{"id":"https://openalex.org/W4389538461","doi":"https://doi.org/10.1109/embc40787.2023.10340611","title":"ChatGPT for phenotypes extraction: one model to rule them all?","display_name":"ChatGPT for phenotypes extraction: one model to rule them all?","publication_year":2023,"publication_date":"2023-07-24","ids":{"openalex":"https://openalex.org/W4389538461","doi":"https://doi.org/10.1109/embc40787.2023.10340611","pmid":"https://pubmed.ncbi.nlm.nih.gov/38082605"},"language":"en","primary_location":{"id":"doi:10.1109/embc40787.2023.10340611","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/embc40787.2023.10340611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04098499/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060544225","display_name":"Thomas Labb\u00e9","orcid":"https://orcid.org/0000-0001-9295-7675"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Labb\u00e9","raw_affiliation_strings":["Orange Labs,Rennes,France","Orange Labs, Rennes, France","bcom Research Institute, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs,Rennes,France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs, Rennes, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"bcom Research Institute, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093357955","display_name":"Pierre Castel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143287","display_name":"Institut de Recherche Technologique B-com","ror":"https://ror.org/03cejhk28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210143287"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Castel","raw_affiliation_strings":["b&#x003C;&#x003E;com Research Institute,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"b&#x003C;&#x003E;com Research Institute,France","institution_ids":["https://openalex.org/I4210143287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017556910","display_name":"Jean-Michel Sanner","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Michel Sanner","raw_affiliation_strings":["Orange Labs,Rennes,France","bcom Research Institute, France","Orange Labs, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs,Rennes,France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"bcom Research Institute, France","institution_ids":[]},{"raw_affiliation_string":"Orange Labs, Rennes, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032528704","display_name":"Majd Saleh","orcid":"https://orcid.org/0000-0003-1800-0028"},"institutions":[{"id":"https://openalex.org/I4210143287","display_name":"Institut de Recherche Technologique B-com","ror":"https://ror.org/03cejhk28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210143287"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Majd Saleh","raw_affiliation_strings":["b&#x003C;&#x003E;com Research Institute,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"b&#x003C;&#x003E;com Research Institute,France","institution_ids":["https://openalex.org/I4210143287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1043,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89965996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2023","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9901000261306763,"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/relevance","display_name":"Relevance (law)","score":0.7962782382965088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507676482200623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568053364753723},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6198010444641113},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5827635526657104},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5814478993415833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5500558018684387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5379090905189514},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4644574820995331},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44828876852989197},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4259251356124878},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39400601387023926},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.381082147359848},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1054772436618805}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7962782382965088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507676482200623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568053364753723},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6198010444641113},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5827635526657104},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5814478993415833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5500558018684387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5379090905189514},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4644574820995331},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44828876852989197},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4259251356124878},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39400601387023926},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.381082147359848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1054772436618805},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D010641","descriptor_name":"Phenotype","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":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","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":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"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}],"locations_count":3,"locations":[{"id":"doi:10.1109/embc40787.2023.10340611","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/embc40787.2023.10340611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 45th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:38082605","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38082605","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null},{"id":"pmh:oai:HAL:hal-04098499v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04098499","pdf_url":"https://hal.science/hal-04098499/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023","raw_type":"Preprints, Working Papers, ..."}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04098499v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04098499","pdf_url":"https://hal.science/hal-04098499/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023","raw_type":"Preprints, Working Papers, ..."},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389538461.pdf","grobid_xml":"https://content.openalex.org/works/W4389538461.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1034019924","https://openalex.org/W2493916176","https://openalex.org/W2617980815","https://openalex.org/W2734608416","https://openalex.org/W2759570644","https://openalex.org/W2767470330","https://openalex.org/W2809721358","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2928818852","https://openalex.org/W2982027034","https://openalex.org/W3087028093","https://openalex.org/W3106811464","https://openalex.org/W4206627019","https://openalex.org/W4224997359","https://openalex.org/W4226278401","https://openalex.org/W4292779060","https://openalex.org/W4381594492","https://openalex.org/W6604181502","https://openalex.org/W6632766574","https://openalex.org/W6783949373"],"related_works":["https://openalex.org/W2334378031","https://openalex.org/W2963217253","https://openalex.org/W2916255597","https://openalex.org/W2999302224","https://openalex.org/W3091569222","https://openalex.org/W4241018868","https://openalex.org/W1495833002","https://openalex.org/W2075635421","https://openalex.org/W2964631078","https://openalex.org/W3006227201"],"abstract_inverted_index":{"Information":[0],"Extraction":[1],"(IE)":[2],"is":[3,15,82,231],"a":[4,51,61,170],"core":[5],"task":[6],"in":[7,20,64,77,195,222],"Natural":[8],"Language":[9],"Processing":[10],"(NLP)":[11],"where":[12,120],"the":[13,31,43,65,73,80,131,139,146,149,176,186,190,196],"objective":[14],"to":[16,41,50,54,83,88,129,155,193,210,224],"identify":[17],"factual":[18],"knowledge":[19],"textual":[21],"documents":[22],"(often":[23],"unstructured),":[24],"and":[25,175,184,189,227],"feed":[26],"downstream":[27],"use":[28],"cases":[29],"with":[30],"resulting":[32],"output.":[33],"In":[34,165],"genomic":[35],"medicine":[36],"for":[37],"instance,":[38],"being":[39],"able":[40],"extract":[42],"most":[44,71],"precise":[45],"list":[46],"of":[47,72,109,113,123,148,151,173],"phenotypes":[48,132],"associated":[49],"patient":[52],"allows":[53],"improve":[55,130,211],"genetic":[56,212],"disease":[57],"diagnostic,":[58],"which":[59],"represents":[60],"vital":[62],"step":[63],"modern":[66],"deep":[67],"phenotyping":[68,201],"approach.":[69],"As":[70],"phenotypic":[74],"information":[75],"lies":[76],"clinical":[78,215],"reports,":[79],"challenge":[81],"build":[84],"an":[85,110,162],"IE":[86],"pipeline":[87],"automatically":[89],"recognize":[90],"phenotype":[91],"concepts":[92],"from":[93],"free-text":[94],"notes.":[95],"A":[96],"new":[97,157],"machine":[98],"learning":[99],"paradigm":[100],"around":[101],"large":[102],"language":[103],"models":[104],"(LLM)":[105],"has":[106,206],"given":[107],"rise":[108],"increasing":[111],"number":[112],"academic":[114],"works":[115],"on":[116,161,180,202],"this":[117,156,166,181],"topic":[118],"lately,":[119],"sophisticated":[121],"combinations":[122],"different":[124],"technics":[125],"have":[126],"been":[127],"employed":[128],"extraction":[133],"accuracy.":[134],"Even":[135],"more":[136],"recently":[137],"released,":[138],"ChatGPT<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[142],"application":[143],"nevertheless":[144],"raises":[145],"question":[147],"relevance":[150],"these":[152],"approches":[153],"compared":[154],"generic":[158],"one":[159],"based":[160],"instruction-oriented":[163],"LLM.":[164],"paper,":[167],"we":[168],"propose":[169],"rigorous":[171],"evaluation":[172],"ChatGPT":[174],"current":[177],"state-of-the-art":[178,220],"solutions":[179,221],"specific":[182],"task,":[183],"discuss":[185],"possible":[187],"impacts":[188],"technical":[191],"evolutions":[192],"consider":[194],"medical":[197],"domain.Clinical":[198],"relevance\u2014":[199],"Deep":[200],"electronic":[203],"health":[204],"records":[205],"proven":[207],"its":[208],"ability":[209],"diagnosis":[213],"by":[214],"exomes":[216],"[10].":[217],"Thus,":[218],"comparing":[219],"order":[223],"derive":[225],"insights":[226],"improving":[228],"research":[229],"paths":[230],"essential.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}