{"id":"https://openalex.org/W4401247463","doi":"https://doi.org/10.1109/jcsse61278.2024.10613630","title":"The Use of Clinical Language Models Pretrained on Institutional EHR Data for Downstream Tasks","display_name":"The Use of Clinical Language Models Pretrained on Institutional EHR Data for Downstream Tasks","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4401247463","doi":"https://doi.org/10.1109/jcsse61278.2024.10613630"},"language":"en","primary_location":{"id":"doi:10.1109/jcsse61278.2024.10613630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/jcsse61278.2024.10613630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Joint Conference on Computer Science and Software Engineering (JCSSE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079497301","display_name":"Kerdkiat Suvirat","orcid":"https://orcid.org/0000-0002-5906-1065"},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kerdkiat Suvirat","raw_affiliation_strings":["Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066481414","display_name":"Sawrawit Chairat","orcid":"https://orcid.org/0000-0002-4629-3924"},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sawrawit Chairat","raw_affiliation_strings":["Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023543381","display_name":"Kanakorn Horsiritham","orcid":"https://orcid.org/0000-0002-6215-5847"},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kanakorn Horsiritham","raw_affiliation_strings":["College of Digital Science, Prince of Songkla University,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Digital Science, Prince of Songkla University,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036521107","display_name":"Thammasin Ingviya","orcid":"https://orcid.org/0000-0002-8894-3817"},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Thammasin Ingviya","raw_affiliation_strings":["Prince of Songkla University,Faculty of Medicine,Department of Family and Preventive Medicine,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Songkla University,Faculty of Medicine,Department of Family and Preventive Medicine,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002547599","display_name":"Chanon Kongkamol","orcid":null},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chanon Kongkamol","raw_affiliation_strings":["Prince of Songkla University,Faculty of Medicine,Department of Family and Preventive Medicine,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Songkla University,Faculty of Medicine,Department of Family and Preventive Medicine,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069430065","display_name":"Sitthichok Chaichulee","orcid":"https://orcid.org/0000-0002-3159-7925"},"institutions":[{"id":"https://openalex.org/I131868736","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84","country_code":"TH","type":"education","lineage":["https://openalex.org/I131868736"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sitthichok Chaichulee","raw_affiliation_strings":["Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prince of Songkla University,Faculty of Medicine,Department of Biomedical Sciences and Biomedical Engineering,Songkhla,Thailand","institution_ids":["https://openalex.org/I131868736"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I131868736"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11296768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"648","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7458000183105469,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.7458000183105469,"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/downstream","display_name":"Downstream (manufacturing)","score":0.7916547060012817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800508737564087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5524800419807434},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42889365553855896},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42752906680107117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38120630383491516},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20509928464889526},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07312214374542236}],"concepts":[{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.7916547060012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800508737564087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5524800419807434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42889365553855896},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42752906680107117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38120630383491516},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20509928464889526},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07312214374542236},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcsse61278.2024.10613630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/jcsse61278.2024.10613630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 21st International Joint Conference on Computer Science and Software Engineering (JCSSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5570538293","display_name":null,"funder_award_id":"MED6601201S","funder_id":"https://openalex.org/F4320322692","funder_display_name":"Prince of Songkla University"}],"funders":[{"id":"https://openalex.org/F4320322692","display_name":"Prince of Songkla University","ror":"https://ror.org/0575ycz84"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2914120296","https://openalex.org/W2937845937","https://openalex.org/W2963026768","https://openalex.org/W2965373594","https://openalex.org/W3035390927","https://openalex.org/W3213545440","https://openalex.org/W4288089799","https://openalex.org/W4288099476","https://openalex.org/W4292199287","https://openalex.org/W4312220150","https://openalex.org/W4322718191","https://openalex.org/W4386701122","https://openalex.org/W4389519363","https://openalex.org/W6755207826","https://openalex.org/W6758293299","https://openalex.org/W6759455113","https://openalex.org/W6761672038","https://openalex.org/W6769263558","https://openalex.org/W6769627184","https://openalex.org/W6850625674"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W2055438207","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2349021146","https://openalex.org/W35583307","https://openalex.org/W4398294854","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Clinical":[0],"language":[1,29,58,71,126,133,153],"models":[2,30,37,127,154],"have":[3,31],"attracted":[4],"considerable":[5],"attention":[6],"in":[7,86],"recent":[8],"years":[9],"because":[10],"of":[11,69,83,99,151],"their":[12],"potential":[13],"to":[14,103,141,155],"improve":[15],"healthcare":[16],"workflows":[17],"a":[18],"nd":[19],"o":[20],"ptimise":[21],"patient":[22],"c":[23],"are.":[24],"While":[25],"many":[26],"pre-trained":[27],"clinical":[28,44,62,106,152,157,160],"been":[32],"published,":[33],"there":[34],"are":[35,49],"no":[36],"specifically":[38],"f":[39],"or":[40],"t":[41],"he":[42],"Thai":[43,57],"context,":[45],"where":[46],"English":[47],"terminologies":[48],"used":[50,60],"for":[51,61],"diseases,":[52],"procedures":[53],"and":[54,56,77,136,162],"medications,":[55],"is":[59],"notes.":[63],"This":[64],"study":[65,147],"investigated":[66,96],"the":[67,80,97,100,131,143,149],"pretraining":[68],"different":[70],"model":[72,102],"architectures,":[73],"namely":[74],"RoBERTa,":[75],"GPT-2":[76],"T5,":[78],"on":[79],"EHR":[81],"data":[82],"Songklanagarind":[84],"Hospital":[85],"Thailand,":[87],"which":[88],"includes":[89],"over":[90],"80":[91],"million":[92],"documents.":[93],"We":[94],"also":[95],"applications":[98],"pretrained":[101],"three":[104],"downstream":[105],"tasks:":[107],"tuberculosis":[108],"case":[109],"finding,":[110],"B":[111],"IRADS":[112],"category":[113],"classification":[114],"an":[115],"d":[116],"intraocular":[117],"pressure":[118],"extraction.":[119],"The":[120,146],"results":[121],"indicate":[122],"that":[123],"our":[124],"domain-specific":[125],"performed":[128],"better":[129],"than":[130],"general-purpose":[132],"model,":[134],"mBERT,":[135],"required":[137],"fewer":[138],"training":[139],"examples":[140],"achieve":[142],"same":[144],"performance.":[145],"encourages":[148],"use":[150],"streamline":[156],"workflows,":[158],"support":[159],"research":[161],"assist":[163],"hospital":[164],"auditing.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
