{"id":"https://openalex.org/W7135169634","doi":"https://doi.org/10.3390/a19030215","title":"Understanding Tradeoffs in Clinical Text Extraction: Prompting, Retrieval-Augmented Generation, and Supervised Learning on Electronic Health Records","display_name":"Understanding Tradeoffs in Clinical Text Extraction: Prompting, Retrieval-Augmented Generation, and Supervised Learning on Electronic Health Records","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135169634","doi":"https://doi.org/10.3390/a19030215"},"language":"en","primary_location":{"id":"doi:10.3390/a19030215","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030215","pdf_url":"https://www.mdpi.com/1999-4893/19/3/215/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/19/3/215/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126627698","display_name":"Tanya Yadav","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Yadav","raw_affiliation_strings":["Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA"],"raw_orcid":"https://orcid.org/0009-0004-9544-5834","affiliations":[{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041003015","display_name":"Aditya Tekale","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Tekale","raw_affiliation_strings":["Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA"],"raw_orcid":"https://orcid.org/0009-0007-9389-3723","affiliations":[{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128361591","display_name":"Jeff Chong","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Chong","raw_affiliation_strings":["Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083502477","display_name":"Mohammad Masum","orcid":"https://orcid.org/0000-0001-9974-6950"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Masum","raw_affiliation_strings":["Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA"],"raw_orcid":"https://orcid.org/0000-0001-9974-6950","affiliations":[{"raw_affiliation_string":"Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA","institution_ids":["https://openalex.org/I51504820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083502477"],"corresponding_institution_ids":["https://openalex.org/I51504820"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":9.1737,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96693788,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"3","first_page":"215","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.45100000500679016,"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":0.45100000500679016,"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":0.3330000042915344,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05820000171661377,"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/terminology","display_name":"Terminology","score":0.6000999808311462},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5715000033378601},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4894999861717224},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.45989999175071716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44119998812675476},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.43799999356269836},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/snomed-ct","display_name":"SNOMED CT","score":0.43290001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939000129699707},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917999744415283},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4894999861717224},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44119998812675476},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.43799999356269836},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.43290001153945923},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.38690000772476196},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.26510000228881836},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a19030215","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030215","pdf_url":"https://www.mdpi.com/1999-4893/19/3/215/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.sjsu.edu:faculty_rsca-8003","is_oa":true,"landing_page_url":"https://scholarworks.sjsu.edu/faculty_rsca/7003","pdf_url":"https://scholarworks.sjsu.edu/cgi/viewcontent.cgi?article=8003&context=faculty_rsca","source":{"id":"https://openalex.org/S4377196389","display_name":"San Jos\u00e9 State University ScholarWorks (San Jose State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51504820","host_organization_name":"San Jose State University","host_organization_lineage":["https://openalex.org/I51504820"],"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":"Faculty Research, Scholarly, and Creative Activity","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:555f3956af20453b848c7c8d9c6b7ad2","is_oa":true,"landing_page_url":"https://doaj.org/article/555f3956af20453b848c7c8d9c6b7ad2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 19, Iss 3, p 215 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a19030215","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19030215","pdf_url":"https://www.mdpi.com/1999-4893/19/3/215/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6146031618118286}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135169634.pdf","grobid_xml":"https://content.openalex.org/works/W7135169634.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W79139011","https://openalex.org/W2162800060","https://openalex.org/W2585785990","https://openalex.org/W2911489562","https://openalex.org/W2963716420","https://openalex.org/W3095092693","https://openalex.org/W3128355884","https://openalex.org/W4313439128","https://openalex.org/W4389519254","https://openalex.org/W4394579747","https://openalex.org/W4402670429","https://openalex.org/W4407218055","https://openalex.org/W4409690035","https://openalex.org/W4411203672"],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"discharge":[1,79],"summaries":[2,80],"contain":[3],"rich":[4],"patient":[5],"information":[6,56],"but":[7],"remain":[8,41],"difficult":[9],"to":[10],"convert":[11],"into":[12],"structured":[13,54],"representations":[14],"for":[15,29,53,68,192,203],"downstream":[16],"analysis.":[17],"Recent":[18],"advances":[19],"in":[20],"large":[21],"language":[22],"models":[23],"(LLMs)":[24],"have":[25],"introduced":[26],"new":[27],"approaches":[28],"clinical":[30,55,193,220],"text":[31],"extraction,":[32],"yet":[33],"their":[34],"relative":[35],"strengths":[36],"compared":[37],"with":[38,147],"supervised":[39,72,160],"methods":[40,107],"unclear.":[42],"This":[43],"study":[44],"presents":[45],"a":[46,101,109,117,177],"controlled":[47],"evaluation":[48,119,216],"of":[49,74,189,215],"three":[50],"dominant":[51],"strategies":[52,206],"extraction":[57,63,157,205],"from":[58,81],"electronic":[59],"health":[60],"records:":[61],"prompting-based":[62],"using":[64,116],"LLMs,":[65,96],"retrieval-augmented":[66,98],"generation":[67],"terminology":[69,153],"canonicalization,":[70],"and":[71,89,94,104,128,159,183,211],"fine-tuning":[73,161],"domain-specific":[75],"transformer":[76],"models.":[77],"Using":[78],"the":[82,163,187,213],"MIMIC-IV":[83],"dataset,":[84],"we":[85,175],"compare":[86],"zero-shot,":[87],"few-shot,":[88],"verification-based":[90],"prompting":[91,142],"across":[92,140],"closed-source":[93],"open-source":[95],"evaluate":[97],"canonicalization":[99],"as":[100],"post-processing":[102],"mechanism,":[103],"benchmark":[105],"these":[106],"against":[108],"fine-tuned":[110],"BioClinicalBERT":[111],"model.":[112],"Performance":[113],"is":[114],"assessed":[115],"multi-level":[118],"framework":[120],"that":[121,218],"combines":[122],"exact":[123],"matching,":[124,127],"fuzzy":[125],"lexical":[126],"semantic":[129,145,184],"assessment":[130],"via":[131],"an":[132],"LLM-based":[133],"judge.":[134],"The":[135],"results":[136],"reveal":[137],"clear":[138],"tradeoffs":[139],"approaches:":[141],"achieves":[143],"strong":[144],"correctness":[146],"minimal":[148],"supervision,":[149],"retrieval":[150],"augmentation":[151],"improves":[152],"consistency":[154],"without":[155],"expanding":[156],"coverage,":[158],"yields":[162],"highest":[164],"overall":[165],"accuracy":[166],"when":[167],"labeled":[168],"data":[169],"are":[170],"available.":[171],"Across":[172],"all":[173],"methods,":[174],"observe":[176],"consistent":[178],"40\u221250%":[179],"gap":[180],"between":[181],"exact-match":[182],"correctness,":[185],"highlighting":[186],"limitations":[188],"string-based":[190],"metrics":[191],"Natural":[194],"Language":[195],"Processing":[196],"(NLP).":[197],"These":[198],"findings":[199],"provide":[200],"practical":[201],"guidance":[202],"selecting":[204],"under":[207],"varying":[208],"resource":[209],"constraints":[210],"emphasize":[212],"importance":[214],"methodologies":[217],"reflect":[219],"equivalence":[221],"rather":[222],"than":[223],"surface-form":[224],"similarity.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-03-14T00:00:00"}