{"id":"https://openalex.org/W7220964696","doi":"https://doi.org/10.64898/2026.10.07.26364402","title":"Large Language Models for Structured Information Extraction from German Histopathology Reports \u2013 Hepatocellular Carcinoma","display_name":"Large Language Models for Structured Information Extraction from German Histopathology Reports \u2013 Hepatocellular Carcinoma","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7220964696","doi":"https://doi.org/10.64898/2026.10.07.26364402"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.07.26364402","doi":"https://doi.org/10.64898/2026.10.07.26364402","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.26364402","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/08/2026.10.07.26364402.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":"submittedVersion","is_accepted":false,"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/2026/10/08/2026.10.07.26364402.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157928241","display_name":"Niklas Koch","orcid":"https://orcid.org/0009-0006-3989-391X","observed_orcids":["https://orcid.org/0009-0006-3989-391X"]},"institutions":[{"id":"https://openalex.org/I4210162051","display_name":"University Hospital Carl Gustav Carus","ror":"https://ror.org/04za5zm41","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210162051"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"N. Koch","raw_affiliation_strings":["Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany"],"raw_orcid":"https://orcid.org/0009-0006-3989-391X","affiliations":[{"raw_affiliation_string":"Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157935016","display_name":"Nora Hartmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210162051","display_name":"University Hospital Carl Gustav Carus","ror":"https://ror.org/04za5zm41","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210162051"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"N. Hartmann","raw_affiliation_strings":["Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119451361","display_name":"Alexander M\u00e4nnel","orcid":"https://orcid.org/0009-0009-5799-3350","observed_orcids":["https://orcid.org/0009-0009-5799-3350"]},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. M\u00e4nnel","raw_affiliation_strings":["Technical University Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071928750","display_name":"Gustavo Bruno Baretton","orcid":"https://orcid.org/0000-0002-4051-6306","observed_orcids":["https://orcid.org/0000-0002-4051-6306"]},"institutions":[{"id":"https://openalex.org/I4210162051","display_name":"University Hospital Carl Gustav Carus","ror":"https://ror.org/04za5zm41","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210162051"]},{"id":"https://openalex.org/I4387153526","display_name":"Nationales Centrum f\u00fcr Tumorerkrankungen Dresden","ror":"https://ror.org/01zy07c70","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529","https://openalex.org/I2801798921","https://openalex.org/I4210162051","https://openalex.org/I4387153526","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G. Baretton","raw_affiliation_strings":["Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","Maldi Imaging Unit, National Center for Tumor Diseases (NCT) Dresden, Dresden, Germany","Tumor and Normal Tissue Bank of the UCC/NCT Dresden, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"]},{"raw_affiliation_string":"Maldi Imaging Unit, National Center for Tumor Diseases (NCT) Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4387153526"]},{"raw_affiliation_string":"Tumor and Normal Tissue Bank of the UCC/NCT Dresden, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I4387153526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062500103","display_name":"Daniela Aust","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210162051","display_name":"University Hospital Carl Gustav Carus","ror":"https://ror.org/04za5zm41","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210162051"]},{"id":"https://openalex.org/I4387153526","display_name":"Nationales Centrum f\u00fcr Tumorerkrankungen Dresden","ror":"https://ror.org/01zy07c70","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529","https://openalex.org/I2801798921","https://openalex.org/I4210162051","https://openalex.org/I4387153526","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Aust","raw_affiliation_strings":["Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","Tumor and Normal Tissue Bank of the UCC/NCT Dresden, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"]},{"raw_affiliation_string":"Tumor and Normal Tissue Bank of the UCC/NCT Dresden, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I4387153526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011990169","display_name":"Pia H\u00f6nscheid","orcid":"https://orcid.org/0000-0002-4179-3233","observed_orcids":["https://orcid.org/0000-0002-4179-3233"]},"institutions":[{"id":"https://openalex.org/I4210162051","display_name":"University Hospital Carl Gustav Carus","ror":"https://ror.org/04za5zm41","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210162051"]},{"id":"https://openalex.org/I4387153526","display_name":"Nationales Centrum f\u00fcr Tumorerkrankungen Dresden","ror":"https://ror.org/01zy07c70","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I1305996414","https://openalex.org/I17937529","https://openalex.org/I2801798921","https://openalex.org/I4210162051","https://openalex.org/I4387153526","https://openalex.org/I78650965"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"P. H\u00f6nscheid","raw_affiliation_strings":["Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","Maldi Imaging Unit, National Center for Tumor Diseases (NCT) Dresden, Dresden, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4179-3233","affiliations":[{"raw_affiliation_string":"Institute of Pathology, University Hospital Carl Gustav Carus, Technical University Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"]},{"raw_affiliation_string":"Maldi Imaging Unit, National Center for Tumor Diseases (NCT) Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4387153526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5157928241"],"corresponding_institution_ids":["https://openalex.org/I4210162051","https://openalex.org/I78650965"],"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5913000106811523,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5913000106811523,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.22220000624656677,"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":0.07100000232458115,"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/large-language-models","display_name":"large language models","score":0.9020000100135803},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.8769999742507935},{"id":"https://openalex.org/keywords/histopathology-reports","display_name":"histopathology reports","score":0.9300000071525574},{"id":"https://openalex.org/keywords/hepatocellular-carcinoma","display_name":"hepatocellular carcinoma","score":0.9990000128746033},{"id":"https://openalex.org/keywords/german-texts","display_name":"German texts","score":0.45100000500679016},{"id":"https://openalex.org/keywords/privacy-preserving-data-processing","display_name":"privacy-preserving data processing","score":0.578000009059906},{"id":"https://openalex.org/keywords/local-deployment","display_name":"local deployment","score":0.5270000100135803},{"id":"https://openalex.org/keywords/gatekeeper-model","display_name":"gatekeeper model","score":0.8009999990463257},{"id":"https://openalex.org/keywords/tumor-node-metastasis-staging","display_name":"tumor-node-metastasis staging","score":0.7319999933242798},{"id":"https://openalex.org/keywords/histological-grading","display_name":"histological grading","score":0.9850000143051147},{"id":"https://openalex.org/keywords/vascular-invasion","display_name":"vascular invasion","score":0.9729999899864197},{"id":"https://openalex.org/keywords/immunohistochemistry","display_name":"immunohistochemistry","score":0.8610000014305115},{"id":"https://openalex.org/keywords/clinical-registries","display_name":"clinical registries","score":0.625},{"id":"https://openalex.org/keywords/automated-data-curation","display_name":"automated data curation","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6773999929428101},{"id":"https://openalex.org/C2778019345","wikidata":"https://www.wikidata.org/wiki/Q1148337","display_name":"Hepatocellular carcinoma","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3889000117778778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3531000018119812},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C544855455","wikidata":"https://www.wikidata.org/wiki/Q1070952","display_name":"Histopathology","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.07.26364402","doi":"https://doi.org/10.64898/2026.10.07.26364402","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.26364402","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/08/2026.10.07.26364402.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.07.26364402","doi":"https://doi.org/10.64898/2026.10.07.26364402","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.26364402","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/08/2026.10.07.26364402.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.8371999859809875,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220964696.pdf","grobid_xml":"https://content.openalex.org/works/W7220964696.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W121839966","https://openalex.org/W2525980773","https://openalex.org/W2763700772","https://openalex.org/W2969542839","https://openalex.org/W3048957408","https://openalex.org/W3083316082","https://openalex.org/W4292318690","https://openalex.org/W4294214983","https://openalex.org/W4379260375","https://openalex.org/W4389792145","https://openalex.org/W4389899921","https://openalex.org/W4409011223","https://openalex.org/W4413721806","https://openalex.org/W4414300890","https://openalex.org/W4414610846","https://openalex.org/W7124165156","https://openalex.org/W7167604932"],"related_works":["https://openalex.org/W4402674664","https://openalex.org/W7162569332","https://openalex.org/W4411955010","https://openalex.org/W7162668292","https://openalex.org/W7166651205","https://openalex.org/W4389490684","https://openalex.org/W4415071286","https://openalex.org/W4409225830","https://openalex.org/W7162039516","https://openalex.org/W4402713323"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Clinical":[2],"registries":[3],"and":[4,126,145,178,231,249],"institutional":[5,40,246],"quality":[6,247],"control":[7,248],"(QC)":[8],"in":[9,24],"pathology":[10,254],"heavily":[11],"depend":[12],"on":[13],"complex":[14],"histopathological":[15,117],"data.":[16,63],"However,":[17],"critical":[18],"tumor":[19],"characteristics":[20],"are":[21],"mostly":[22],"locked":[23],"unstructured":[25],"free-text":[26],"reports.":[27,106],"We":[28,65],"hypothesize":[29],"that":[30],"locally":[31],"deployed,":[32],"resource-eWicient":[33],"language":[34],"models":[35,189],"operating":[36],"within":[37],"a":[38,67,84,99,110,227,242],"secure":[39,232],"network":[41],"can":[42],"reliably":[43],"extract":[44,114],"relevant":[45],"variables":[46],"from":[47,98],"German":[48],"reports":[49],"of":[50,77,93,102,197,253],"hepatocellular":[51],"carcinoma":[52],"(HCC),":[53],"thereby":[54],"enabling":[55],"automated":[56],"data":[57],"curation":[58,252],"without":[59],"transferring":[60],"sensitive":[61],"patient":[62,162],"Methods":[64],"developed":[66],"local,":[68],"privacy-preserving":[69,243],"open-weight":[70],"Large":[71],"Language":[72],"Model":[73],"(LLM)":[74],"pipeline":[75,137],"consisting":[76],"two":[78],"consecutive":[79],"stages:":[80],"Stage":[81,107,156,184],"1":[82,157],"utilizes":[83],"lightweight":[85],"gatekeeper":[86,158],"model":[87,112,202],"to":[88,113,149],"isolate":[89],"the":[90,160,173,195,215,250],"target":[91,161],"cohort":[92,163],"confirmed":[94],"Hepatocellular":[95],"Carcinoma":[96],"cases":[97],"screening":[100],"pool":[101],"N":[103],"=":[104],"2,864":[105],"2":[108,185],"deploys":[109],"high-capacity":[111],"15":[115],"predefined":[116],"variables,":[118],"including":[119],"tumor\u2013node\u2013metastasis":[120],"staging,":[121],"histological":[122],"grading,":[123],"vascular":[124],"invasion,":[125],"selected":[127],"immunohistochemical":[128],"features":[129],"into":[130],"structured":[131],"JSON":[132],"format.":[133],"For":[134,183],"both":[135],"Stages,":[136],"performance":[138],"was":[139],"evaluated":[140],"using":[141],"Accuracy,":[142],"Macro":[143],"F1-scores,":[144],"Cohen\u2019s":[146],"kappa":[147],"compared":[148],"expert-curated":[150],"reference":[151,174,216],"annotations.":[152],"Results":[153],"The":[154,200],"top-performing":[155],"isolated":[159],"with":[164,172,214],"zero":[165],"classification":[166],"errors,":[167,210],"effectively":[168],"reaching":[169],"complete":[170],"agreement":[171,213],"standard":[175,217],"(ground":[176],"truth)":[177],"correcting":[179],"inaccurate":[180],"administrative":[181],"metadata.":[182],"feature":[186],"extraction,":[187],"current-generation":[188],"demonstrated":[190],"robust":[191],"structural":[192],"reliability,":[193],"reducing":[194],"burden":[196],"manual":[198],"post-processing.":[199],"31B":[201],"configuration":[203],"(Gemma":[204],"4)":[205],"virtually":[206],"eliminated":[207],"objective":[208],"factual":[209],"achieving":[211],"near-perfect":[212],"(Macro":[218],"F1":[219],">":[220],"0.99).":[221],"Conclusion":[222],"Local":[223],"two-stage":[224],"pipelines":[225],"offer":[226],"highly":[228],"accurate,":[229],"resource-efficient,":[230],"solution":[233],"for":[234,245],"clinical":[235],"text":[236],"processing.":[237],"This":[238],"framework":[239],"serves":[240],"as":[241],"engine":[244],"scalable":[251],"registries.":[255]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-09T00:00:00"}