{"id":"https://openalex.org/W4408135179","doi":"https://doi.org/10.3389/fdgth.2025.1495040","title":"A simplified retriever to improve accuracy of phenotype normalizations by large language models","display_name":"A simplified retriever to improve accuracy of phenotype normalizations by large language models","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4408135179","doi":"https://doi.org/10.3389/fdgth.2025.1495040","pmid":"https://pubmed.ncbi.nlm.nih.gov/40103736"},"language":"en","primary_location":{"id":"doi:10.3389/fdgth.2025.1495040","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1495040","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1495040/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1495040/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046843425","display_name":"Daniel B. Hier","orcid":"https://orcid.org/0000-0002-6179-0793"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel B. Hier","raw_affiliation_strings":["Department of Neurology and Rehabilitation, University of Illinois at Chicago, Chicago, IL, United States"],"affiliations":[{"raw_affiliation_string":"Department of Neurology and Rehabilitation, University of Illinois at Chicago, Chicago, IL, United States","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113004855","display_name":"Tran Le Son","orcid":null},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thanh Son Do","raw_affiliation_strings":["Department of Computer Science, Missouri State University, Springfield, MO, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Missouri State University, Springfield, MO, United States","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040578359","display_name":"Tayo Obafemi-Ajayi","orcid":"https://orcid.org/0000-0002-0155-9733"},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tayo Obafemi-Ajayi","raw_affiliation_strings":["Engineering Program, Missouri State University, Springfield, MO, United States"],"affiliations":[{"raw_affiliation_string":"Engineering Program, Missouri State University, Springfield, MO, United States","institution_ids":["https://openalex.org/I119942284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046843425"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":5.5244,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95716454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"1495040","last_page":"1495040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/normalization","display_name":"Normalization (sociology)","score":0.8020951747894287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150018811225891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5668050050735474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5540602803230286},{"id":"https://openalex.org/keywords/labrador-retriever","display_name":"Labrador Retriever","score":0.5368967652320862},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.47293806076049805},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4558587670326233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.367196261882782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33531898260116577}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8020951747894287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150018811225891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5668050050735474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540602803230286},{"id":"https://openalex.org/C2910597052","wikidata":"https://www.wikidata.org/wiki/Q38726","display_name":"Labrador Retriever","level":2,"score":0.5368967652320862},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47293806076049805},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4558587670326233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367196261882782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33531898260116577},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdgth.2025.1495040","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1495040","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1495040/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},{"id":"pmid:40103736","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40103736","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":"Frontiers in digital health","raw_type":null},{"id":"pmh:oai:doaj.org/article:3460c73f5efe4a31811e3c4c1324520e","is_oa":true,"landing_page_url":"https://doaj.org/article/3460c73f5efe4a31811e3c4c1324520e","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":"Frontiers in Digital Health, Vol 7 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:10729351","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11913805","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"}],"best_oa_location":{"id":"doi:10.3389/fdgth.2025.1495040","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1495040","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1495040/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408135179.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1808652302","https://openalex.org/W2025349319","https://openalex.org/W2060427373","https://openalex.org/W2119613819","https://openalex.org/W2151068025","https://openalex.org/W2162151166","https://openalex.org/W2165748167","https://openalex.org/W2168091868","https://openalex.org/W2513408092","https://openalex.org/W2548932017","https://openalex.org/W2588904016","https://openalex.org/W2810450065","https://openalex.org/W2911489562","https://openalex.org/W2946102094","https://openalex.org/W3021112536","https://openalex.org/W4210876812","https://openalex.org/W4212919921","https://openalex.org/W4221142212","https://openalex.org/W4224997359","https://openalex.org/W4226119217","https://openalex.org/W4311903220","https://openalex.org/W4381587418","https://openalex.org/W4385163750","https://openalex.org/W4386501849","https://openalex.org/W4387485634","https://openalex.org/W4387500346","https://openalex.org/W4389984066","https://openalex.org/W4391292768","https://openalex.org/W4395067526","https://openalex.org/W4399941107","https://openalex.org/W4399986826","https://openalex.org/W4400177176","https://openalex.org/W4400435111","https://openalex.org/W4402683886","https://openalex.org/W4405492031","https://openalex.org/W4408521246","https://openalex.org/W6856223801","https://openalex.org/W6859201984","https://openalex.org/W6869998741","https://openalex.org/W6870391763","https://openalex.org/W6870634631","https://openalex.org/W6876141110"],"related_works":["https://openalex.org/W2357222614","https://openalex.org/W125958542","https://openalex.org/W4407384309","https://openalex.org/W4360983758","https://openalex.org/W86065725","https://openalex.org/W2771667642","https://openalex.org/W4406245716","https://openalex.org/W1850020175","https://openalex.org/W2992441222","https://openalex.org/W1037096755"],"abstract_inverted_index":{"Large":[0],"language":[1,35],"models":[2],"have":[3],"shown":[4],"improved":[5],"accuracy":[6,37,83],"in":[7,75],"phenotype":[8],"term":[9,22,59,107],"normalization":[10,82,108],"tasks":[11,109],"when":[12],"augmented":[13],"with":[14,96],"retrievers":[15],"that":[16,32,80],"suggest":[17],"candidate":[18,46],"normalizations":[19],"based":[20],"on":[21,64],"definitions.":[23,60],"In":[24],"this":[25,62],"work,":[26],"we":[27,78],"introduce":[28],"a":[29,88],"simplified":[30],"retriever":[31,97],"enhances":[33],"large":[34],"model":[36],"by":[38],"searching":[39],"the":[40,55,68,81],"Human":[41],"Phenotype":[42],"Ontology":[43],"(HPO)":[44],"for":[45,57],"matches":[47],"using":[48],"contextual":[49],"word":[50],"embeddings":[51],"from":[52,67,87],"BioBERT":[53],"without":[54,92],"need":[56],"explicit":[58],"Testing":[61],"method":[63],"terms":[65],"derived":[66],"clinical":[69],"synopses":[70],"of":[71,84,90],"Online":[72],"Mendelian":[73],"Inheritance":[74],"Man":[76],"(OMIM<sup>\u00ae</sup>),":[77],"demonstrate":[79],"GPT-4o":[85],"increases":[86],"baseline":[89],"62%":[91],"augmentation":[93],"to":[94,104,115],"85%":[95],"augmentation.":[98],"This":[99],"approach":[100],"is":[101],"potentially":[102],"generalizable":[103],"other":[105],"biomedical":[106],"and":[110],"offers":[111],"an":[112],"efficient":[113],"alternative":[114],"more":[116],"complex":[117],"retrieval":[118],"methods.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
