{"id":"https://openalex.org/W4407977713","doi":"https://doi.org/10.1007/s44230-025-00093-7","title":"Offline Safe Reinforcement Learning for Sepsis Treatment: Tackling Variable-Length Episodes with Sparse Rewards","display_name":"Offline Safe Reinforcement Learning for Sepsis Treatment: Tackling Variable-Length Episodes with Sparse Rewards","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407977713","doi":"https://doi.org/10.1007/s44230-025-00093-7"},"language":"en","primary_location":{"id":"doi:10.1007/s44230-025-00093-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-025-00093-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44230-025-00093-7.pdf","source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44230-025-00093-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100600687","display_name":"Rui Tu","orcid":"https://orcid.org/0000-0002-4821-9613"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Tu","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076976899","display_name":"Zhipeng Luo","orcid":"https://orcid.org/0000-0002-4053-5443"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhipeng Luo","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-4053-5443","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005867273","display_name":"Chuanliang Pan","orcid":"https://orcid.org/0000-0002-8030-2636"},"institutions":[{"id":"https://openalex.org/I4210093384","display_name":"Third People's Hospital of Chengdu","ror":"https://ror.org/00ebdgr24","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210093384"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanliang Pan","raw_affiliation_strings":["Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China","institution_ids":["https://openalex.org/I4210093384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039914294","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-1229-4005"},"institutions":[{"id":"https://openalex.org/I4210093384","display_name":"Third People's Hospital of Chengdu","ror":"https://ror.org/00ebdgr24","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210093384"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China","institution_ids":["https://openalex.org/I4210093384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031355271","display_name":"Jie Su","orcid":"https://orcid.org/0000-0003-0275-0334"},"institutions":[{"id":"https://openalex.org/I4210093384","display_name":"Third People's Hospital of Chengdu","ror":"https://ror.org/00ebdgr24","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210093384"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Su","raw_affiliation_strings":["Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intensive Care Units, The Third People\u2019s Hospital, Chengdu, 610031, Sichuan, China","institution_ids":["https://openalex.org/I4210093384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433675","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-0718-8045"},"institutions":[{"id":"https://openalex.org/I4210097637","display_name":"Tangshan People's Hospital","ror":"https://ror.org/00xw2x114","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097637"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Department of Intensive Care Units, Tangshan People\u2019s Hospital, Tangshan, 063001, Hebei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intensive Care Units, Tangshan People\u2019s Hospital, Tangshan, 063001, Hebei, China","institution_ids":["https://openalex.org/I4210097637"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398565","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-5285-5743"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, 611756, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076976899"],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":null,"apc_paid":null,"fwci":4.568,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94671587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"63","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.9975000023841858,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9933000206947327,"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/T10745","display_name":"Heart Rate Variability and Autonomic Control","score":0.9476000070571899,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular 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":0.6134457588195801},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5122451186180115},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.476081520318985},{"id":"https://openalex.org/keywords/sepsis","display_name":"Sepsis","score":0.4750789999961853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34004783630371094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.338336706161499},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.335858017206192},{"id":"https://openalex.org/keywords/intensive-care-medicine","display_name":"Intensive care medicine","score":0.3286287784576416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.319149374961853},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.1671258509159088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15766820311546326},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0880441963672638}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6134457588195801},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5122451186180115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.476081520318985},{"id":"https://openalex.org/C2778384902","wikidata":"https://www.wikidata.org/wiki/Q183134","display_name":"Sepsis","level":2,"score":0.4750789999961853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34004783630371094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.338336706161499},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.335858017206192},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.3286287784576416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.319149374961853},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.1671258509159088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15766820311546326},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0880441963672638},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44230-025-00093-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-025-00093-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44230-025-00093-7.pdf","source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c7a5f8e615574737b3f54a8306fe77aa","is_oa":true,"landing_page_url":"https://doaj.org/article/c7a5f8e615574737b3f54a8306fe77aa","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Human-Centric Intelligent Systems, Vol 5, Iss 1, Pp 63-76 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44230-025-00093-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44230-025-00093-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44230-025-00093-7.pdf","source":{"id":"https://openalex.org/S4210207486","display_name":"Human-Centric Intelligent Systems","issn_l":"2667-1336","issn":["2667-1336"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Human-Centric Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407977713.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1497976081","https://openalex.org/W1967435431","https://openalex.org/W1981276685","https://openalex.org/W1997020095","https://openalex.org/W2005149470","https://openalex.org/W2055744632","https://openalex.org/W2057780602","https://openalex.org/W2091444911","https://openalex.org/W2096350581","https://openalex.org/W2109453625","https://openalex.org/W2128249288","https://openalex.org/W2145339207","https://openalex.org/W2160691650","https://openalex.org/W2164985671","https://openalex.org/W2198041288","https://openalex.org/W2280404143","https://openalex.org/W2344786740","https://openalex.org/W2396881363","https://openalex.org/W2550143307","https://openalex.org/W2746553466","https://openalex.org/W2883566781","https://openalex.org/W2896893468","https://openalex.org/W2898645858","https://openalex.org/W2964010366","https://openalex.org/W2997896107","https://openalex.org/W3005510897","https://openalex.org/W3009943557","https://openalex.org/W3012225633","https://openalex.org/W3022643593","https://openalex.org/W3023896219","https://openalex.org/W3087810330","https://openalex.org/W3112765753","https://openalex.org/W3127561923","https://openalex.org/W3132782787","https://openalex.org/W3137881228","https://openalex.org/W3140623462","https://openalex.org/W3197040406","https://openalex.org/W3209445167","https://openalex.org/W3211602965","https://openalex.org/W3212587319","https://openalex.org/W4205606665","https://openalex.org/W4206497039","https://openalex.org/W4223973398","https://openalex.org/W4225349188","https://openalex.org/W4253431854","https://openalex.org/W4293242440","https://openalex.org/W4293589470","https://openalex.org/W4300754431","https://openalex.org/W4312520804","https://openalex.org/W4313011033","https://openalex.org/W4323027663","https://openalex.org/W4367310095","https://openalex.org/W4375796951","https://openalex.org/W4375855901","https://openalex.org/W4387249883","https://openalex.org/W4390970754","https://openalex.org/W4392796722","https://openalex.org/W4392908308","https://openalex.org/W4396223901","https://openalex.org/W6600910721","https://openalex.org/W6814003322","https://openalex.org/W6824910662"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W4400410424","https://openalex.org/W4400177841"],"abstract_inverted_index":{"Abstract":[0],"In":[1,49,76],"critical":[2],"medicine,":[3],"data-driven":[4],"methods":[5,39],"that":[6,45],"assist":[7],"in":[8,114,163],"physician":[9],"decisions":[10],"often":[11,64],"require":[12],"accurate":[13],"responses":[14],"and":[15,31,85,161,171],"controllable":[16],"safety":[17,62,120],"risks.":[18],"Most":[19],"recent":[20],"reinforcement":[21,97],"learning":[22,98],"models":[23],"developed":[24],"for":[25,88],"clinical":[26],"research":[27],"typically":[28],"use":[29],"fixed-length":[30],"very":[32,59],"short":[33],"time":[34],"series":[35],"data.":[36],"Unfortunately,":[37],"such":[38,50],"generalize":[40],"poorly":[41],"on":[42,101,152],"variable-length":[43,143],"data":[44,168],"can":[46,139,173],"be":[47,174],"overlong.":[48],"as":[51],"case,":[52],"a":[53,118],"single":[54],"final":[55],"reward":[56],"signal":[57],"appears":[58],"sparse.":[60],"Meanwhile,":[61],"is":[63],"overlooked":[65],"by":[66,130],"many":[67],"models,":[68],"leading":[69],"them":[70],"to":[71,82],"make":[72],"excessively":[73],"extreme":[74],"recommendations.":[75],"this":[77],"paper,":[78],"we":[79,156],"study":[80],"how":[81],"recommend":[83],"effective":[84],"safe":[86],"treatments":[87,113],"critically":[89],"ill":[90],"septic":[91],"patients.":[92],"We":[93,122],"develop":[94],"an":[95],"offline":[96],"model":[99,126],"based":[100],"CQL":[102],"(Conservative":[103],"Q-Learning),":[104],"which":[105],"underestimates":[106],"the":[107,125,133,153,158],"expected":[108],"rewards":[109,129],"of":[110,167],"rarely":[111],"seen":[112],"data,":[115],"thus":[116],"enjoying":[117],"high":[119],"standard.":[121],"further":[123],"enhance":[124],"with":[127,142,145],"intermediate":[128],"particularly":[131],"using":[132],"Apache":[134],"II":[135],"scoring":[136],"system.":[137],"This":[138],"effectively":[140],"deal":[141],"episodes":[144],"sparse":[146],"rewards.":[147],"By":[148],"performing":[149],"extensive":[150],"experiments":[151],"MIMIC-III":[154],"database,":[155],"demonstrated":[157],"enhanced":[159],"performance":[160],"robustness":[162],"safety.":[164],"Our":[165],"code":[166],"extraction,":[169],"preprocessing,":[170],"modeling":[172],"found":[175],"at":[176],"https://github.com/OOPSDINOSAUR/RL_safety_model":[177],".":[178]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}