{"id":"https://openalex.org/W4414509355","doi":"https://doi.org/10.1093/database/baaf047","title":"Biomedical literature-based clinical phenotype definition discovery using large language models","display_name":"Biomedical literature-based clinical phenotype definition discovery using large language models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414509355","doi":"https://doi.org/10.1093/database/baaf047","pmid":"https://pubmed.ncbi.nlm.nih.gov/40996710"},"language":"en","primary_location":{"id":"doi:10.1093/database/baaf047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf047","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf047/64394823/baaf047.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf047/64394823/baaf047.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013073771","display_name":"Samar Binkheder","orcid":"https://orcid.org/0000-0003-0400-823X"},"institutions":[{"id":"https://openalex.org/I2801066305","display_name":"King Saud Medical City","ror":"https://ror.org/03aj9rj02","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I2801066305"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["SA","US"],"is_corresponding":true,"raw_author_name":"Samar Binkheder","raw_affiliation_strings":["King Saud University Medical Informatics Unit, Department of Medical Education, College of Medicine, , Riyadh 12372 ,","Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,"],"raw_orcid":"https://orcid.org/0000-0003-0400-823X","affiliations":[{"raw_affiliation_string":"King Saud University Medical Informatics Unit, Department of Medical Education, College of Medicine, , Riyadh 12372 ,","institution_ids":["https://openalex.org/I2801066305"]},{"raw_affiliation_string":"Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035708242","display_name":"X. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofu Liu","raw_affiliation_strings":["Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397569","display_name":"Michael Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Wu","raw_affiliation_strings":["gRED Computational Sciences, Computational Biology & Translation, Genentech, Inc , 1 DNA Way, South San Francisco, CA 94080 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"gRED Computational Sciences, Computational Biology & Translation, Genentech, Inc , 1 DNA Way, South San Francisco, CA 94080 ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436105","display_name":"Lei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,"],"raw_orcid":"https://orcid.org/0000-0003-1904-1737","affiliations":[{"raw_affiliation_string":"Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044452976","display_name":"Aditi Shendre","orcid":"https://orcid.org/0000-0003-4123-7613"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditi Shendre","raw_affiliation_strings":["Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061341188","display_name":"Sara K. Quinney","orcid":"https://orcid.org/0000-0002-6554-0695"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sara K Quinney","raw_affiliation_strings":["Indiana University Department of Obstetrics and Gynecology, School of Medicine, , 950 W Walnut Street, Indianapolis, IN 46202 ,"],"raw_orcid":"https://orcid.org/0000-0002-6554-0695","affiliations":[{"raw_affiliation_string":"Indiana University Department of Obstetrics and Gynecology, School of Medicine, , 950 W Walnut Street, Indianapolis, IN 46202 ,","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040262386","display_name":"Wei\u2010Qi Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Qi Wei","raw_affiliation_strings":["Vanderbilt University Medical Center Department of Biomedical Informatics, , 2525 West End Ave, Nashville, TN 37203 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center Department of Biomedical Informatics, , 2525 West End Ave, Nashville, TN 37203 ,","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383612","display_name":"Lang Li","orcid":"https://orcid.org/0000-0002-0746-1809"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lang Li","raw_affiliation_strings":["Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,"],"raw_orcid":"https://orcid.org/0000-0002-0746-1809","affiliations":[{"raw_affiliation_string":"Ohio State University Department of Biomedical Informatics,, College of Medicine, , 1800 Cannon Drive, Columbus, OH 43210 ,","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5013073771"],"corresponding_institution_ids":["https://openalex.org/I2801066305","https://openalex.org/I52357470"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21840218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","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":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9900000095367432,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9534000158309937,"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/support-vector-machine","display_name":"Support vector machine","score":0.6359000205993652},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6263999938964844},{"id":"https://openalex.org/keywords/clinical-phenotype","display_name":"Clinical phenotype","score":0.4918000102043152},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43050000071525574},{"id":"https://openalex.org/keywords/phenotype","display_name":"Phenotype","score":0.4262999892234802},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4124999940395355},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3828999996185303},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6722000241279602},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6359000205993652},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5864999890327454},{"id":"https://openalex.org/C3020646490","wikidata":"https://www.wikidata.org/wiki/Q25203551","display_name":"Clinical phenotype","level":4,"score":0.4918000102043152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47769999504089355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35199999809265137},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2547000050544739}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","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":"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":"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":"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"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":"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":"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":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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},{"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},{"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},{"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},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/database/baaf047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf047","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf047/64394823/baaf047.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:40996710","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40996710","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:scholarworks.indianapolis.iu.edu:1805/51446","is_oa":true,"landing_page_url":"https://hdl.handle.net/1805/51446","pdf_url":"https://scholarworks.indianapolis.iu.edu/bitstreams/1d442773-fbb6-4d5d-8eab-7afd9719483b/download","source":{"id":"https://openalex.org/S4306400987","display_name":"IUScholarWorks (Indiana University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I592451","host_organization_name":"Indiana University","host_organization_lineage":["https://openalex.org/I592451"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PMC","raw_type":"Article"},{"id":"pmh:oai:europepmc.org:11271101","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12462612","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12462612","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12462612/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baaf047","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf047","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf047/64394823/baaf047.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1898671489","display_name":null,"funder_award_id":"NSF1622526","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414509355.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W176696043","https://openalex.org/W1555243480","https://openalex.org/W1666916593","https://openalex.org/W1676815716","https://openalex.org/W1759667598","https://openalex.org/W1779612606","https://openalex.org/W1808652302","https://openalex.org/W1974660612","https://openalex.org/W1983745852","https://openalex.org/W2029592334","https://openalex.org/W2039612385","https://openalex.org/W2095588973","https://openalex.org/W2105637130","https://openalex.org/W2105714645","https://openalex.org/W2106393550","https://openalex.org/W2113952938","https://openalex.org/W2117243442","https://openalex.org/W2125055259","https://openalex.org/W2131668595","https://openalex.org/W2148008364","https://openalex.org/W2148563768","https://openalex.org/W2158743996","https://openalex.org/W2163107094","https://openalex.org/W2317648909","https://openalex.org/W2319116535","https://openalex.org/W2520392019","https://openalex.org/W2594685110","https://openalex.org/W2728065598","https://openalex.org/W2801591490","https://openalex.org/W2803290558","https://openalex.org/W2804842126","https://openalex.org/W2883582971","https://openalex.org/W2895486342","https://openalex.org/W2911489562","https://openalex.org/W2913694856","https://openalex.org/W2952312197","https://openalex.org/W2969522674","https://openalex.org/W2991319174","https://openalex.org/W2991379615","https://openalex.org/W3088156227","https://openalex.org/W3136253378","https://openalex.org/W3145004415","https://openalex.org/W3203868315","https://openalex.org/W4205170775","https://openalex.org/W4280556295","https://openalex.org/W4282920482","https://openalex.org/W4309650827","https://openalex.org/W4310572401","https://openalex.org/W4312960235","https://openalex.org/W4317209892","https://openalex.org/W4377564798","https://openalex.org/W4407830080"],"related_works":[],"abstract_inverted_index":{"Electronic":[0],"health":[1],"record":[2],"(EHR)":[3],"phenotyping":[4,253,266],"is":[5,22,255,261],"a":[6,187,201,224,237],"high-demand":[7],"task":[8],"because":[9],"most":[10],"phenotypes":[11],"are":[12],"not":[13],"usually":[14],"readily":[15],"defined.":[16],"The":[17,174,206],"objective":[18],"of":[19,56,106,156,204,228],"this":[20],"study":[21],"to":[23,195,213,223,241,263],"develop":[24],"an":[25],"effective":[26],"text-mining":[27],"approach":[28,254],"that":[29],"automatically":[30,242],"extracts":[31],"clinical":[32,47,87,94,168,181,197,216,226,244],"phenotype":[33,48,202,217,227,245],"definitions-related":[34],"sentences":[35,170,199,221,247],"from":[36,50,119,126,171,248],"biomedical":[37],"literature.":[38,250],"Abstract-level":[39],"and":[40,73,122,164,219,257,259],"full-text":[41,99,141],"sentence-level":[42,100,142],"classifiers":[43,143,152],"were":[44],"developed":[45,186,236],"for":[46,128,153,215],"discovery":[49],"PubMed.":[51],"We":[52,147],"compared":[53,103],"the":[54,57,79,98,104,136,140,157,249],"performance":[55,81,105],"abstract-level":[58],"classifier":[59,77],"on":[60],"machine":[61,66],"learning":[62],"algorithms:":[63],"support":[64],"vector":[65],"(SVM),":[67],"logistic":[68],"regression":[69],"(LR),":[70],"na\u00efve":[71,109],"Bayes,":[72,110],"decision":[74,111],"tree.":[75],"SVM":[76],"showed":[78],"best":[80,137],"(F-measure":[82,144],"=":[83,145],"98%)":[84],"in":[85],"identifying":[86],"phenotype-relevant":[88],"abstracts.":[89,96],"It":[90],"predicted":[91,177,191],"459":[92],"406":[93],"phenotype-related":[95,169,182,198],"For":[97],"classifier,":[101],"we":[102,185,235],"SVM,":[107],"LR,":[108],"trees,":[112],"convolutional":[113],"neural":[114],"networks,":[115],"Bidirectional":[116,123],"Encoder":[117,124],"Representations":[118,125],"Transformers":[120,127],"(BERT),":[121],"Biomedical":[129],"Text":[130],"Mining":[131],"(BioBERT).":[132],"BioBERT":[133],"model":[134],"was":[135],"performer":[138],"among":[139],"91%).":[146],"used":[148],"these":[149],"two":[150,179],"optimal":[151],"large-scale":[154,175],"screening":[155,176],"PubMed":[158],"database,":[159],"starting":[160],"with":[161,200],"abstract":[162],"retrieval":[163],"followed":[165],"by":[166],"predicting":[167],"full":[172],"texts.":[173],"over":[178],"million":[180],"sentences.":[183],"Lastly,":[184],"knowledgebase":[188],"using":[189],"positively":[190],"sentences,":[192],"allowing":[193],"users":[194,212],"query":[196],"term":[203],"interest.":[205],"Clinical":[207],"Phenotype":[208],"Knowledgebase":[209],"(CliPheKB)":[210],"enables":[211],"search":[214],"terms":[218],"retrieve":[220],"related":[222],"specific":[225],"interest":[229],"(https://cliphekb.shinyapps.io/phenotype-main/).":[230],"Building":[231],"upon":[232],"prior":[233],"methods,":[234],"text":[238],"mining":[239],"pipeline":[240],"extract":[243],"definition-related":[246],"This":[251],"high-throughput":[252],"generalizable":[256],"scalable,":[258],"it":[260],"complementary":[262],"existing":[264],"EHR":[265],"methods.":[267]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}