{"id":"https://openalex.org/W4400056759","doi":"https://doi.org/10.3389/fdata.2024.1371680","title":"MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain","display_name":"MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400056759","doi":"https://doi.org/10.3389/fdata.2024.1371680","pmid":"https://pubmed.ncbi.nlm.nih.gov/38988646"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2024.1371680","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1371680","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1371680/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1371680/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051568671","display_name":"Alaa Marshan","orcid":"https://orcid.org/0000-0001-6764-9160"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alaa Marshan","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111240138","display_name":"Anwar Nais Almutairi","orcid":null},"institutions":[{"id":"https://openalex.org/I143601524","display_name":"Public Authority for Applied Education and Training","ror":"https://ror.org/024242h31","country_code":"KW","type":"education","lineage":["https://openalex.org/I143601524"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Anwar Nais Almutairi","raw_affiliation_strings":["College of Business Studies, PAAET, Kuwait City, Kuwait"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Business Studies, PAAET, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I143601524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038247020","display_name":"Athina Ioannou","orcid":"https://orcid.org/0000-0001-7038-938X"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Athina Ioannou","raw_affiliation_strings":["Surrey Business School, University of Surrey, Guildford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Surrey Business School, University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103043663","display_name":"David R. Bell","orcid":"https://orcid.org/0000-0002-9418-7886"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Bell","raw_affiliation_strings":["Department of Computer Science, Brunel University London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brunel University London, London, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065339802","display_name":"Asmat Monaghan","orcid":null},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Asmat Monaghan","raw_affiliation_strings":["School of Business and Management, Royal Holloway, University of London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business and Management, Royal Holloway, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077607362","display_name":"Mahir Arzoky","orcid":null},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mahir Arzoky","raw_affiliation_strings":["Department of Computer Science, Brunel University London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brunel University London, London, United Kingdom","institution_ids":["https://openalex.org/I59433898"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051568671"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":5.3462,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96105992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"1371680","last_page":"1371680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35010001063346863,"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":0.35010001063346863,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12309999763965607,"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":0.07479999959468842,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6296709775924683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5863128304481506},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5405480265617371},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.5077506303787231},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38790225982666016},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29828473925590515},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1763196885585785},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1039116382598877},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0796210765838623}],"concepts":[{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6296709775924683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863128304481506},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5405480265617371},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.5077506303787231},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38790225982666016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29828473925590515},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1763196885585785},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1039116382598877},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0796210765838623},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fdata.2024.1371680","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1371680","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1371680/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:38988646","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38988646","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:bura.brunel.ac.uk:2438/29710","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/29710","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/29710/1/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"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":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11233734","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11233734","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11233734/pdf/fdata-07-1371680.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:15e2340838f4410d9e135e9de8586159","is_oa":true,"landing_page_url":"https://doaj.org/article/15e2340838f4410d9e135e9de8586159","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":"Frontiers in Big Data, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2024.1371680","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1371680","pdf_url":"https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1371680/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400056759.pdf"},"referenced_works_count":99,"referenced_works":["https://openalex.org/W1496189301","https://openalex.org/W1603598191","https://openalex.org/W1606653819","https://openalex.org/W1810943226","https://openalex.org/W2029907219","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2145618437","https://openalex.org/W2155027007","https://openalex.org/W2163274265","https://openalex.org/W2181417294","https://openalex.org/W2250539671","https://openalex.org/W2269738476","https://openalex.org/W2396881363","https://openalex.org/W2515682654","https://openalex.org/W2536574992","https://openalex.org/W2587019100","https://openalex.org/W2599674900","https://openalex.org/W2751448157","https://openalex.org/W2768409085","https://openalex.org/W2891000242","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2912500072","https://openalex.org/W2913954081","https://openalex.org/W2945102109","https://openalex.org/W2962713807","https://openalex.org/W2962739339","https://openalex.org/W2963854351","https://openalex.org/W2964373647","https://openalex.org/W2965373594","https://openalex.org/W2969670656","https://openalex.org/W2970002529","https://openalex.org/W2978017171","https://openalex.org/W2998701638","https://openalex.org/W3013119194","https://openalex.org/W3022196370","https://openalex.org/W3022893496","https://openalex.org/W3031696893","https://openalex.org/W3046744391","https://openalex.org/W3088018251","https://openalex.org/W3096744741","https://openalex.org/W3103801878","https://openalex.org/W3121273931","https://openalex.org/W3139060586","https://openalex.org/W3150263485","https://openalex.org/W3173274550","https://openalex.org/W3209235691","https://openalex.org/W3214600982","https://openalex.org/W4205918858","https://openalex.org/W4224316871","https://openalex.org/W4288089799","https://openalex.org/W4288601872","https://openalex.org/W4295312788","https://openalex.org/W4366769280","https://openalex.org/W4382202531","https://openalex.org/W4385245566","https://openalex.org/W4385572953","https://openalex.org/W4385573058","https://openalex.org/W4388975618","https://openalex.org/W6629631241","https://openalex.org/W6636510571","https://openalex.org/W6638273328","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6683204974","https://openalex.org/W6684031499","https://openalex.org/W6685974346","https://openalex.org/W6725207838","https://openalex.org/W6733081445","https://openalex.org/W6737850504","https://openalex.org/W6739901393","https://openalex.org/W6743367031","https://openalex.org/W6745921949","https://openalex.org/W6748634344","https://openalex.org/W6750396386","https://openalex.org/W6753816834","https://openalex.org/W6754576135","https://openalex.org/W6754969413","https://openalex.org/W6755207826","https://openalex.org/W6756315458","https://openalex.org/W6757817989","https://openalex.org/W6758814090","https://openalex.org/W6763701032","https://openalex.org/W6765899115","https://openalex.org/W6766669437","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6767606193","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6769642167","https://openalex.org/W6772920163","https://openalex.org/W6775410893","https://openalex.org/W6777040464","https://openalex.org/W6780226713","https://openalex.org/W6784229166","https://openalex.org/W6809680184","https://openalex.org/W6849716403"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Introduction:":[0],"In":[1],"response":[2],"to":[3,24,53,74,239,247],"the":[4,92,104,127,130,135,142,164,193,196,201,233],"increasing":[5],"prevalence":[6],"of":[7,150,175,195,212,235],"electronic":[8],"medical":[9,40],"records":[10,22,34],"(EMRs)":[11],"stored":[12],"in":[13,29,117,169,205,244,252,261],"databases,":[14],"healthcare":[15,51,136,253],"staff":[16,52],"are":[17,35],"encountering":[18],"difficulties":[19],"retrieving":[20],"these":[21,33],"due":[23],"their":[25],"limited":[26],"technical":[27],"expertise":[28],"database":[30],"operations.":[31],"As":[32],"crucial":[36],"for":[37,46,50,64,97,134,180,218,258],"delivering":[38],"appropriate":[39],"care,":[41],"there":[42],"is":[43,124],"a":[44,69,110,256],"need":[45],"an":[47,210],"accessible":[48],"method":[49],"access":[54],"EMRs.":[55],"Methods:":[56],"To":[57],"address":[58],"this,":[59],"natural":[60,79,245],"language":[61,80,246],"processing":[62],"(NLP)":[63],"Text-to-SQL":[65,88,132],"has":[66],"emerged":[67],"as":[68],"solution,":[70],"enabling":[71],"non-technical":[72],"users":[73],"generate":[75],"SQL":[76,207],"queries":[77],"using":[78,154],"text.":[81],"This":[82,230],"research":[83,260],"assesses":[84],"existing":[85],"work":[86,231],"on":[87,126,145,198,214],"conversion":[89],"and":[90,153,158,178,187,216],"proposes":[91],"MedT5SQL":[93,143],"model":[94,102,123,144,165,197,202,238],"specifically":[95],"designed":[96],"EMR":[98],"retrieval.":[99],"The":[100,122],"proposed":[101],"utilizes":[103],"Text-to-Text":[105],"Transfer":[106],"Transformer":[107],"(T5)":[108],"model,":[109],"Large":[111],"Language":[112,250],"Model":[113],"(LLM)":[114],"commonly":[115],"used":[116],"various":[118],"text-based":[119],"NLP":[120],"tasks.":[121],"fine-tuned":[125,236],"MIMICSQL":[128,157,162],"dataset,":[129,163,200],"first":[131],"dataset":[133],"domain.":[137],"Performance":[138],"evaluation":[139],"involves":[140],"benchmarking":[141],"two":[146,155],"optimizers,":[147],"varying":[148],"numbers":[149],"training":[151,228],"epochs,":[152],"datasets,":[156],"WikiSQL.":[159],"Results:":[160],"For":[161],"demonstrates":[166,203],"considerable":[167],"effectiveness":[168],"generating":[170,206],"question-SQL":[171],"pairs":[172],"achieving":[173],"accuracy":[174,183,211],"80.63%,":[176],"98.937%,":[177],"90%":[179],"exact":[181],"match":[182],"matrix,":[184],"approximate":[185,219],"string-matching,":[186],"manual":[188],"evaluation,":[189],"respectively.":[190],"When":[191],"testing":[192],"performance":[194,225],"WikiSQL":[199,215],"efficiency":[204],"queries,":[208],"with":[209,226],"44.2%":[213],"94.26%":[217],"string-matching.":[220],"Discussion:":[221],"Results":[222],"indicate":[223],"improved":[224],"increased":[227],"epochs.":[229],"highlights":[232],"potential":[234],"T5":[237],"convert":[240],"medical-related":[241],"questions":[242],"written":[243],"Structured":[248],"Query":[249],"(SQL)":[251],"domain,":[254],"providing":[255],"foundation":[257],"future":[259],"this":[262],"area.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":12}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}