{"id":"https://openalex.org/W7225633571","doi":"https://doi.org/10.21203/rs.3.rs-11380217/v1","title":"Dual-Gated Double Deep Q-Networks for Sepsis Resuscitation: An Offline Reinforcement Learning Framework for Hemodynamic Management in Intensive Care","display_name":"Dual-Gated Double Deep Q-Networks for Sepsis Resuscitation: An Offline Reinforcement Learning Framework for Hemodynamic Management in Intensive Care","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225633571","doi":"https://doi.org/10.21203/rs.3.rs-11380217/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11380217/v1","doi":"https://doi.org/10.21203/rs.3.rs-11380217/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11380217/v1","pdf_url":"https://www.researchsquare.com/article/rs-11380217/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11380217/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122847169","display_name":"DEEPAK YADAV","orcid":"https://orcid.org/0009-0007-1476-5118","observed_orcids":["https://orcid.org/0009-0007-1476-5118"]},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"DEEPAK Yadav","raw_affiliation_strings":["Indian Institute of Technology Roorkee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081953081","display_name":"Millie Pant","orcid":"https://orcid.org/0000-0002-7668-7887","observed_orcids":["https://orcid.org/0000-0002-7668-7887"]},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Millie Pant","raw_affiliation_strings":["Indian Institute of Technology Roorkee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021797294","display_name":"Kusum Deep","orcid":"https://orcid.org/0000-0001-5821-2696","observed_orcids":["https://orcid.org/0000-0001-5821-2696"]},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kusum Deep","raw_affiliation_strings":["Indian Institute of Technology Roorkee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.6937999725341797,"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"}},"topics":[{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.6937999725341797,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.2930000126361847,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/sepsis-resuscitation","display_name":"sepsis resuscitation","score":0.9649999737739563},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.824999988079071},{"id":"https://openalex.org/keywords/double-deep-q-network","display_name":"double deep Q-network","score":0.8899999856948853},{"id":"https://openalex.org/keywords/dual-gating","display_name":"dual gating","score":0.6129999756813049},{"id":"https://openalex.org/keywords/confidence-gating","display_name":"confidence gating","score":0.8519999980926514},{"id":"https://openalex.org/keywords/overestimation-bias","display_name":"overestimation bias","score":0.7429999709129333},{"id":"https://openalex.org/keywords/vasopressor-dosing","display_name":"vasopressor dosing","score":0.8299999833106995},{"id":"https://openalex.org/keywords/fluid-resuscitation","display_name":"fluid resuscitation","score":0.847000002861023},{"id":"https://openalex.org/keywords/hemodynamic-management","display_name":"hemodynamic management","score":0.871999979019165},{"id":"https://openalex.org/keywords/critical-care","display_name":"intensive care","score":0.675000011920929},{"id":"https://openalex.org/keywords/mimic-iv","display_name":"MIMIC-IV","score":0.9079999923706055}],"concepts":[{"id":"https://openalex.org/C2987404301","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care","level":2,"score":0.6711000204086304},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6503000259399414},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.6315000057220459},{"id":"https://openalex.org/C2778384902","wikidata":"https://www.wikidata.org/wiki/Q183134","display_name":"Sepsis","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C177713679","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Intensive care medicine","level":1,"score":0.6018999814987183},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4023999869823456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34540000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393999934196472},{"id":"https://openalex.org/C178853913","wikidata":"https://www.wikidata.org/wiki/Q1642137","display_name":"Hemodynamics","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2991859549","wikidata":"https://www.wikidata.org/wiki/Q679690","display_name":"Critically ill","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C203915360","wikidata":"https://www.wikidata.org/wiki/Q352454","display_name":"Critical care nursing","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C2776376669","wikidata":"https://www.wikidata.org/wiki/Q5094647","display_name":"Intensive care unit","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C66283442","wikidata":"https://www.wikidata.org/wiki/Q1389268","display_name":"Failure mode and effects analysis","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11380217/v1","doi":"https://doi.org/10.21203/rs.3.rs-11380217/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11380217/v1","pdf_url":"https://www.researchsquare.com/article/rs-11380217/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11380217/v1","doi":"https://doi.org/10.21203/rs.3.rs-11380217/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11380217/v1","pdf_url":"https://www.researchsquare.com/article/rs-11380217/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.9391000270843506,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225633571.pdf","grobid_xml":"https://content.openalex.org/works/W7225633571.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160869870","https://openalex.org/W7203660277","https://openalex.org/W4390585316","https://openalex.org/W3180809143","https://openalex.org/W7125827026","https://openalex.org/W7155648667","https://openalex.org/W4295073588","https://openalex.org/W3134800431","https://openalex.org/W4323027598","https://openalex.org/W4293589470"],"abstract_inverted_index":{"Abstract":[0],"Sepsis":[1],"is":[2,42],"a":[3,116,149,195],"serious":[4],"condition":[5],"caused":[6],"by":[7],"an":[8,95,156],"uncontrolled":[9],"body":[10],"response":[11],"to":[12,44,48,61,122,140,159,177,215,255],"infection,":[13],"and":[14,36,57,76,82,135,167,183,236,246,262],"it":[15],"remains":[16],"one":[17],"of":[18,22,33,133,138,251],"the":[19,30,39,105,136,179],"primary":[20],"cause":[21],"death":[23],"in":[24,64,127,249,258,264],"intensive":[25],"care":[26,129],"units":[27],"worldwide.":[28],"Giving":[29],"right":[31,40],"amount":[32],"intravenous":[34],"fluids":[35],"vasopressors":[37],"at":[38],"time":[41,93],"critical":[43,128],"keep":[45,178],"blood":[46],"flowing":[47],"vital":[49],"organs.":[50],"However,":[51],"current":[52],"clinical":[53,102],"guidelines":[54],"are":[55],"broad":[56],"inconsistent.":[58],"This":[59],"leads":[60],"large":[62],"differences":[63],"practice,":[65],"where":[66],"giving":[67],"either":[68],"too":[69,73],"little":[70],"treatment":[71,231],"or":[72],"much":[74],"fluid":[75,245],"medication":[77],"can":[78],"worsen":[79],"organ":[80],"failure":[81],"increase":[83],"mortality.":[84],"In":[85,170],"this":[86],"work,":[87],"we":[88,172],"formulate":[89],"sepsis":[90],"management":[91],"over":[92],"as":[94,192,194],"offline":[96],"Markov":[97],"Decision":[98],"Process":[99],"using":[100],"real":[101],"data":[103,218],"from":[104,187],"MIMIC-IV":[106],"v3.0":[107],"database.":[108],"We":[109,206],"introduce":[110],"Dual-Gated":[111],"Dueling":[112],"Double":[113,164],"Deep":[114],"Q-Networks,":[115],"model-free":[117],"reinforcement":[118],"learning":[119],"method":[120],"developed":[121],"solve":[123],"two":[124],"major":[125],"issues":[126],"learning:":[130],"severe":[131],"overestimation":[132,234],"Q-values":[134],"tendency":[137],"models":[139,261],"recommend":[141],"dangerously":[142],"high":[143],"doses.":[144],"The":[145,221],"proposed":[146,226],"network":[147],"uses":[148],"learned":[150],"confidence":[151],"gating":[152],"mechanism":[153],"combined":[154],"with":[155],"uncertainty":[157],"gate":[158],"adjust":[160],"smoothly":[161],"between":[162],"standard":[163,259],"DQN":[165],"targets":[166],"greedy":[168],"updates.":[169],"addition,":[171],"add":[173],"normalized":[174],"advantage":[175],"centering":[176],"calculations":[180],"mathematically":[181],"stable":[182,230],"prevent":[184],"risky":[185],"treatments":[186],"distorting":[188],"baseline":[189,260],"state":[190],"values,":[191],"well":[193],"penalty":[196],"term":[197],"that":[198,224],"encourages":[199],"lower":[200],"doses":[201],"based":[202],"on":[203,210],"patient":[204,212,252],"severity.":[205],"evaluated":[207],"our":[208,225],"model":[209,227],"separate":[211],"test":[213],"sets":[214],"ensure":[216],"no":[217],"leakage":[219],"occurred.":[220],"results":[222],"show":[223],"produces":[228],"more":[229,239],"policies,":[232],"reduces":[233],"bias,":[235],"provides":[237],"safer,":[238],"conservative":[240,244],"dosage":[241],"recommendations,":[242],"suggesting":[243],"vasopressor":[247],"amounts":[248],"43.3%":[250],"states":[253],"compared":[254],"roughly":[256],"21%":[257],"19%":[263],"actual":[265],"clinician":[266],"practice.":[267]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}