{"id":"https://openalex.org/W7214079356","doi":"https://doi.org/10.64898/2026.09.22.26363595","title":"An LLM-Based Auditing Framework for Targeted Quality Assurance in Cancer Registries","display_name":"An LLM-Based Auditing Framework for Targeted Quality Assurance in Cancer Registries","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214079356","doi":"https://doi.org/10.64898/2026.09.22.26363595"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.22.26363595","doi":"https://doi.org/10.64898/2026.09.22.26363595","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.26363595","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.22.26363595.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","license_id":"https://openalex.org/licenses/cc-by","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/2026/09/23/2026.09.22.26363595.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048173103","display_name":"Maryam Seifaddini","orcid":"https://orcid.org/0000-0001-5179-5526","observed_orcids":["https://orcid.org/0000-0001-5179-5526"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Seifaddini","raw_affiliation_strings":["MU Institute for Data Science and Informatics, University of Missouri, MO, United States","Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MU Institute for Data Science and Informatics, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065912316","display_name":"Mohammad Beheshti","orcid":"https://orcid.org/0000-0002-6095-1743","observed_orcids":["https://orcid.org/0000-0002-6095-1743"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Beheshti","raw_affiliation_strings":["MU Institute for Data Science and Informatics, University of Missouri, MO, United States","Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MU Institute for Data Science and Informatics, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135864869","display_name":"Jeffrey Steffens","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Steffens","raw_affiliation_strings":["Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152503562","display_name":"Deborah Carnagey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deborah Carnagey","raw_affiliation_strings":["Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084117084","display_name":"Magda Esebua","orcid":"https://orcid.org/0000-0001-5884-9603","observed_orcids":["https://orcid.org/0000-0001-5884-9603"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magda Esebua","raw_affiliation_strings":["Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036835784","display_name":"Mark Wakefield","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Wakefield","raw_affiliation_strings":["Department of Surgery, School of Medicine, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Surgery, School of Medicine, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072004214","display_name":"Iris Zachary","orcid":"https://orcid.org/0000-0002-8159-807X","observed_orcids":["https://orcid.org/0000-0002-8159-807X"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iris Zachary","raw_affiliation_strings":["MU Institute for Data Science and Informatics, University of Missouri, MO, United States","Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MU Institute for Data Science and Informatics, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"Missouri Cancer Registry and Research Center, Department of Public Health, College of Health Sciences, University of Missouri, MO, United States","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072004214"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"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/T14400","display_name":"Medical Coding and Health Information","score":0.41499999165534973,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T14400","display_name":"Medical Coding and Health Information","score":0.41499999165534973,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10556","display_name":"Global Cancer Incidence and Screening","score":0.21780000627040863,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.07819999754428864,"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/cancer-registry","display_name":"cancer registry","score":0.9900000095367432},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"quality assurance","score":0.9359999895095825},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8920000195503235},{"id":"https://openalex.org/keywords/clinical-text-extraction","display_name":"clinical text extraction","score":0.7310000061988831},{"id":"https://openalex.org/keywords/breast-cancer-biomarkers","display_name":"breast cancer biomarkers","score":0.7950000166893005},{"id":"https://openalex.org/keywords/prostate-cancer","display_name":"prostate cancer","score":0.9660000205039978},{"id":"https://openalex.org/keywords/gleason-score","display_name":"Gleason score","score":0.859000027179718},{"id":"https://openalex.org/keywords/psa","display_name":"PSA","score":0.8889999985694885},{"id":"https://openalex.org/keywords/data-discrepancies","display_name":"data discrepancies","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7116000056266785},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.6575999855995178},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.6427000164985657},{"id":"https://openalex.org/C2778527826","wikidata":"https://www.wikidata.org/wiki/Q1787017","display_name":"Cancer registry","level":3,"score":0.614799976348877},{"id":"https://openalex.org/C2780192828","wikidata":"https://www.wikidata.org/wiki/Q181257","display_name":"Prostate cancer","level":3,"score":0.5931000113487244},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.5292999744415283},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33329999446868896},{"id":"https://openalex.org/C512399662","wikidata":"https://www.wikidata.org/wiki/Q3505712","display_name":"Family medicine","level":1,"score":0.32820001244544983},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2776579137","wikidata":"https://www.wikidata.org/wiki/Q5133817","display_name":"Clinical audit","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2776235491","wikidata":"https://www.wikidata.org/wiki/Q9625","display_name":"Prostate","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C29456083","wikidata":"https://www.wikidata.org/wiki/Q1221899","display_name":"Gynecology","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.22.26363595","doi":"https://doi.org/10.64898/2026.09.22.26363595","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.26363595","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.22.26363595.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.22.26363595","doi":"https://doi.org/10.64898/2026.09.22.26363595","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.22.26363595","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/23/2026.09.22.26363595.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","license_id":"https://openalex.org/licenses/cc-by","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","display_name":"Good health and well-being","score":0.9537000060081482}],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000371069","display_name":null,"funder_award_id":"NU58DP007130-05","funder_id":"https://openalex.org/F4320315861","funder_display_name":"Missouri Department of Health and Senior Services"}],"funders":[{"id":"https://openalex.org/F4320309568","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06"},{"id":"https://openalex.org/F4320315861","display_name":"Missouri Department of Health and Senior Services","ror":"https://ror.org/041qkag73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214079356.pdf","grobid_xml":"https://content.openalex.org/works/W7214079356.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4416419445"],"related_works":["https://openalex.org/W7166559474","https://openalex.org/W7162569332","https://openalex.org/W7135037086","https://openalex.org/W4404622670","https://openalex.org/W4416358908","https://openalex.org/W7136898288","https://openalex.org/W7162663023","https://openalex.org/W4416821373","https://openalex.org/W4394062224","https://openalex.org/W2015138852"],"abstract_inverted_index":{"Abstract":[0],"Cancer":[1],"registries":[2],"are":[3,241,253],"essential":[4],"for":[5,63,87,151,157,176,255,278],"population-level":[6],"surveillance,":[7],"epidemiologic":[8],"research,":[9],"and":[10,32,84,100,106,113,135,155,216,224,247,250],"public":[11],"health":[12],"planning,":[13],"but":[14],"their":[15,244],"accuracy":[16],"depends":[17],"on":[18,39],"human":[19],"review":[20,259],"of":[21,44,117,194,212],"key":[22],"variables":[23],"documented":[24],"in":[25,96,122,144,231],"unstructured":[26],"clinical":[27,77],"text.":[28],"This":[29],"is":[30],"time-consuming,":[31],"current":[33],"quality":[34],"assurance":[35],"(QA)":[36],"typically":[37],"relies":[38],"reviewing":[40],"fewer":[41],"than":[42,204],"10%":[43],"records":[45,213,261],"at":[46,153,159],"random,":[47],"which":[48],"can":[49],"miss":[50],"facility-":[51],"or":[52],"time-specific":[53],"errors.":[54],"We":[55],"developed":[56],"a":[57,97,209,227],"large":[58],"language":[59],"model":[60,103],"(LLM)-based":[61],"framework":[62,69,221,268],"targeted":[64],"cancer":[65,130,147,164,279],"registry":[66,82,142],"QA.":[67],"The":[68],"uses":[70],"LLMs":[71,92],"to":[72,111,208,235,243,264,274],"extract":[73],"biomarker":[74],"values":[75,143,240],"from":[76],"text,":[78,246],"compares":[79],"them":[80],"with":[81,169],"entries,":[83],"flags":[85,200],"disagreements":[86,223],"expert":[88,237],"review.":[89,238],"Six":[90],"open-source":[91],"were":[93],"benchmarked":[94],"locally":[95],"privacy-preserving":[98],"environment,":[99],"the":[101,118,123,127,137,166,170,182,191,220,267],"best":[102],"per":[104],"site":[105],"report":[107],"type":[108],"was":[109,149],"applied":[110],"breast":[112,129,146,215],"prostate":[114,163,218],"cancer,":[115],"two":[116],"most":[119,262],"common":[120],"cancers":[121],"United":[124],"States.":[125],"For":[126],"four":[128],"biomarkers":[131],"ER,":[132],"PR,":[133],"HER2,":[134],"Ki-67,":[136],"disagreement":[138,167],"rate":[139,168],"against":[140],"quality-assured":[141],"1,852":[145],"cases":[148],"lowest":[150],"ER":[152],"1.67%":[154],"highest":[156],"Ki-67":[158],"9.18%.":[160],"In":[161],"920":[162],"cases,":[165],"deployed":[171],"models":[172],"stayed":[173],"below":[174],"8%":[175],"every":[177],"categorical":[178,205],"Gleason":[179],"variable,":[180],"while":[181],"exact-value":[183],"PSA":[184,188,199],"metric":[185],"reached":[186],"17.28%.":[187],"therefore":[189],"generated":[190],"largest":[192],"volume":[193],"candidate":[195],"discrepancies,":[196,266],"though":[197],"individual":[198],"require":[201],"more":[202],"corroboration":[203],"flags.":[206],"Applied":[207],"full":[210],"year":[211],"(11,740":[214],"6,792":[217],"cases),":[219],"flagged":[222],"assigned":[225],"each":[226],"probable":[228],"cause,":[229],"grounded":[230],"NAACCR":[232],"coding":[233],"rules,":[234],"prioritize":[236],"Extracted":[239],"linked":[242],"supporting":[245],"model,":[248],"prompt,":[249],"pipeline":[251],"versions":[252],"logged":[254],"reproducibility.":[256],"By":[257],"directing":[258],"toward":[260],"likely":[263],"contain":[265],"offers":[269],"an":[270],"efficient,":[271],"auditable":[272],"alternative":[273],"random":[275],"QA":[276],"sampling":[277],"registries.":[280]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-24T00:00:00"}
