{"id":"https://openalex.org/W7161979101","doi":"https://doi.org/10.3233/shti260319","title":"THERA-IE: An AI-Enabled System for Therapeutic Indication Identification and Extraction from Biomedical Literature","display_name":"THERA-IE: An AI-Enabled System for Therapeutic Indication Identification and Extraction from Biomedical Literature","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7161979101","doi":"https://doi.org/10.3233/shti260319","pmid":"https://pubmed.ncbi.nlm.nih.gov/42174993"},"language":"en","primary_location":{"id":"doi:10.3233/shti260319","doi":"https://doi.org/10.3233/shti260319","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260319","pdf_url":null,"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,"listed_in":["cwts-core","doyens","jufo-1","ki-jl-1","medline","norway-1","vabb-shw"],"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"},"volume":{"id":"https://openalex.org/W7162004737","display_name":"Opening the Personal Gate between Technology and Health Care"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti260319","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086602697","display_name":"Indra Neil Sarkar","orcid":"https://orcid.org/0000-0003-2054-7356","observed_orcids":["https://orcid.org/0000-0003-2054-7356"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Indra Neil Sarkar","raw_affiliation_strings":["Center for Biomedical Informatics, Brown University, Providence, Rhode Island, USA"],"raw_orcid":"https://orcid.org/0000-0003-2054-7356","affiliations":[{"raw_affiliation_string":"Center for Biomedical Informatics, Brown University, Providence, Rhode Island, USA","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086602697"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37129537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"336","issue":null,"first_page":"949","last_page":"953"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0003000000142492354,"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":0.0003000000142492354,"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/off-label-drug-use","display_name":"off-label drug use","score":0.8949999809265137},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7540000081062317},{"id":"https://openalex.org/keywords/pubmedbert","display_name":"PubMedBERT","score":0.6439999938011169},{"id":"https://openalex.org/keywords/semmeddb","display_name":"SemMedDB","score":0.972000002861023},{"id":"https://openalex.org/keywords/fda-approved-drugs","display_name":"FDA-approved drugs","score":0.8579999804496765},{"id":"https://openalex.org/keywords/evidence-based-prescribing","display_name":"evidence-based prescribing","score":0.6710000038146973},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"biomedical text mining","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019000053405762},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5253000259399414},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4106000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25200000405311584}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056687","descriptor_name":"Off-Label Use","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}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti260319","doi":"https://doi.org/10.3233/shti260319","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260319","pdf_url":null,"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,"listed_in":["cwts-core","doyens","jufo-1","ki-jl-1","medline","norway-1","vabb-shw"],"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:42174993","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42174993","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.3233/shti260319","doi":"https://doi.org/10.3233/shti260319","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti260319","pdf_url":null,"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,"listed_in":["cwts-core","doyens","jufo-1","ki-jl-1","medline","norway-1","vabb-shw"],"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":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.766700029373169}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3187248639","https://openalex.org/W7165423402","https://openalex.org/W6968283619","https://openalex.org/W2049825704","https://openalex.org/W4398764592","https://openalex.org/W2104400119","https://openalex.org/W2409319733","https://openalex.org/W7118965376","https://openalex.org/W7096957975","https://openalex.org/W4404311522"],"abstract_inverted_index":{"Drug-indication":[0],"knowledge":[1,165],"underpins":[2],"evidence-based":[3],"prescribing":[4],"but":[5,131],"remains":[6],"challenging":[7],"to":[8,59,158],"maintain":[9],"manually.":[10],"Existing":[11],"resources":[12],"incompletely":[13],"represent":[14],"off-label":[15,147],"uses":[16],"that":[17,47],"may":[18],"be":[19],"captured":[20],"within":[21],"artificial":[22],"intelligence":[23],"models":[24],"or":[25],"described":[26],"in":[27,86],"the":[28,104,112,117,125,134,154],"biomedical":[29,167],"literature.":[30,168],"This":[31],"study":[32],"presents":[33],"THERA-IE":[34,138,157],"(Therapeutic":[35],"Hypothesis":[36],"Extraction":[37],"and":[38,53,72,80,90],"Relationship":[39],"Analytics":[40],"-":[41],"Indication":[42],"Extraction),":[43],"an":[44,140],"open-source":[45,74],"framework":[46],"combines":[48],"natural":[49],"language":[50,55],"processing,":[51],"transformer,":[52],"large":[54],"model":[56],"(LLM)":[57],"approaches":[58],"identify":[60],"putative":[61],"therapeutic":[62,164],"indications.":[63],"Twenty":[64],"FDA-approved":[65],"drugs":[66],"were":[67,84],"analyzed":[68],"using":[69],"SemMedDB,":[70],"PubMedBERT,":[71],"three":[73],"LLMs":[75,83],"(Llama":[76],"3.2,":[77],"MedLlama":[78],"3,":[79],"Qwen":[81],"3).":[82],"implemented":[85],"both":[87],"model-only":[88],"(\"Na\u00efve\")":[89],"literature-supported":[91],"(\"Literature-Based\")":[92],"modes.":[93],"System":[94],"performance":[95],"was":[96],"benchmarked":[97],"against":[98],"DrugBank.":[99],"Na\u00efve":[100],"Llama":[101,114],"3.2":[102,115],"achieved":[103,124],"highest":[105,118,126],"overall":[106],"F1-score":[107],"(0.60":[108],"\u00b1":[109,121,129,144],"0.18),":[110],"while":[111],"Literature-Based":[113],"attained":[116],"precision":[119],"(0.67":[120],"0.29).":[122],"SemMedDB":[123],"recall":[127],"(0.77":[128],"0.25)":[130],"also":[132],"produced":[133],"most":[135],"false":[136],"positives.":[137],"identified":[139],"average":[141],"of":[142,156,163],"4.8":[143],"2.1":[145],"plausible":[146],"indications":[148],"per":[149],"drug.":[150],"These":[151],"findings":[152],"demonstrate":[153],"potential":[155],"enable":[159],"scalable,":[160],"reproducible":[161],"extraction":[162],"from":[166]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-05-22T00:00:00"}