{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T13:36:57Z","timestamp":1794317817192,"version":"4.9.0"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1109\/icdmw60847.2023.00048","type":"proceedings-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T18:47:08Z","timestamp":1707245228000},"page":"329-337","source":"Crossref","is-referenced-by-count":21,"title":["Deep Attention Q-Network for Personalized Treatment Recommendation"],"prefix":"10.1109","author":[{"given":"Simin","family":"Ma","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junghwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicoleta","family":"Serban","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihao","family":"Yang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-2600(18)30279-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2019.06.015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_62"},{"key":"ref5","first-page":"301","article-title":"Doctor ai: Predicting clinical events via recurrent neural networks","volume-title":"Machine learning for healthcare conference","author":"Choi"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13271"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00192-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01331-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref10","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach","volume-title":"Machine Learning for Healthcare Conference","author":"Raghu"},{"key":"ref11","first-page":"887","article-title":"Improving sepsis treatment strategies by combining deep and kernel-based reinforcement learning","volume-title":"AMIA Annual Symposium Proceedings","volume":"2018","author":"Peng"},{"key":"ref12","article-title":"Deep reinforcement learning for sepsis treatment","author":"Raghu","year":"2017"},{"key":"ref13","first-page":"1","article-title":"Reinforcement learning for sepsis treatment: A continuous action space solution","volume-title":"Machine Learning for Healthcare Conference","author":"Huang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.05.013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2011.15"},{"key":"ref16","article-title":"A reinforcement learning approach to weaning of mechanical ventilation in intensive care units","author":"Prasad","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0763-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219961"},{"key":"ref19","article-title":"Representation and reinforcement learning for personalized glycemic control in septic patients","author":"Weng","year":"2017"},{"key":"ref20","article-title":"Optimizing sequential medical treatments with auto-encoding heuristic search in pomdps","author":"Li","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref22","article-title":"Deep recurrent q-learning for partially observable mdps","volume-title":"2015 aaai fall symposium series","author":"Hausknecht"},{"key":"ref23","first-page":"2117","article-title":"Deep variational reinforcement learning for pomdps","volume-title":"International Conference on Machine Learning","author":"Igl"},{"key":"ref24","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Deep transformer q-networks for partially observable reinforcement learning","author":"Esslinger","year":"2022"},{"key":"ref26","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Personalized medication dosing using volatile data streams","volume-title":"Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence","author":"Ghassemi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8513203"},{"key":"ref29","article-title":"Model-based reinforcement learning for sepsis treatment","author":"Raghu","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2019.8857295"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(15)70112-X"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"3","key":"ref33","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/s19183837"},{"key":"ref35","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref36","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref37","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref40","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref42","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1089\/sur.2017.278"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF01709751"},{"key":"ref47","first-page":"3658","article-title":"Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions","volume-title":"International Conference on Machine Learning","author":"Gottesman"},{"key":"ref48","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Thomas"},{"key":"ref49","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Jiang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-019-2663-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1186\/s13049-019-0609-3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1001\/jama.286.14.1754"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0012-3692(15)51124-0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-018-5134-8"},{"key":"ref56","article-title":"Evaluating reinforcement learning algorithms in observational health settings","author":"Gottesman","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"}],"event":{"name":"2023 IEEE International Conference on Data Mining Workshops (ICDMW)","location":"Shanghai, China","start":{"date-parts":[[2023,12,4]]},"end":{"date-parts":[[2023,12,4]]}},"container-title":["2023 IEEE International Conference on Data Mining Workshops (ICDMW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10411504\/10411508\/10411559.pdf?arnumber=10411559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T08:42:28Z","timestamp":1709455348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10411559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/icdmw60847.2023.00048","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}