{"id":"https://openalex.org/W4391448746","doi":"https://doi.org/10.1145/3643856","title":"Optimal Treatment Strategies for Critical Patients with Deep Reinforcement Learning","display_name":"Optimal Treatment Strategies for Critical Patients with Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4391448746","doi":"https://doi.org/10.1145/3643856"},"language":"en","primary_location":{"id":"doi:10.1145/3643856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643856","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056653244","display_name":"Simi Job","orcid":"https://orcid.org/0000-0003-1716-7475"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Simi Job","raw_affiliation_strings":["School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065941595","display_name":"Xiaohui Tao","orcid":"https://orcid.org/0000-0002-0020-077X"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaohui Tao","raw_affiliation_strings":["School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013151488","display_name":"Haoran Xie","orcid":"https://orcid.org/0000-0003-0965-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Xie","raw_affiliation_strings":["Department of Computing and Decision Sciences, Lingnan University, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Decision Sciences, Lingnan University, Hong Kong, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051414197","display_name":"Taotao Cai","orcid":"https://orcid.org/0000-0002-3624-6120"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Taotao Cai","raw_affiliation_strings":["School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012159374","display_name":"Jianming Yong","orcid":"https://orcid.org/0000-0003-4111-1076"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianming Yong","raw_affiliation_strings":["School of Business, University of Southern Queensland, Springfield, Australia"],"affiliations":[{"raw_affiliation_string":"School of Business, University of Southern Queensland, Springfield, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, the Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computing, the Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056653244"],"corresponding_institution_ids":["https://openalex.org/I185523456"],"apc_list":null,"apc_paid":null,"fwci":3.4752,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93004885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10867","display_name":"Intensive Care Unit Cognitive Disorders","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/2706","display_name":"Critical Care and Intensive Care Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8796944618225098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726118266582489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6085113286972046},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48311781883239746},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4598439931869507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44686123728752136},{"id":"https://openalex.org/keywords/intensive-care","display_name":"Intensive care","score":0.4274786412715912},{"id":"https://openalex.org/keywords/personalized-medicine","display_name":"Personalized medicine","score":0.419540673494339},{"id":"https://openalex.org/keywords/intensive-care-medicine","display_name":"Intensive care medicine","score":0.2201405167579651},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1685311496257782},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.08151459693908691}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8796944618225098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726118266582489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6085113286972046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48311781883239746},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4598439931869507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44686123728752136},{"id":"https://openalex.org/C2987404301","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care","level":2,"score":0.4274786412715912},{"id":"https://openalex.org/C32220436","wikidata":"https://www.wikidata.org/wiki/Q2072214","display_name":"Personalized medicine","level":2,"score":0.419540673494339},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.2201405167579651},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1685311496257782},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.08151459693908691},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3643856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643856","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5093608303","display_name":null,"funder_award_id":"62276196","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5476631443","display_name":null,"funder_award_id":"201013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6353738511","display_name":null,"funder_award_id":"DP220101360","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8735542678","display_name":null,"funder_award_id":"DB23B2","funder_id":"https://openalex.org/F4320328618","funder_display_name":"Lingnan University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320328618","display_name":"Lingnan University","ror":"https://ror.org/0563pg902"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1898928487","https://openalex.org/W2069289706","https://openalex.org/W2145339207","https://openalex.org/W2162800060","https://openalex.org/W2173248099","https://openalex.org/W2396881363","https://openalex.org/W2533691405","https://openalex.org/W2746553466","https://openalex.org/W2796586126","https://openalex.org/W2798705390","https://openalex.org/W2896893468","https://openalex.org/W2898757811","https://openalex.org/W2902790901","https://openalex.org/W2911667635","https://openalex.org/W2937671098","https://openalex.org/W2963864421","https://openalex.org/W2964340928","https://openalex.org/W2970315086","https://openalex.org/W2970360512","https://openalex.org/W2982341360","https://openalex.org/W2990721380","https://openalex.org/W3012850108","https://openalex.org/W3013137043","https://openalex.org/W3025016712","https://openalex.org/W3037168997","https://openalex.org/W3040948586","https://openalex.org/W3082374968","https://openalex.org/W3083167820","https://openalex.org/W3087580035","https://openalex.org/W3092267918","https://openalex.org/W3108731616","https://openalex.org/W3122582799","https://openalex.org/W3138417050","https://openalex.org/W3140623462","https://openalex.org/W3157757720","https://openalex.org/W3161844450","https://openalex.org/W3167305608","https://openalex.org/W3210302619","https://openalex.org/W4213370086","https://openalex.org/W4220663376","https://openalex.org/W4221023404","https://openalex.org/W4224308779","https://openalex.org/W4224881322","https://openalex.org/W4225518548","https://openalex.org/W4226092483","https://openalex.org/W4283325102","https://openalex.org/W4286896628","https://openalex.org/W4288083420","https://openalex.org/W4293577878","https://openalex.org/W4324291664","https://openalex.org/W4404788945","https://openalex.org/W6767782324"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"Personalized":[0],"clinical":[1],"decision":[2],"support":[3],"systems":[4],"are":[5],"increasingly":[6],"being":[7],"adopted":[8],"due":[9,42],"to":[10,43,75,100,144,146],"the":[11,44,61,122,159,172,176,180,201,205],"emergence":[12],"of":[13,27,47,63,171],"data-driven":[14],"technologies,":[15],"with":[16,90,135,179],"this":[17,80],"approach":[18],"now":[19],"gaining":[20],"recognition":[21],"in":[22,51,108,113],"critical":[23,36,114],"care.":[24],"The":[25,195],"task":[26],"incorporating":[28],"diverse":[29],"patient":[30,110,153,156,217],"conditions":[31],"and":[32,95,121,164],"treatment":[33,65,103,212],"procedures":[34],"into":[35],"care":[37,115],"decision-making":[38],"can":[39,151],"be":[40],"challenging":[41],"heterogeneous":[45],"nature":[46],"medical":[48],"data.":[49],"Advances":[50],"Artificial":[52],"Intelligence":[53],"(AI),":[54],"particularly":[55],"Reinforcement":[56,86],"Learning":[57,87],"(RL)":[58],"techniques,":[59],"enables":[60],"development":[62],"personalized":[64],"strategies":[66],"for":[67,105,126,203],"severe":[68],"illnesses":[69],"by":[70],"using":[71],"a":[72,84,91],"learning":[73,183,188],"agent":[74,184],"recommend":[76],"optimal":[77,102,148,187,211],"policies.":[78],"In":[79],"study,":[81],"we":[82,131],"propose":[83],"Deep":[85],"(DRL)":[88],"model":[89,174],"tailored":[92],"reward":[93],"function":[94],"an":[96,118,186,210],"LSTM-GRU-derived":[97],"state":[98,197],"representation":[99,198],"formulate":[101],"policies":[104,149],"vasopressor":[106],"administration":[107],"stabilizing":[109],"physiological":[111],"states":[112],"settings.":[116],"Using":[117],"ICU":[119],"dataset":[120],"Medical":[123],"Information":[124],"Mart":[125],"Intensive":[127],"Care":[128],"(MIMIC-III)":[129],"dataset,":[130],"focus":[132],"on":[133,215],"patients":[134],"Acute":[136],"Respiratory":[137],"Distress":[138],"Syndrome":[139],"(ARDS)":[140],"that":[141,150],"has":[142],"led":[143],"Sepsis,":[145],"derive":[147],"prioritize":[152],"recovery":[154],"over":[155],"survival.":[157],"Both":[158],"DDQN":[160,166],"(":[161,167],"RepDRL-DDQN":[162],")":[163,169],"Dueling":[165],"RepDRL-DDDQN":[168],"versions":[170],"DRL":[173],"surpass":[175],"baseline":[177],"performance,":[178,207],"proposed":[181],"model\u2019s":[182,206],"achieving":[185],"process":[189],"across":[190],"our":[191],"performance":[192],"measuring":[193],"schemes.":[194],"robust":[196],"served":[199],"as":[200],"foundation":[202],"enhancing":[204],"ultimately":[208],"providing":[209],"policy":[213],"focused":[214],"rapid":[216],"recovery.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}