{"id":"https://openalex.org/W4400104517","doi":"https://doi.org/10.48550/arxiv.2406.18027","title":"Automated Clinical Data Extraction with Knowledge Conditioned LLMs","display_name":"Automated Clinical Data Extraction with Knowledge Conditioned LLMs","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400104517","doi":"https://doi.org/10.48550/arxiv.2406.18027"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.18027","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18027","pdf_url":"https://arxiv.org/pdf/2406.18027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070880857","display_name":"Diya Li","orcid":"https://orcid.org/0000-0002-3287-9385","observed_orcids":["https://orcid.org/0000-0002-3287-9385"]},"institutions":[{"id":"https://openalex.org/I4210130631","display_name":"Freenome (United States)","ror":"https://ror.org/03w5jxa69","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Diya","raw_affiliation_strings":["Freenome , South San Francisco , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freenome , South San Francisco , CA , USA","institution_ids":["https://openalex.org/I4210130631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016480160","display_name":"Asim Kadav","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210130631","display_name":"Freenome (United States)","ror":"https://ror.org/03w5jxa69","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kadav, Asim","raw_affiliation_strings":["Freenome , South San Francisco , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freenome , South San Francisco , CA , USA","institution_ids":["https://openalex.org/I4210130631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099623087","display_name":"Aijing Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210130631","display_name":"Freenome (United States)","ror":"https://ror.org/03w5jxa69","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gao, Aijing","raw_affiliation_strings":["Freenome , South San Francisco , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freenome , South San Francisco , CA , USA","institution_ids":["https://openalex.org/I4210130631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448323","display_name":"Rui Li","orcid":"https://orcid.org/0000-0001-5953-2341","observed_orcids":["https://orcid.org/0000-0001-5953-2341"]},"institutions":[{"id":"https://openalex.org/I4210130631","display_name":"Freenome (United States)","ror":"https://ror.org/03w5jxa69","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Rui","raw_affiliation_strings":["Freenome , South San Francisco , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freenome , South San Francisco , CA , USA","institution_ids":["https://openalex.org/I4210130631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009855982","display_name":"Richard Bourgon","orcid":"https://orcid.org/0000-0002-5890-4374","observed_orcids":["https://orcid.org/0000-0002-5890-4374"]},"institutions":[{"id":"https://openalex.org/I4210130631","display_name":"Freenome (United States)","ror":"https://ror.org/03w5jxa69","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bourgon, Richard","raw_affiliation_strings":["Freenome , South San Francisco , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freenome , South San Francisco , CA , USA","institution_ids":["https://openalex.org/I4210130631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210130631"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"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":0.296099990606308,"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":0.296099990606308,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2896000146865845,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10028","display_name":"Topic Modeling","score":0.15369999408721924,"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/clinical-information-extraction","display_name":"clinical information extraction","score":0.734000027179718},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.9210000038146973},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/knowledge-base-alignment","display_name":"knowledge base alignment","score":0.6520000100135803}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5072023868560791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3803187906742096},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35276687145233154},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.23868602514266968},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14129343628883362}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.18027","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18027","pdf_url":"https://arxiv.org/pdf/2406.18027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.18027","doi":"https://doi.org/10.48550/arxiv.2406.18027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18027","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.18027","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18027","pdf_url":"https://arxiv.org/pdf/2406.18027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.46810001134872437}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104517.pdf","grobid_xml":"https://content.openalex.org/works/W4400104517.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4377121468","https://openalex.org/W4385573099","https://openalex.org/W4405736832","https://openalex.org/W4410705984"],"related_works":["https://openalex.org/W4410687020","https://openalex.org/W7212030673","https://openalex.org/W4405183692","https://openalex.org/W7165405988","https://openalex.org/W4403709562","https://openalex.org/W7169848346","https://openalex.org/W4404690294","https://openalex.org/W4407482948","https://openalex.org/W4417486464","https://openalex.org/W4409295452"],"abstract_inverted_index":{"The":[0],"extraction":[1],"of":[2,20,44,88,102,140],"lung":[3],"lesion":[4],"information":[5],"from":[6],"clinical":[7,18,57],"and":[8,17,51,93,100,109,135],"medical":[9],"imaging":[10],"reports":[11],"is":[12],"crucial":[13],"for":[14,54,129],"research":[15],"on":[16],"care":[19],"lung-related":[21],"diseases.":[22],"Large":[23],"language":[24],"models":[25],"(LLMs)":[26],"can":[27,124],"be":[28],"effective":[29],"at":[30],"interpreting":[31],"unstructured":[32],"text":[33],"in":[34,56],"reports,":[35],"but":[36],"they":[37],"often":[38],"hallucinate":[39],"due":[40],"to":[41,48,84,96,107],"a":[42,64,82,94],"lack":[43],"domain-specific":[45],"knowledge,":[46],"leading":[47],"reduced":[49],"accuracy":[50],"posing":[52],"challenges":[53],"use":[55],"settings.":[58],"To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"novel":[65],"framework":[66,80],"that":[67,120],"aligns":[68],"generated":[69],"internal":[70,89],"knowledge":[71,74,92,112],"with":[72,115],"external":[73,91],"through":[75],"in-context":[76],"learning":[77],"(ICL).":[78],"Our":[79],"employs":[81],"retriever":[83],"identify":[85],"relevant":[86],"units":[87],"or":[90],"grader":[95],"evaluate":[97],"the":[98,103,111,126],"truthfulness":[99],"helpfulness":[101],"retrieved":[104],"internal-knowledge":[105],"rules,":[106],"align":[108],"update":[110],"bases.":[113],"Experiments":[114],"expert-curated":[116],"test":[117],"datasets":[118],"demonstrate":[119],"this":[121],"ICL":[122,144],"approach":[123],"increase":[125],"F1":[127],"score":[128],"key":[130],"fields":[131],"(lesion":[132],"size,":[133],"margin":[134],"solidity)":[136],"by":[137],"an":[138],"average":[139],"12.9%":[141],"over":[142],"existing":[143],"methods.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-06-28T00:00:00"}