{"id":"https://openalex.org/W7138129921","doi":"https://doi.org/10.48550/arxiv.2603.13275","title":"PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation","display_name":"PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7138129921","doi":"https://doi.org/10.48550/arxiv.2603.13275"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13275","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.13275","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126761488","display_name":"Wanyin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wanyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695814","display_name":"Kanxue Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kanxue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704298","display_name":"Baosheng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Baosheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721994","display_name":"Haoyun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Haoyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739351","display_name":"Yibing Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Yibing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722865","display_name":"Dapeng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Dapeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129749140","display_name":"Hua Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7674999833106995,"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":0.7674999833106995,"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":0.06700000166893005,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.02889999933540821,"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/bayesian-probability","display_name":"Bayesian probability","score":0.5956000089645386},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5950999855995178},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4830999970436096},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48179998993873596},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41510000824928284},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.41290000081062317},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.382099986076355},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.3382999897003174}],"concepts":[{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5956000089645386},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5719000101089478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.569599986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687000155448914},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4830999970436096},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41510000824928284},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3287000060081482},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.2980000078678131},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13275","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13275","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"prediction":[1],"of":[2,106],"surgical":[3,124],"duration":[4,187],"is":[5,108],"pivotal":[6],"for":[7,34,114],"hospital":[8],"resource":[9],"management.":[10],"Although":[11],"recent":[12],"supervised":[13,232],"learning":[14,17],"approaches-from":[15],"machine":[16],"(ML)":[18],"to":[19,73,93,109,153,165,173,215,222],"fine-tuned":[20],"large":[21],"language":[22],"models":[23],"(LLMs)-have":[24],"shown":[25],"strong":[26,236],"performance,":[27],"they":[28],"remain":[29],"constrained":[30],"by":[31,213],"the":[32,115,119,161,166],"need":[33],"high-quality":[35],"labeled":[36],"data":[37],"and":[38,63,71,89,101,126,184,204,217,238],"computationally":[39],"intensive":[40],"training.":[41],"In":[42],"contrast,":[43],"zero-shot":[44,225],"LLM":[45,95,176],"inference":[46],"offers":[47],"a":[48,82,141],"promising":[49],"training-free":[50],"alternative":[51],"but":[52],"it":[53,227],"lacks":[54],"grounding":[55],"in":[56,97],"institution-specific":[57,98],"clinical":[58,99,128,138,195],"context":[59,163],"(e.g.,":[60],"local":[61],"demographics":[62],"case-mix":[64],"distributions),":[65],"making":[66],"its":[67],"predictions":[68,96,177],"clinically":[69,121,155,185],"misaligned":[70],"prone":[72],"instability.":[74],"To":[75,131],"address":[76],"these":[77],"limitations,":[78],"we":[79],"present":[80],"PREBA,":[81],"retrieval-augmented":[83],"framework":[84],"that":[85],"integrates":[86],"PCA-weighted":[87,151],"retrieval":[88,152],"Bayesian":[90,171],"averaging":[91,172],"aggregation":[92],"ground":[94],"evidence":[100,162],"statistical":[102,129,180],"priors.":[103,130],"The":[104],"core":[105],"PREBA":[107,134,169,191,206],"construct":[110],"an":[111],"evidence-based":[112],"prompt":[113],"LLM,":[116],"comprising":[117],"(1)":[118],"most":[120],"similar":[122],"historical":[123,157],"cases":[125],"(2)":[127],"achieve":[132],"this,":[133],"first":[135],"encodes":[136],"heterogeneous":[137],"features":[139],"into":[140],"unified":[142],"representation":[143],"space":[144],"enabling":[145],"systematic":[146],"retrieval.":[147],"It":[148],"then":[149],"performs":[150],"identify":[154],"relevant":[156],"cases,":[158],"which":[159],"form":[160],"supplied":[164],"LLM.":[167],"Finally,":[168],"applies":[170],"fuse":[174],"multi-round":[175],"with":[178,231],"population-level":[179],"priors,":[181],"yielding":[182],"calibrated":[183],"plausible":[186],"estimates.":[188],"We":[189],"evaluate":[190],"on":[192],"two":[193],"real-world":[194],"datasets":[196],"using":[197],"three":[198],"state-of-the-art":[199],"LLMs,":[200],"including":[201],"Qwen3,":[202],"DeepSeek-R1,":[203],"HuatuoGPT-o1.":[205],"significantly":[207],"improves":[208],"performance-for":[209],"instance,":[210],"reducing":[211],"MAE":[212],"up":[214],"40%":[216],"raising":[218],"R^2":[219],"from":[220],"-0.13":[221],"0.62":[223],"over":[224],"inference-and":[226],"achieves":[228],"accuracy":[229],"competitive":[230],"ML":[233],"methods,":[234],"demonstrating":[235],"effectiveness":[237],"generalization.":[239]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}