{"id":"https://openalex.org/W4403201819","doi":"https://doi.org/10.3389/fdata.2024.1463543","title":"Ontology extension by online clustering with large language model agents","display_name":"Ontology extension by online clustering with large language model agents","publication_year":2024,"publication_date":"2024-10-07","ids":{"openalex":"https://openalex.org/W4403201819","doi":"https://doi.org/10.3389/fdata.2024.1463543","pmid":"https://pubmed.ncbi.nlm.nih.gov/39435030"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2024.1463543","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1463543","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1463543/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","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/big-data/articles/10.3389/fdata.2024.1463543/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067651547","display_name":"Guanchen Wu","orcid":"https://orcid.org/0000-0002-5579-1052"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanchen Wu","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, United States","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411152","display_name":"Ling Chen","orcid":"https://orcid.org/0000-0003-4557-8511"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Ling","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, United States","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057737203","display_name":"Ilana Graetz","orcid":"https://orcid.org/0000-0003-3664-5815"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilana Graetz","raw_affiliation_strings":["Rollins School of Public Health, Emory University, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Rollins School of Public Health, Emory University, Atlanta, GA, United States","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061568038","display_name":"Liang Zhao","orcid":"https://orcid.org/0000-0001-5829-6850"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liang Zhao","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA, United States","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061568038"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":0.7288,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71302953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"1463543","last_page":"1463543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9983999729156494,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9872000217437744,"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/computer-science","display_name":"Computer science","score":0.7995802164077759},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7323449850082397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.657477617263794},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.631891131401062},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5410820841789246},{"id":"https://openalex.org/keywords/ontology-based-data-integration","display_name":"Ontology-based data integration","score":0.46485435962677},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.45381611585617065},{"id":"https://openalex.org/keywords/upper-ontology","display_name":"Upper ontology","score":0.4446928799152374},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4348660111427307},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4295922517776489},{"id":"https://openalex.org/keywords/suggested-upper-merged-ontology","display_name":"Suggested Upper Merged Ontology","score":0.37413352727890015},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3702196478843689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30018892884254456},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27734968066215515},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.14653536677360535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995802164077759},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7323449850082397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.657477617263794},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.631891131401062},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5410820841789246},{"id":"https://openalex.org/C22550185","wikidata":"https://www.wikidata.org/wiki/Q7095047","display_name":"Ontology-based data integration","level":3,"score":0.46485435962677},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.45381611585617065},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.4446928799152374},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4348660111427307},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4295922517776489},{"id":"https://openalex.org/C50971890","wikidata":"https://www.wikidata.org/wiki/Q7635093","display_name":"Suggested Upper Merged Ontology","level":4,"score":0.37413352727890015},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3702196478843689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30018892884254456},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27734968066215515},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.14653536677360535},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2024.1463543","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1463543","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1463543/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","raw_type":"journal-article"},{"id":"pmid:39435030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39435030","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 big data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11491333","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11491333","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11491333/pdf/fdata-07-1463543.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:699266ce404545a1b6dc9bfb6740bb1d","is_oa":true,"landing_page_url":"https://doaj.org/article/699266ce404545a1b6dc9bfb6740bb1d","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 Big Data, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2024.1463543","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1463543","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1463543/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"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 Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403201819.pdf","grobid_xml":"https://content.openalex.org/works/W4403201819.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W17780832","https://openalex.org/W3215548747","https://openalex.org/W4290989329","https://openalex.org/W4299285712","https://openalex.org/W4379138252","https://openalex.org/W4384407924","https://openalex.org/W4386794445","https://openalex.org/W4389483764","https://openalex.org/W4390529182","https://openalex.org/W4401042535"],"related_works":["https://openalex.org/W26549824","https://openalex.org/W2732632690","https://openalex.org/W1506177826","https://openalex.org/W72173000","https://openalex.org/W2726617685","https://openalex.org/W2396086199","https://openalex.org/W2357775360","https://openalex.org/W2608149786","https://openalex.org/W2130691104","https://openalex.org/W2365397974"],"abstract_inverted_index":{"An":[0],"ontology":[1,42,53],"is":[2,21],"a":[3,13,34,47],"structured":[4,139],"framework":[5,36,55],"that":[6],"categorizes":[7],"entities,":[8],"concepts,":[9],"and":[10,19,26,58,93,98,106,120,133,138,141,155,174,184],"relationships":[11],"within":[12],"domain":[14],"to":[15,37,61,151],"facilitate":[16],"shared":[17],"understanding,":[18],"it":[20],"important":[22],"in":[23,46,180,188],"computational":[24],"linguistics":[25],"knowledge":[27,64],"representation.":[28],"In":[29],"this":[30,80],"paper,":[31],"we":[32],"propose":[33],"novel":[35],"automatically":[38],"extend":[39],"an":[40,125],"existing":[41,66,126],"from":[43,110],"streaming":[44],"data":[45,71,175],"zero-shot":[48,52],"manner.":[49],"Specifically,":[50],"the":[51,77,168],"extension":[54],"uses":[56],"online":[57,112,132],"hierarchical":[59,134],"clustering":[60,135],"integrate":[62],"new":[63,159],"into":[65,124],"ontologies":[67,183],"without":[68],"substantial":[69],"annotated":[70],"or":[72],"domain-specific":[73],"expertise.":[74],"Focusing":[75],"on":[76],"medical":[78,108,182],"field,":[79],"approach":[81],"leverages":[82],"Large":[83],"Language":[84],"Models":[85],"(LLMs)":[86],"for":[87],"two":[88],"key":[89],"tasks:":[90],"Symptom":[91,94,102,117],"Typing":[92,103],"Taxonomy":[95,118],"among":[96],"breast":[97],"bladder":[99],"cancer":[100],"survivors.":[101],"involves":[104],"identifying":[105],"classifying":[107],"symptoms":[109,123,160],"unstructured":[111],"patient":[113],"forum":[114],"data,":[115],"while":[116],"organizes":[119],"integrates":[121],"these":[122],"ontology.":[127],"The":[128,145,165],"combined":[129],"use":[130],"of":[131,143,158],"enables":[136],"real-time":[137],"categorization":[140],"integration":[142,157],"symptoms.":[144],"dual-phase":[146],"model":[147],"employs":[148],"multiple":[149],"LLMs":[150],"ensure":[152],"accurate":[153],"classification":[154],"seamless":[156],"with":[161],"minimal":[162],"human":[163],"oversight.":[164],"paper":[166],"details":[167],"framework's":[169],"development,":[170],"experiments,":[171],"quantitative":[172],"analyses,":[173],"visualizations,":[176],"demonstrating":[177],"its":[178],"effectiveness":[179],"enhancing":[181],"advancing":[185],"knowledge-based":[186],"systems":[187],"healthcare.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}