{"id":"https://openalex.org/W4392477433","doi":"https://doi.org/10.2196/preprints.57484","title":"Considerations for health care institutions training large language models on electronic health records (Preprint)","display_name":"Considerations for health care institutions training large language models on electronic health records (Preprint)","publication_year":2024,"publication_date":"2024-02-18","ids":{"openalex":"https://openalex.org/W4392477433","doi":"https://doi.org/10.2196/preprints.57484"},"language":"en","primary_location":{"id":"doi:10.2196/preprints.57484","doi":"https://doi.org/10.2196/preprints.57484","is_oa":true,"landing_page_url":"https://doi.org/10.2196/preprints.57484","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2196/preprints.57484","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062009708","display_name":"Weipeng Zhou","orcid":"https://orcid.org/0000-0003-1215-8043","observed_orcids":["https://orcid.org/0000-0003-1215-8043"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weipeng Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039369605","display_name":"Danielle S. Bitterman","orcid":"https://orcid.org/0000-0003-0345-2232","observed_orcids":["https://orcid.org/0000-0003-0345-2232"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danielle Bitterman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063499248","display_name":"Majid Afshar","orcid":"https://orcid.org/0000-0002-6368-4652","observed_orcids":["https://orcid.org/0000-0002-6368-4652"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Majid Afshar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039901099","display_name":"Timothy A. Miller","orcid":"https://orcid.org/0000-0003-4513-403X","observed_orcids":["https://orcid.org/0000-0003-4513-403X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy A. Miller","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4513-403X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.7871000170707703,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.7871000170707703,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.19449999928474426,"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/T10028","display_name":"Topic Modeling","score":0.00800000037997961,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9850000143051147},{"id":"https://openalex.org/keywords/training-costs","display_name":"training costs","score":0.3970000147819519},{"id":"https://openalex.org/keywords/training-funding","display_name":"training funding","score":0.6859999895095825},{"id":"https://openalex.org/keywords/continual-pre-training","display_name":"continual pre-training","score":0.7390000224113464},{"id":"https://openalex.org/keywords/training-duration","display_name":"training duration","score":0.7940000295639038},{"id":"https://openalex.org/keywords/healthcare-facilities","display_name":"healthcare facilities","score":0.8130000233650208}],"concepts":[{"id":"https://openalex.org/C43169469","wikidata":"https://www.wikidata.org/wiki/Q580922","display_name":"Preprint","level":2,"score":0.9673576354980469},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5897179841995239},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5651667714118958},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.5101099610328674},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.4769938588142395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33619099855422974},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33164840936660767},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2667171061038971},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19723400473594666},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19675958156585693},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2196/preprints.57484","doi":"https://doi.org/10.2196/preprints.57484","is_oa":true,"landing_page_url":"https://doi.org/10.2196/preprints.57484","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.2196/preprints.57484","doi":"https://doi.org/10.2196/preprints.57484","is_oa":true,"landing_page_url":"https://doi.org/10.2196/preprints.57484","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.504800021648407,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387030566","https://openalex.org/W4415319839","https://openalex.org/W4416608639","https://openalex.org/W7163016947","https://openalex.org/W4402796316","https://openalex.org/W4405029851","https://openalex.org/W7122668742","https://openalex.org/W4393407423","https://openalex.org/W4417507934","https://openalex.org/W7160293740"],"abstract_inverted_index":{"BACKGROUND":[0],"Large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5,40],"usually":[6],"built":[7],"(pretrained)":[8],"on":[9,33,56,98,168,183],"general":[10],"domain":[11],"data.":[12,37],"To":[13],"adapt":[14],"LLMs":[15,31,182,210,237],"better":[16,85],"to":[17,29,43,73,78,190,206],"health":[18,26,82,197,228],"care":[19,27,83,198,229],"needs,":[20],"it":[21],"might":[22],"be":[23,187,218],"beneficial":[24],"for":[25,90,220,227],"institutions":[28,84,199,230],"create":[30],"pretrained":[32,59,173],"their":[34,208,239],"own":[35,209],"EHR":[36,63,138,151,167,184],"Nevertheless,":[38],"there":[39],"concerns":[41,76],"related":[42],"the":[44,47,62,109,150,203,234],"training":[45,110,118],"budget,":[46,111],"type":[48],"of":[49,58,69,137,236],"pretraining":[50,55,102,114,124,163,216],"(pretraining":[51],"from":[52,131,211],"scratch":[53,132],"vs.":[54],"top":[57],"LLMs),":[60],"and":[61,77,88,104,117,140,192,213],"database":[64,115,193],"size.":[65],"OBJECTIVE":[66],"The":[67],"objective":[68],"this":[70],"manuscript":[71],"is":[72,153],"address":[74],"these":[75],"help":[79],"decision-makers":[80],"at":[81],"understand":[86],"opportunities":[87],"challenges":[89],"LLM":[91,112,127,174],"development.":[92],"METHODS":[93],"We":[94,121],"use":[95],"published":[96],"work":[97],"empirical":[99],"experience":[100],"in":[101,238],"LLMs,":[103],"establish":[105],"a":[106,125,145,169,225],"relationship":[107],"between":[108],"size,":[113],"size":[116,194],"time.":[119],"RESULTS":[120],"found":[122],"that":[123],"modest-sized":[126],"(13":[128],"billion":[129,147,171],"parameters)":[130],"requires":[133],"around":[134],"800":[135],"GB":[136,166],"data":[139,185],"costs":[141],"127,000":[142],"USD.":[143,159,178],"For":[144],"65":[146,170],"parameter":[148,172],"LLM,":[149],"requirement":[152],"4000":[154],"GB,":[155],"costing":[156],"3":[157],"million":[158],"In":[160],"comparison,":[161],"continued":[162,215],"using":[164],"500":[165],"would":[175],"cost":[176],"400,000":[177],"CONCLUSIONS":[179],"Building":[180],"private":[181],"can":[186],"challenging":[188,219],"due":[189],"budget":[191],"limitations.":[195],"Most":[196],"will":[200,217],"not":[201],"have":[202],"required":[204],"resources":[205],"train":[207],"scratch,":[212],"even":[214],"many.":[221],"This":[222],"study":[223],"provides":[224],"framework":[226],"when":[231],"deciding":[232],"about":[233],"deployment":[235],"systems.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2024-03-06T00:00:00"}