{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T14:51:17Z","timestamp":1775832677316,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang Province Key Research and Development Program","award":["2020C03073"],"award-info":[{"award-number":["2020C03073"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81871454"],"award-info":[{"award-number":["81871454"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31870938"],"award-info":[{"award-number":["31870938"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/jbhi.2023.3274568","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T23:49:43Z","timestamp":1683762583000},"page":"4120-4130","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement Learning Model for Managing Noninvasive Ventilation Switching Policy"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3758-421X","authenticated-orcid":false,"given":"Xue","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7145-6011","authenticated-orcid":false,"given":"Qing","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Molei","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Intensive Care Unit, Zhejiang Hospital, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9878-088X","authenticated-orcid":false,"given":"Xiaoqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Deepwise AI LAB, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfei","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Intensive Care Unit, Zhejiang Hospital, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7752-4839","authenticated-orcid":false,"given":"Luping","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0056-663X","authenticated-orcid":false,"given":"Guolong","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Intensive Care Unit, Zhejiang Hospital, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9107-5785","authenticated-orcid":false,"given":"Gangmin","family":"Ning","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-016-4601-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000001379"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1159\/000499361"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.20452\/pamw.2460"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000000945"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.04.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00388-6"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afi211"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-012-2475-6"},{"key":"ref54","article-title":"Learning to diagnose with LSTM recurrent neural networks","author":"lipton","year":"2015","journal-title":"Computer ence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-01197-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0310-5"},{"key":"ref19","first-page":"1","article-title":"Mining patient data from heterogeneous sources for decision making on administration of non invasive mechanical ventilation in intensive care units","author":"garc\u00eda","year":"0","journal-title":"Proc IEEE 17th Int Conf Inf Fusion"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958047"},{"key":"ref51","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","author":"jiang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","first-page":"1447","article-title":"More robust doubly robust off-policy evaluation","author":"farajtabar","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","author":"kumar","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref45","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","first-page":"759","article-title":"Eligibility traces for off-policy policy evaluation","author":"precup","year":"0","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref47","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"yu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2012.12.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2018.8483478"},{"key":"ref49","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"thomas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s13613-015-0044-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-006-0324-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa032736"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s12871-017-0409-0"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1097\/00003246-200203000-00010","article-title":"Noninvasive ventilation in acute respiratory failure","volume":"30","author":"wark","year":"2002","journal-title":"Crit Care Med"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.05.00085304"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1136\/thorax.55.10.819"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0253-x"},{"key":"ref37","first-page":"1","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"johnson","year":"2016","journal-title":"Data Science Journal"},{"key":"ref36","first-page":"209","article-title":"A reinforcement learning approach to weaning of mechanical ventilation in intensive care units","author":"prasad","year":"0","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2014.07.004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377527"},{"key":"ref33","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017"},{"key":"ref32","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: A deep reinforcement learning approach","author":"raghu","year":"0","journal-title":"Proc Mach Learn Healthcare Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201106-1094OC"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11739-015-1293-6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.03.018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(03)00170-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30316-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2466-14-19"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e3181bc8243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3414\/ME14-01-0015"},{"key":"ref22","first-page":"1","article-title":"Early prediction of noninvasive ventilation failure in COPD patients: Derivation, internal validation, and external validation of a simple risk score","volume":"9","author":"duan","year":"2019","journal-title":"Ann Intensive Care"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-77893-3"},{"key":"ref28","first-page":"1671","article-title":"Adaptive treatment of epilepsy via batch-mode reinforcement learning","author":"guez","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref29","article-title":"Representation and reinforcement learning for personalized glycemic control in septic patients","author":"weng","year":"2017"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221020\/10210140\/10122152.pdf?arnumber=10122152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:01:55Z","timestamp":1693245715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2023.3274568","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}