{"id":"https://openalex.org/W4410687020","doi":"https://doi.org/10.1038/s41746-025-01686-z","title":"Iterative refinement and goal articulation to optimize large language models for clinical information extraction","display_name":"Iterative refinement and goal articulation to optimize large language models for clinical information extraction","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4410687020","doi":"https://doi.org/10.1038/s41746-025-01686-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/40410408"},"language":"en","primary_location":{"id":"doi:10.1038/s41746-025-01686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-025-01686-z","pdf_url":"https://www.nature.com/articles/s41746-025-01686-z.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41746-025-01686-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090356242","display_name":"David Hein","orcid":"https://orcid.org/0000-0002-8625-9528"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Hein","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA. david.hein@utsouthwestern.edu"],"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA. david.hein@utsouthwestern.edu","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018252851","display_name":"Alana Christie","orcid":"https://orcid.org/0000-0002-7034-818X"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alana Christie","raw_affiliation_strings":["Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001219539","display_name":"Michael J. Holcomb","orcid":"https://orcid.org/0000-0003-1135-4237"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Holcomb","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022846227","display_name":"Bingqing Xie","orcid":"https://orcid.org/0000-0001-9246-9321"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingqing Xie","raw_affiliation_strings":["Department of Internal Medicine, Division of Hematology & Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Hematology & Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103349948","display_name":"Apurva Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"AJ Jain","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017437229","display_name":"Joseph Vento","orcid":"https://orcid.org/0000-0002-5561-7003"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Vento","raw_affiliation_strings":["Department of Internal Medicine, Division of Hematology & Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Internal Medicine, Division of Hematology & Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116255452","display_name":"Neil Rakheja","orcid":null},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Rakheja","raw_affiliation_strings":["Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023574893","display_name":"Ameer Hamza Shakur","orcid":"https://orcid.org/0000-0002-2695-8378"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ameer Hamza Shakur","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078078996","display_name":"Scott Christley","orcid":"https://orcid.org/0000-0002-9889-1221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Christley","raw_affiliation_strings":["Department of Health Data Science and Biostatistics, Peter O'Donnell Jr. School of Public Health, Univerisity of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Health Data Science and Biostatistics, Peter O'Donnell Jr. School of Public Health, Univerisity of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090203652","display_name":"Lindsay G. Cowell","orcid":"https://orcid.org/0000-0003-1617-8244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindsay G. Cowell","raw_affiliation_strings":["Department of Health Data Science and Biostatistics, Peter O'Donnell Jr. School of Public Health, Univerisity of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Health Data Science and Biostatistics, Peter O'Donnell Jr. School of Public Health, Univerisity of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046541559","display_name":"James Brugarolas","orcid":"https://orcid.org/0000-0002-8575-499X"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Brugarolas","raw_affiliation_strings":["Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069788317","display_name":"Andrew R. Jamieson","orcid":"https://orcid.org/0000-0001-5416-9379"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew R. Jamieson","raw_affiliation_strings":["Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069595062","display_name":"Payal Kapur","orcid":"https://orcid.org/0000-0002-4239-0495"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"education","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Payal Kapur","raw_affiliation_strings":["Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA","Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]},{"raw_affiliation_string":"Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA","institution_ids":["https://openalex.org/I867280407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5090356242"],"corresponding_institution_ids":[],"apc_list":{"value":3060,"currency":"USD","value_usd":3060},"apc_paid":{"value":3060,"currency":"USD","value_usd":3060},"fwci":25.7746,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99426514,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"301","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.7259182929992676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5940596461296082},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5224363207817078},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4804948568344116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3372909426689148},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10417774319648743},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06682035326957703}],"concepts":[{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.7259182929992676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5940596461296082},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5224363207817078},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4804948568344116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3372909426689148},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10417774319648743},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06682035326957703},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s41746-025-01686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-025-01686-z","pdf_url":"https://www.nature.com/articles/s41746-025-01686-z.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},{"id":"pmid:40410408","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40410408","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NPJ digital medicine","raw_type":null},{"id":"pmh:oai:doaj.org/article:5811e3ee46cd46c2a6e717083e666493","is_oa":true,"landing_page_url":"https://doaj.org/article/5811e3ee46cd46c2a6e717083e666493","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"npj Digital Medicine, Vol 8, Iss 1, Pp 1-13 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12102345","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12102345","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NPJ Digit Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41746-025-01686-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-025-01686-z","pdf_url":"https://www.nature.com/articles/s41746-025-01686-z.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2909881060","display_name":null,"funder_award_id":"P50CA196516","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3505956679","display_name":null,"funder_award_id":"P50CA196516","funder_id":"https://openalex.org/F4320310169","funder_display_name":"University of Texas Southwestern Medical Center"},{"id":"https://openalex.org/G3531319132","display_name":null,"funder_award_id":"1TR003163","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G392093004","display_name":null,"funder_award_id":"UL1TR003163","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7639100644","display_name":null,"funder_award_id":"CA196516","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320310169","display_name":"University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410687020.pdf","grobid_xml":"https://content.openalex.org/works/W4410687020.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W147910726","https://openalex.org/W1865128887","https://openalex.org/W1908864745","https://openalex.org/W1965380368","https://openalex.org/W2114843025","https://openalex.org/W2124014074","https://openalex.org/W2149441684","https://openalex.org/W2161112598","https://openalex.org/W2418239156","https://openalex.org/W2884934935","https://openalex.org/W2896812724","https://openalex.org/W2911489562","https://openalex.org/W2925863688","https://openalex.org/W2951675429","https://openalex.org/W3009297012","https://openalex.org/W3160137267","https://openalex.org/W3181361218","https://openalex.org/W4221143046","https://openalex.org/W4226191767","https://openalex.org/W4281644150","https://openalex.org/W4310568840","https://openalex.org/W4312220150","https://openalex.org/W4360891289","https://openalex.org/W4363671827","https://openalex.org/W4378464928","https://openalex.org/W4381587418","https://openalex.org/W4384071683","https://openalex.org/W4384831237","https://openalex.org/W4385014449","https://openalex.org/W4385381606","https://openalex.org/W4385571331","https://openalex.org/W4386120650","https://openalex.org/W4386438154","https://openalex.org/W4387526446","https://openalex.org/W4387559558","https://openalex.org/W4390064615","https://openalex.org/W4391292768","https://openalex.org/W4391301614","https://openalex.org/W4391901128","https://openalex.org/W4391987698","https://openalex.org/W4392005379","https://openalex.org/W4392740458","https://openalex.org/W4393157213","https://openalex.org/W4394579747","https://openalex.org/W4394869910","https://openalex.org/W4395467677","https://openalex.org/W4396553888","https://openalex.org/W4396722287","https://openalex.org/W4399854538","https://openalex.org/W4401306886","https://openalex.org/W4401542090","https://openalex.org/W4401847921","https://openalex.org/W4403798678","https://openalex.org/W4404105438","https://openalex.org/W4404330874","https://openalex.org/W4404718139","https://openalex.org/W4404867176","https://openalex.org/W4405023514","https://openalex.org/W4405655184","https://openalex.org/W4408226143","https://openalex.org/W6778883912","https://openalex.org/W6910494829"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2416809655","https://openalex.org/W2011075082","https://openalex.org/W4205477866","https://openalex.org/W2038626839","https://openalex.org/W2369832197","https://openalex.org/W2390279801","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Extracting":[0],"structured":[1],"data":[2,84],"from":[3,37],"free-text":[4],"medical":[5],"records":[6],"at":[7],"scale":[8],"is":[9],"laborious,":[10],"and":[11,35,59,99,113,122,142],"traditional":[12],"approaches":[13],"struggle":[14],"in":[15,145],"complex":[16],"clinical":[17,147],"domains.":[18],"We":[19,105],"present":[20],"a":[21,60,68,89],"novel,":[22],"end-to-end":[23],"pipeline":[24,75,130],"leveraging":[25],"large":[26],"language":[27],"models":[28],"(LLMs)":[29],"for":[30,86,94,101],"highly":[31],"accurate":[32],"information":[33],"extraction":[34],"normalization":[36],"unstructured":[38],"pathology":[39],"reports,":[40],"focusing":[41],"initially":[42],"on":[43],"kidney":[44,78,96,103],"tumors.":[45],"Our":[46],"innovation":[47],"combines":[48],"flexible":[49],"prompt":[50],"templates,":[51],"the":[52,73,134],"direct":[53],"production":[54],"of":[55,92,137],"analysis-ready":[56],"tabular":[57],"data,":[58],"rigorous,":[61],"human-in-the-loop":[62],"iterative":[63],"refinement":[64],"process":[65],"guided":[66],"by":[67],"comprehensive":[69],"error":[70],"ontology.":[71],"Applying":[72],"finalized":[74],"to":[76,115],"2297":[77],"tumor":[79,97],"reports":[80],"with":[81,109],"pre-existing":[82],"templated":[83],"available":[85,120],"validation":[87],"yielded":[88],"macro-averaged":[90],"F1":[91],"0.99":[93],"six":[95],"subtypes":[98],"0.97":[100],"detecting":[102],"metastasis.":[104],"further":[106],"demonstrate":[107],"flexibility":[108],"multiple":[110],"LLM":[111],"backbones":[112],"adaptability":[114],"new":[116],"domains,":[117],"utilizing":[118],"publicly":[119],"breast":[121],"prostate":[123],"cancer":[124],"reports.":[125],"Beyond":[126],"performance":[127],"metrics":[128],"or":[129],"specifics,":[131],"we":[132],"emphasize":[133],"critical":[135],"importance":[136],"task":[138],"definition,":[139],"interdisciplinary":[140],"collaboration,":[141],"complexity":[143],"management":[144],"LLM-based":[146],"workflows.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}