{"id":"https://openalex.org/W4413051597","doi":"https://doi.org/10.3233/shti250934","title":"PheCatcher: Leveraging LLM-Generated Synthetic Data for Automated Phenotype Definition Extraction from Biomedical Literature","display_name":"PheCatcher: Leveraging LLM-Generated Synthetic Data for Automated Phenotype Definition Extraction from Biomedical Literature","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413051597","doi":"https://doi.org/10.3233/shti250934","pmid":"https://pubmed.ncbi.nlm.nih.gov/40775952"},"language":"en","primary_location":{"id":"doi:10.3233/shti250934","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250934","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti250934","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100715220","display_name":"Yan Hu","orcid":"https://orcid.org/0009-0008-2413-5918"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Hu","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0009-0008-2413-5918","affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041242363","display_name":"Na Hong","orcid":"https://orcid.org/0000-0001-6798-1761"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Hong","raw_affiliation_strings":["Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0001-6798-1761","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiming Li","orcid":"https://orcid.org/0009-0009-8784-1745"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Li","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0009-0009-8784-1745","affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xueqing Peng","orcid":"https://orcid.org/0009-0004-1484-0622"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xueqing Peng","raw_affiliation_strings":["Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0009-0004-1484-0622","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454438","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0003-0835-0788"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0835-0788","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084072550","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-5274-4672"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Xu","raw_affiliation_strings":["Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0002-5274-4672","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Data Science, Yale School of Medicine, Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.2735,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9888697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"329","issue":null,"first_page":"718","last_page":"722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9973000288009644,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6056890487670898},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5662197470664978},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.514323353767395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3388223648071289},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3251228332519531},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.20738428831100464},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12742570042610168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6056890487670898},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5662197470664978},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.514323353767395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3388223648071289},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3251228332519531},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.20738428831100464},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12742570042610168},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti250934","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250934","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40775952","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40775952","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":"Studies in health technology and informatics","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3233/shti250934","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250934","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Phenotype":[0],"definitions":[1],"are":[2,23,116],"crucial":[3],"for":[4,78,128],"the":[5,20,87,99,102,109,123,134,138],"progression":[6],"of":[7,94,98,111,125,137,140],"precision":[8],"and":[9,19,45,52,86,132],"personalized":[10],"medicine.":[11],"Although":[12],"phenotype":[13,113],"knowledge":[14],"bases":[15],"such":[16],"as":[17],"PheKB":[18],"OHDSI":[21],"library":[22],"available,":[24],"they":[25],"rely":[26],"heavily":[27],"on":[28],"manual":[29],"input.":[30],"This":[31],"study":[32,121],"introduces":[33],"PheCatcher,":[34],"an":[35,91],"automated":[36],"pipeline":[37,100],"that":[38],"integrates":[39],"BiomedBERT-based":[40],"Named":[41],"Entity":[42],"Recognition":[43],"(NER)":[44],"Relation":[46],"Extraction":[47],"(RE)":[48],"to":[49,65,84,101,144],"extract":[50],"phenotypes":[51],"standardized":[53],"codes":[54],"from":[55,82],"biomedical":[56],"literature.":[57],"To":[58],"complement":[59],"human":[60],"annotation,":[61],"GPT-4":[62],"was":[63],"utilized":[64],"generate":[66],"synthetic":[67,126,142],"data,":[68],"which":[69,115],"improved":[70],"model":[71,89],"performance.":[72],"The":[73,96],"NER":[74],"model's":[75],"F1":[76,92],"score":[77,93],"\"phenotype\"":[79],"entities":[80],"increased":[81],"0.616":[83],"0.800,":[85],"RE":[88],"achieved":[90],"0.901.":[95],"application":[97],"PubMed":[103],"Central":[104],"(PMC)":[105],"articles":[106],"resulted":[107],"in":[108],"extraction":[110,130],"173,283":[112],"definitions,":[114],"now":[117],"publicly":[118],"accessible.":[119],"Our":[120],"underscores":[122],"potential":[124],"data":[127,143],"information":[129],"(IE)":[131],"offers":[133],"first":[135],"evidence":[136],"feasibility":[139],"leveraging":[141],"build":[145],"a":[146],"complete":[147],"IE":[148],"system.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
