{"id":"https://openalex.org/W4407184427","doi":"https://doi.org/10.48550/arxiv.2502.01620","title":"LLM-TA: An LLM-Enhanced Thematic Analysis Pipeline for Transcripts from Parents of Children with Congenital Heart Disease","display_name":"LLM-TA: An LLM-Enhanced Thematic Analysis Pipeline for Transcripts from Parents of Children with Congenital Heart Disease","publication_year":2025,"publication_date":"2025-02-03","ids":{"openalex":"https://openalex.org/W4407184427","doi":"https://doi.org/10.48550/arxiv.2502.01620"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.01620","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01620","pdf_url":"https://arxiv.org/pdf/2502.01620","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Raza, Muhammad Zain","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raza, Muhammad Zain","raw_affiliation_strings":["School of Information , UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information , UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086159352","display_name":"Jiawei Xu","orcid":"https://orcid.org/0000-0003-4336-7972","observed_orcids":["https://orcid.org/0000-0003-4336-7972"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Jiawei","raw_affiliation_strings":["School of Information , UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information , UT Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063224515","display_name":"Terence Lim","orcid":"https://orcid.org/0009-0006-6651-4807","observed_orcids":["https://orcid.org/0009-0006-6651-4807"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lim, Terence","raw_affiliation_strings":["College of Natural Sciences , UT Austin 3 Graphen , Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Natural Sciences , UT Austin 3 Graphen , Inc","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Boddy, Lily","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boddy, Lily","raw_affiliation_strings":["College of Natural Sciences , UT Austin 3 Graphen , Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Natural Sciences , UT Austin 3 Graphen , Inc","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002938900","display_name":"Carlos M. Mery","orcid":"https://orcid.org/0000-0003-0779-2381","observed_orcids":["https://orcid.org/0000-0003-0779-2381","https://orcid.org/0000-0001-8966-6551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mery, Carlos M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054449239","display_name":"Andrew M Well","orcid":"https://orcid.org/0000-0002-0725-2791","observed_orcids":["https://orcid.org/0000-0002-0725-2791"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Well, Andrew","raw_affiliation_strings":["Dell Medical School , UT Austin","Texas Center for Pediatric and Congenital Heart Disease"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell Medical School , UT Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Texas Center for Pediatric and Congenital Heart Disease","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047170063","display_name":"Ying Ding","orcid":"https://orcid.org/0000-0003-2567-2009","observed_orcids":["https://orcid.org/0000-0003-2567-2009","https://orcid.org/0009-0008-7423-1510","https://orcid.org/0000-0003-1352-1000","https://orcid.org/0000-0002-8988-859X","https://orcid.org/0000-0003-1355-6959"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding, Ying","raw_affiliation_strings":["Dell Medical School , UT Austin","School of Information , UT Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell Medical School , UT Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"School of Information , UT Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9262999892234802,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12880","display_name":"Qualitative Research Methods and Applications","score":0.047600001096725464,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00559999980032444,"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/large-language-models","display_name":"large language models","score":0.859000027179718},{"id":"https://openalex.org/keywords/interview-transcripts","display_name":"interview transcripts","score":0.7369999885559082},{"id":"https://openalex.org/keywords/parents-of-children-with-congenital-heart-disease","display_name":"parents of children with congenital heart disease","score":0.9399999976158142},{"id":"https://openalex.org/keywords/anomalous-origin-of-coronary-artery","display_name":"anomalous coronary artery origin","score":0.9819999933242798},{"id":"https://openalex.org/keywords/gpt-4o-mini","display_name":"GPT-4o-mini","score":0.9139999747276306},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.8080000281333923},{"id":"https://openalex.org/keywords/langchain","display_name":"LangChain","score":0.7400000095367432},{"id":"https://openalex.org/keywords/chunking","display_name":"chunking","score":0.7900000214576721},{"id":"https://openalex.org/keywords/thematic-similarity","display_name":"thematic similarity","score":0.5329999923706055}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6577355265617371},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.5532766580581665},{"id":"https://openalex.org/C2780074459","wikidata":"https://www.wikidata.org/wiki/Q389735","display_name":"Heart disease","level":2,"score":0.5010557174682617},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.45374804735183716},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.4352504312992096},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.346720814704895},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3330027163028717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1864408254623413},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18342000246047974},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1248617172241211},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.08582434058189392},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.01620","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01620","pdf_url":"https://arxiv.org/pdf/2502.01620","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.01620","doi":"https://doi.org/10.48550/arxiv.2502.01620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01620","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.01620","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01620","pdf_url":"https://arxiv.org/pdf/2502.01620","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.428600013256073,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G399616987","display_name":"Bridge2AI: Cell Maps for AI (CM4AI) Data Generation Project","funder_award_id":"OT2OD032742","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5688846197","display_name":"AIM-AHEAD Coordinating Center - All Four Cores","funder_award_id":"OT2OD032581","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407184427.pdf","grobid_xml":"https://content.openalex.org/works/W4407184427.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4388092820","https://openalex.org/W4389523946","https://openalex.org/W4391876619","https://openalex.org/W4396913146","https://openalex.org/W4404781781","https://openalex.org/W4408735049","https://openalex.org/W7125218033"],"related_works":["https://openalex.org/W4416524320","https://openalex.org/W4409048589","https://openalex.org/W7162004439","https://openalex.org/W7134895536","https://openalex.org/W4415254001","https://openalex.org/W4417275657","https://openalex.org/W7167276432","https://openalex.org/W4389520295","https://openalex.org/W7212174643","https://openalex.org/W4417529645"],"abstract_inverted_index":{"Thematic":[0,72],"Analysis":[1,73],"(TA)":[2],"is":[3,16],"a":[4,59,63],"fundamental":[5],"method":[6],"in":[7,42,140],"healthcare":[8,44],"research":[9],"for":[10,22,167],"analyzing":[11],"transcript":[12],"data,":[13],"but":[14],"it":[15,143],"resource-intensive":[17],"and":[18,86,116,151,174,191],"difficult":[19],"to":[20,36,92,147,184,188],"scale":[21],"large,":[23],"complex":[24],"datasets.":[25],"This":[26],"study":[27],"investigates":[28],"the":[29,38,98,104,131,176],"potential":[30,146],"of":[31,52,58,178],"large":[32],"language":[33],"models":[34],"(LLMs)":[35],"augment":[37],"inductive":[39,99,141],"TA":[40,100,127,172],"process":[41],"high-stakes":[43,171],"settings.":[45],"Focusing":[46],"on":[47],"interview":[48],"transcripts":[49,96],"from":[50],"parents":[51],"children":[53],"with":[54,89,160,181],"Anomalous":[55],"Aortic":[56],"Origin":[57],"Coronary":[60],"Artery":[61],"(AAOCA),":[62],"rare":[64],"congenital":[65],"heart":[66],"disease,":[67],"we":[68],"propose":[69],"an":[70,79],"LLM-Enhanced":[71],"(LLM-TA)":[74],"pipeline.":[75],"Our":[76],"pipeline":[77,123,132],"integrates":[78],"affordable":[80],"state-of-the-art":[81],"LLM":[82],"(GPT-4o":[83],"mini),":[84],"LangChain,":[85],"prompt":[87],"engineering":[88],"chunking":[90],"techniques":[91],"analyze":[93],"nine":[94],"detailed":[95],"following":[97],"framework.":[101],"We":[102,163],"evaluate":[103],"LLM-generated":[105],"themes":[106],"against":[107],"human-generated":[108],"results":[109],"using":[110],"thematic":[111],"similarity":[112],"metrics,":[113],"LLM-assisted":[114,126],"assessments,":[115],"expert":[117],"reviews.":[118],"Results":[119],"demonstrate":[120],"that":[121],"our":[122],"outperforms":[124],"existing":[125],"methods":[128],"significantly.":[129],"While":[130],"alone":[133],"has":[134],"not":[135],"yet":[136],"reached":[137],"human-level":[138],"quality":[139],"TA,":[142],"shows":[144],"great":[145],"improve":[148],"scalability,":[149],"efficiency,":[150],"accuracy":[152],"while":[153],"reducing":[154],"analyst":[155],"workload":[156],"when":[157],"working":[158],"collaboratively":[159],"domain":[161,182],"experts.":[162],"provide":[164],"practical":[165],"recommendations":[166],"incorporating":[168],"LLMs":[169],"into":[170],"workflows":[173],"emphasize":[175],"importance":[177],"close":[179],"collaboration":[180],"experts":[183],"address":[185],"challenges":[186],"related":[187],"real-world":[189],"applicability":[190],"dataset":[192],"complexity.":[193],"https://github.com/jiaweixu98/LLM-TA":[194]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2025-02-06T00:00:00"}
