{"id":"https://openalex.org/W7223457014","doi":"https://doi.org/10.64898/2026.10.23.26366163","title":"Digital Twin Workflow for Continuous Glucose Forecasting: Real-Time Data Assimilation Using Reinforcement Learning","display_name":"Digital Twin Workflow for Continuous Glucose Forecasting: Real-Time Data Assimilation Using Reinforcement Learning","publication_year":2026,"publication_date":"2026-10-24","ids":{"openalex":"https://openalex.org/W7223457014","doi":"https://doi.org/10.64898/2026.10.23.26366163"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.23.26366163","doi":"https://doi.org/10.64898/2026.10.23.26366163","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.23.26366163","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/24/2026.10.23.26366163.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","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.medrxiv.org/content/medrxiv/early/2026/10/24/2026.10.23.26366163.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112309566","display_name":"Cao Xiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Cao","raw_affiliation_strings":["Department of Mathematics, University of South Carolina, Columbia, SC 29208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of South Carolina, Columbia, SC 29208, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035473719","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0001-9928-2703","observed_orcids":["https://orcid.org/0000-0001-9928-2703","https://orcid.org/0000-0003-3418-8809","https://orcid.org/0000-0002-0501-1599","https://orcid.org/0000-0002-1328-8571"]},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Department of Mathematics, University of South Carolina, Columbia, SC 29208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of South Carolina, Columbia, SC 29208, USA","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035473719"],"corresponding_institution_ids":["https://openalex.org/I155781252"],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9067000150680542,"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":0.9067000150680542,"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/T10560","display_name":"Diabetes Management and Research","score":0.03500000014901161,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"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/T11623","display_name":"Hyperglycemia and glycemic control in critically ill and hospitalized patients","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/2712","display_name":"Endocrinology, Diabetes and Metabolism"},"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/digital-twin","display_name":"digital twin","score":0.8849999904632568},{"id":"https://openalex.org/keywords/continuous-glucose-monitoring","display_name":"continuous glucose monitoring","score":0.843999981880188},{"id":"https://openalex.org/keywords/blood-glucose-prediction","display_name":"blood glucose prediction","score":0.8970000147819519},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6669999957084656},{"id":"https://openalex.org/keywords/residual-correction","display_name":"residual correction","score":0.777999997138977},{"id":"https://openalex.org/keywords/patchtst","display_name":"PatchTST","score":0.8970000147819519},{"id":"https://openalex.org/keywords/data-assimilation","display_name":"data assimilation","score":0.7110000252723694},{"id":"https://openalex.org/keywords/sepsis","display_name":"sepsis","score":0.7630000114440918},{"id":"https://openalex.org/keywords/critically-ill-patients","display_name":"critically ill patients","score":0.9259999990463257},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8061000108718872},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7993000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421000003814697},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7167999744415283},{"id":"https://openalex.org/C24552861","wikidata":"https://www.wikidata.org/wiki/Q2670177","display_name":"Data assimilation","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5396000146865845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C2780468074","wikidata":"https://www.wikidata.org/wiki/Q16628824","display_name":"Digital learning","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.23.26366163","doi":"https://doi.org/10.64898/2026.10.23.26366163","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.23.26366163","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/24/2026.10.23.26366163.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.23.26366163","doi":"https://doi.org/10.64898/2026.10.23.26366163","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.23.26366163","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/24/2026.10.23.26366163.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.5683000087738037,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G5554097790","display_name":"RII Track-1: AI-enabled Devices for the Advancement of Personalized and Transformative Healthcare in South Carolina","funder_award_id":"2242812","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8921292286","display_name":"RTG: Mathematical Foundation of Data Science at University of South Carolina","funder_award_id":"2038080","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223457014.pdf","grobid_xml":"https://content.openalex.org/works/W7223457014.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215079506","https://openalex.org/W7221758551","https://openalex.org/W7161725761","https://openalex.org/W7134930873","https://openalex.org/W7133486539","https://openalex.org/W4414702782","https://openalex.org/W7163387033","https://openalex.org/W7132837465","https://openalex.org/W4403096591","https://openalex.org/W7151409241"],"abstract_inverted_index":{"Abstract":[0],"Digital":[1],"twins":[2],"for":[3,9,57,168],"physiological":[4],"forecasting":[5,127],"require":[6],"robust":[7],"mechanisms":[8],"continuously":[10],"assimilating":[11],"streaming":[12],"data":[13,111,171],"and":[14,65,96,143,151],"adapting":[15],"to":[16,75],"patient-specific":[17,130,183],"dynamics.":[18],"Threshold-triggered":[19],"model":[20,49],"updates":[21],"can":[22],"restore":[23],"predictive":[24,179],"performance":[25],"after":[26],"substantial":[27],"drift,":[28],"but":[29],"their":[30],"reactive":[31,154],"nature":[32],"limits":[33],"continuous":[34,108],"adaptation.":[35],"We":[36,90],"propose":[37],"a":[38,45,61,86,97,165],"proactive":[39],"digital":[40,155],"twin":[41,156],"framework":[42],"that":[43,173],"couples":[44],"pretrained":[46,123],"PatchTST":[47],"foundation":[48,176],"with":[50,80,103,117,147,186],"an":[51,93],"Actor\u2013Critic":[52],"reinforcement":[53,162],"learning":[54,163],"(RL)":[55],"agent":[56,70,125],"residual":[58,67,161],"correction.":[59],"Using":[60],"30-minute":[62],"look-back":[63],"window":[64],"recent":[66],"history,":[68],"the":[69,76,122,148,175],"generates":[71],"bounded":[72],"corrections":[73],"(\u00b10.05)":[74],"first-step":[77],"baseline":[78,150],"forecast,":[79],"corrected":[81],"predictions":[82],"recursively":[83],"propagated":[84],"over":[85],"15-":[87],"step":[88],"horizon.":[89],"evaluate":[91],"both":[92],"RL-only":[94],"workflow":[95,99],"hybrid":[98],"combining":[100],"RL":[101,124],"correction":[102],"threshold-triggered":[104],"fine-tuning":[105],"using":[106],"minute-by-minute":[107],"glucose":[109],"monitoring":[110],"from":[112],"10":[113],"critically":[114],"ill":[115],"patients":[116],"sepsis.":[118],"Across":[119],"all":[120],"patients,":[121],"improves":[126],"accuracy":[128],"without":[129],"retraining.":[131],"Both":[132],"workflows":[133],"reduce":[134],"trajectory-averaged":[135],"mean":[136],"absolute":[137],"percentage":[138],"error,":[139,142],"ensemble":[140],"relative":[141],"maximum":[144],"errors":[145],"compared":[146],"uncorrected":[149],"previously":[152],"developed":[153],"models.":[157],"These":[158],"findings":[159],"support":[160],"as":[164],"lightweight":[166],"mechanism":[167],"continuous,":[169],"real-time":[170],"assimilation":[172],"preserves":[174],"model\u2019s":[177],"global":[178],"prior":[180],"while":[181],"enabling":[182],"forecast":[184],"adaptation,":[185],"potential":[187],"applications":[188],"in":[189],"critical":[190],"care":[191],"decision":[192],"support.":[193]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-25T00:00:00"}