{"id":"https://openalex.org/W4410448256","doi":"https://doi.org/10.3233/shti250465","title":"Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets","display_name":"Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4410448256","doi":"https://doi.org/10.3233/shti250465","pmid":"https://pubmed.ncbi.nlm.nih.gov/40380573"},"language":"en","primary_location":{"id":"doi:10.3233/shti250465","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250465","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250465","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041023180","display_name":"Anthony Yazdani","orcid":"https://orcid.org/0000-0003-3309-6128"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anthony Yazdani","raw_affiliation_strings":["Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3309-6128","affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071643063","display_name":"Hossein Rouhizadeh","orcid":"https://orcid.org/0000-0002-6496-6766"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hossein Rouhizadeh","raw_affiliation_strings":["Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6496-6766","affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017831867","display_name":"Alban Bornet","orcid":"https://orcid.org/0000-0002-7266-627X"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alban Bornet","raw_affiliation_strings":["Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7266-627X","affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042070839","display_name":"Douglas Teodoro","orcid":"https://orcid.org/0000-0001-6238-4503"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Douglas Teodoro","raw_affiliation_strings":["Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6238-4503","affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114457229"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14101115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"327","issue":null,"first_page":"778","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9926999807357788,"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":0.9926999807357788,"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":0.9757000207901001,"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/T10260","display_name":"Software Engineering Research","score":0.9207000136375427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7773677110671997},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6996491551399231},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.6022199392318726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.559555172920227},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5378355979919434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4854176938533783},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.475766122341156},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.45333534479141235},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.42306041717529297},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.419563889503479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36677467823028564},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1459663212299347},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.10953214764595032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773677110671997},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6996491551399231},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.6022199392318726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.559555172920227},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5378355979919434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4854176938533783},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.475766122341156},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.45333534479141235},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42306041717529297},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.419563889503479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36677467823028564},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1459663212299347},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.10953214764595032},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016907","descriptor_name":"Adverse Drug Reaction Reporting Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016907","descriptor_name":"Adverse Drug Reaction Reporting Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D061108","descriptor_name":"Social Media","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D064420","descriptor_name":"Drug-Related Side Effects and Adverse Reactions","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.3233/shti250465","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250465","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250465","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40380573","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40380573","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":"Journal Article"},{"id":"pmh:oai:unige.ch:aou:unige:185634","is_oa":true,"landing_page_url":"https://archive-ouverte.unige.ch/unige:185634","pdf_url":null,"source":{"id":"https://openalex.org/S4306402259","display_name":"Archive ouverte UNIGE (University of Geneva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114457229","host_organization_name":"University of Geneva","host_organization_lineage":["https://openalex.org/I114457229"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Intelligent Health Systems \u2013 From Technology to Data and Knowledge / Andrikopoulou, E., Gallos, P., Arvanitis, T.N., Austin, R., Benis, A., Cornet, R., Chatzistergos, P., Dejaco, D., Dusseljee-Peute, L., Mohasseb, A., Natsiavas, P., Nakkas, H. & Scott, P. (ed.), (2025) p. 778-782","raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.3233/shti250465","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti250465","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI250465","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410448256.pdf","grobid_xml":"https://content.openalex.org/works/W4410448256.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1571141552","https://openalex.org/W4391636338","https://openalex.org/W4386067343","https://openalex.org/W4294250823","https://openalex.org/W2093086151","https://openalex.org/W3199871245","https://openalex.org/W55936454","https://openalex.org/W2095572632","https://openalex.org/W2944249426","https://openalex.org/W4294609170"],"abstract_inverted_index":{"Adverse":[0],"drug":[1],"event":[2],"(ADE)":[3],"detection":[4,44,130,145],"in":[5,128,153],"social":[6,36],"media":[7,37],"texts":[8],"poses":[9],"significant":[10],"challenges":[11],"due":[12],"to":[13,64,151,155],"the":[14,18,21,39,56,125,156],"informal":[15],"nature":[16],"of":[17,24,28,41,49,59,94,158],"text":[19],"and":[20,80,106],"limited":[22],"availability":[23],"annotations.":[25],"The":[26,162],"scarcity":[27,157],"ADE":[29,43,78,129,144,160],"named":[30],"entity":[31],"recognition":[32],"(NER)":[33],"datasets":[34],"for":[35,46],"hinders":[38],"development":[40],"robust":[42],"models":[45,62,83,102,120],"this":[47,52,69,85],"type":[48],"corpus.":[50],"In":[51],"paper,":[53],"we":[54,73],"leveraged":[55],"generative":[57],"capabilities":[58],"large":[60],"language":[61],"(LLMs)":[63],"create":[65],"synthetic":[66,86,137,163],"data,":[67],"addressing":[68],"dataset":[70,164],"gap.":[71],"Specifically,":[72],"generated":[74,139],"17,000":[75],"tweets":[76,98],"with":[77],"annotations":[79],"pre-trained":[81,108,119],"NER":[82,110],"on":[84,90,121,131],"data.":[87],"Our":[88],"evaluations":[89],"an":[91],"out-of-sample":[92],"collection":[93],"915":[95],"manually":[96],"annotated":[97,159],"revealed":[99],"that":[100,115,136],"these":[101],"outperform":[103],"state-of-the-art":[104,127],"lexico-based":[105],"massively":[107],"open":[109],"models.":[111],"We":[112],"also":[113],"show":[114],"fine-tuning":[116],"our":[117],"synthetically":[118],"human-annotated":[122],"data":[123,138],"surpasses":[124],"current":[126],"tweets.":[132],"These":[133],"findings":[134],"suggest":[135],"by":[140],"LLMs":[141],"can":[142],"enhance":[143],"performance,":[146],"offering":[147],"a":[148],"promising":[149],"avenue":[150],"explore":[152],"response":[154],"datasets.":[161],"is":[165],"available":[166],"at":[167],"https://huggingface.co/datasets/anthonyyazdaniml/synthetic-ner-ade-tweets-v1.":[168]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
