-unsafe-incorrect-treatments\/ (published 25 July 2018). Accessed 30 Dec 2021."},{"key":"1774_CR72","unstructured":"Abrams C. Google\u2019s effort to prevent blindness shows AI challenges. Dow Jones News. https:\/\/uk.advfn.com\/stock-market\/NASDAQ\/GOOGL\/share-news\/Googles-Effort-to-Prevent-Blindness-Hits-Roadblock\/79124560 (published 26 Jan 2019). Accessed 30 Dec 2021."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-01774-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-022-01774-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-01774-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T03:04:43Z","timestamp":1644894283000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-022-01774-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,15]]},"references-count":72,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["1774"],"URL":"https:\/\/doi.org\/10.1186\/s12911-022-01774-0","relation":{"references":[{"id-type":"uri","id":"","asserted-by":"subject"}],"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.27351","asserted-by":"object"}]},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,15]]},"assertion":[{"value":"26 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"MIMIC-III is a freely accessible critical care database made by Johnson et al. [\n                      \n                      ]. Research use of MIMIC-III was approved by the Institutional Review Board of Beth Israel Deaconess Medical Center and Massachusetts Institute of Technology [\n                      \n                      ]. The author accessed the database as a credentialed user and signed a specified DUA under the PhysioNet Credentialed Health Data License 1.5.0 [\n                      \n                      ].","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The manuscript has been approved by all the authors for publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"39"}}