{"id":"https://openalex.org/W4406457803","doi":"https://doi.org/10.1109/bigdata62323.2024.10825057","title":"EHRGPT: Leveraging language models for generating synthetic health records","display_name":"EHRGPT: Leveraging language models for generating synthetic health records","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457803","doi":"https://doi.org/10.1109/bigdata62323.2024.10825057"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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/A5065642629","display_name":"Giridhar Pamisetty","orcid":"https://orcid.org/0000-0001-5945-6860"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Giridhar Pamisetty","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Electrical Engineering,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080188532","display_name":"Subbareddy Batreddy","orcid":"https://orcid.org/0000-0002-3265-4100"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subbareddy Batreddy","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Electrical Engineering,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Electrical Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109191017","display_name":"Priya Ranjan Prasad Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I187424834","display_name":"Administrative Staff College of India","ror":"https://ror.org/00death42","country_code":"IN","type":"education","lineage":["https://openalex.org/I187424834"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priya Verma","raw_affiliation_strings":["Administrative Staff College of India,Centre for Management Studies,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Administrative Staff College of India,Centre for Management Studies,Hyderabad,India","institution_ids":["https://openalex.org/I187424834"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082756334","display_name":"Ch. Sobhan Babu","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ch Sobhan Babu","raw_affiliation_strings":["Indian Institute of Technology,Dept. of Computer Science and Engineering,Hyderabad,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Dept. of Computer Science and Engineering,Hyderabad,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065642629"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70991741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4579","last_page":"4587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9990000128746033,"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":0.9990000128746033,"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/T11719","display_name":"Data Quality and Management","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.7527914047241211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4980320930480957},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.47052040696144104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37586328387260437},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32309699058532715},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.20109984278678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527914047241211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4980320930480957},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.47052040696144104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37586328387260437},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32309699058532715},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.20109984278678894},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1600293573","https://openalex.org/W1665563134","https://openalex.org/W2041069220","https://openalex.org/W2051267297","https://openalex.org/W2064675550","https://openalex.org/W2066203299","https://openalex.org/W2112289862","https://openalex.org/W2148143831","https://openalex.org/W2162800060","https://openalex.org/W2467604901","https://openalex.org/W2535690855","https://openalex.org/W2586756136","https://openalex.org/W2803782214","https://openalex.org/W2904931021","https://openalex.org/W2962784628","https://openalex.org/W2980100290","https://openalex.org/W3124513372","https://openalex.org/W3160590016","https://openalex.org/W3184998487","https://openalex.org/W4200366874","https://openalex.org/W4235186792","https://openalex.org/W4285149890","https://openalex.org/W4287901133","https://openalex.org/W4292779060","https://openalex.org/W4306178203","https://openalex.org/W4310917402","https://openalex.org/W4313439128","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W4401110270","https://openalex.org/W6640963894","https://openalex.org/W6688384872","https://openalex.org/W6720208624","https://openalex.org/W6735926176","https://openalex.org/W6739901393","https://openalex.org/W6774580004","https://openalex.org/W6778883912","https://openalex.org/W6787753657","https://openalex.org/W6846967249","https://openalex.org/W7038994942"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Electronic":[0],"health":[1,11,20,127],"records":[2,8],"(EHRs)":[3],"are":[4,29,67],"the":[5,37,40,61,91,97,103,107,125,139,145,152,156,170,174],"comprehensive":[6],"digital":[7],"containing":[9],"patient":[10,93,131],"information,":[12],"which":[13],"help":[14],"in":[15,96,112],"various":[16],"domains":[17],"like":[18],"public":[19],"monitoring,":[21],"predictive":[22],"modeling,":[23],"data-driven":[24],"research,":[25],"etc.":[26],"However,":[27],"there":[28,44],"strict":[30],"regulations":[31],"about":[32,75],"data":[33,54,99,168],"sharing":[34],"due":[35],"to":[36,64,89,123,137,147],"sensitivity":[38],"of":[39,60,82,109,129,155,173],"EHR":[41,53,65,167],"data.":[42,176],"So,":[43],"is":[45],"an":[46],"increasing":[47],"demand":[48],"for":[49,85,132],"generating":[50],"high-quality":[51],"synthetic":[52],"that":[55],"mitigates":[56],"privacy":[57,165],"concerns.":[58],"Most":[59],"existing":[62],"approaches":[63],"generation":[66],"limited":[68],"as":[69,142],"they":[70],"predominantly":[71],"generate":[72,124,163],"binary":[73],"decisions":[74],"affecting":[76],"a":[77,86,117,130],"disease":[78,83],"or":[79],"count-based":[80],"summaries":[81],"occurrences":[84],"patient,":[87],"failing":[88],"capture":[90,148],"full":[92],"trajectory":[94],"contained":[95],"real":[98,175],"and":[100,151],"hence":[101],"reducing":[102],"downstream":[104],"applications.":[105],"With":[106],"success":[108],"language":[110,118],"models":[111],"generative":[113],"approaches,":[114],"we":[115],"propose":[116,136],"modeling":[119],"approach":[120],"using":[121],"transformers":[122],"complete":[126],"record":[128],"each":[133],"admission.":[134],"We":[135],"group":[138],"patient\u2019s":[140],"EHRs":[141],"it":[143],"enhances":[144],"model":[146,161],"temporal":[149],"coherence":[150],"medical":[153],"history":[154],"corresponding":[157],"patient.":[158],"The":[159],"proposed":[160],"can":[162],"high-fidelity":[164],"preserved":[166],"with":[169],"statistical":[171],"properties":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}