{"id":"https://openalex.org/W4415659615","doi":"https://doi.org/10.1186/s12911-025-03055-y","title":"Pretrained language models for semantics-aware data harmonisation of observational clinical studies in the era of big data","display_name":"Pretrained language models for semantics-aware data harmonisation of observational clinical studies in the era of big data","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415659615","doi":"https://doi.org/10.1186/s12911-025-03055-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/41162963"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-025-03055-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03055-y","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-03055-y","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-03055-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047663237","display_name":"Jakub Dylag","orcid":"https://orcid.org/0000-0001-6263-7339"},"institutions":[{"id":"https://openalex.org/I4210118229","display_name":"NIHR Southampton Biomedical Research Centre","ror":"https://ror.org/01qqpzg67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2802965805","https://openalex.org/I4210118229","https://openalex.org/I43439940"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jakub J. Dylag","raw_affiliation_strings":["Highfield Campus, University of Southampton, Southampton, SO17 1BJ, UK. J.J.Dylag@soton.ac.uk","IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK. J.J.Dylag@soton.ac.uk","IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"raw_orcid":"https://orcid.org/0000-0001-6263-7339","affiliations":[{"raw_affiliation_string":"Highfield Campus, University of Southampton, Southampton, SO17 1BJ, UK. J.J.Dylag@soton.ac.uk","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK. J.J.Dylag@soton.ac.uk","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I4210118229"]},{"raw_affiliation_string":"IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I4210118229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086986674","display_name":"Zlatko Zlatev","orcid":"https://orcid.org/0000-0001-6275-5626"},"institutions":[{"id":"https://openalex.org/I4210118229","display_name":"NIHR Southampton Biomedical Research Centre","ror":"https://ror.org/01qqpzg67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2802965805","https://openalex.org/I4210118229","https://openalex.org/I43439940"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zlatko Zlatev","raw_affiliation_strings":["IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"raw_orcid":"https://orcid.org/0000-0001-6275-5626","affiliations":[{"raw_affiliation_string":"IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I4210118229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076941728","display_name":"Michael Boniface","orcid":"https://orcid.org/0000-0002-9281-6095"},"institutions":[{"id":"https://openalex.org/I4210118229","display_name":"NIHR Southampton Biomedical Research Centre","ror":"https://ror.org/01qqpzg67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2802965805","https://openalex.org/I4210118229","https://openalex.org/I43439940"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Boniface","raw_affiliation_strings":["IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"raw_orcid":"https://orcid.org/0000-0002-9281-6095","affiliations":[{"raw_affiliation_string":"IT Innovation Centre, Digital Health and Biomedical Engineering, School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940","https://openalex.org/I4210118229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047663237"],"corresponding_institution_ids":["https://openalex.org/I4210118229","https://openalex.org/I43439940"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":6.6032,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96572694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"400","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.4851999878883362,"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":0.4851999878883362,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2540000081062317,"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/T10028","display_name":"Topic Modeling","score":0.041099999099969864,"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/big-data","display_name":"Big data","score":0.8535000085830688},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8033999800682068},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5824999809265137},{"id":"https://openalex.org/keywords/health-informatics","display_name":"Health informatics","score":0.5623999834060669},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4447999894618988},{"id":"https://openalex.org/keywords/observational-study","display_name":"Observational study","score":0.40549999475479126},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3443000018596649}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8535000085830688},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8033999800682068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045999765396118},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6837000250816345},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.5623999834060669},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35420000553131104},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2567000091075897}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064887","descriptor_name":"Observational Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064887","descriptor_name":"Observational Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064887","descriptor_name":"Observational Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064887","descriptor_name":"Observational Studies as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12911-025-03055-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03055-y","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-03055-y","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:41162963","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41162963","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":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:78c723d7bc05484d8af8a5570f415594","is_oa":true,"landing_page_url":"https://doaj.org/article/78c723d7bc05484d8af8a5570f415594","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":"BMC Medical Informatics and Decision Making, Vol 25, Iss 1, Pp 1-15 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11383400","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12573878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12911-025-03055-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-025-03055-y","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/s12911-025-03055-y","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7653024225","display_name":"The development and validation of population clusters for integrating health and social care: A mixed-methods study on Multiple Long-Term Conditions","funder_award_id":"NIHR202637","funder_id":"https://openalex.org/F4320319990","funder_display_name":"National Institute for Health and Care Research"}],"funders":[{"id":"https://openalex.org/F4320319990","display_name":"National Institute for Health and Care Research","ror":"https://ror.org/0187kwz08"},{"id":"https://openalex.org/F4320319994","display_name":"Department of Health and Social Care","ror":"https://ror.org/03sbpja79"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415659615.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1697154133","https://openalex.org/W1840435438","https://openalex.org/W1981208470","https://openalex.org/W1985533374","https://openalex.org/W2038885294","https://openalex.org/W2082302018","https://openalex.org/W2090243146","https://openalex.org/W2108323654","https://openalex.org/W2113586398","https://openalex.org/W2127042504","https://openalex.org/W2143844589","https://openalex.org/W2150593711","https://openalex.org/W2155653793","https://openalex.org/W2160642098","https://openalex.org/W2161693184","https://openalex.org/W2171469118","https://openalex.org/W2243299842","https://openalex.org/W2250473257","https://openalex.org/W2251249502","https://openalex.org/W2264805935","https://openalex.org/W2278812662","https://openalex.org/W2294798173","https://openalex.org/W2296157284","https://openalex.org/W2575772377","https://openalex.org/W2576754561","https://openalex.org/W2616141209","https://openalex.org/W2751642492","https://openalex.org/W2792897917","https://openalex.org/W2889326414","https://openalex.org/W2891177506","https://openalex.org/W2909866185","https://openalex.org/W2919149650","https://openalex.org/W2963078909","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W2972437240","https://openalex.org/W3008374555","https://openalex.org/W3011922644","https://openalex.org/W3015453090","https://openalex.org/W3024922541","https://openalex.org/W3080232144","https://openalex.org/W3111667862","https://openalex.org/W3153125849","https://openalex.org/W3186799149","https://openalex.org/W3194782062","https://openalex.org/W3207095490","https://openalex.org/W3208762930","https://openalex.org/W4221153690","https://openalex.org/W4226158161","https://openalex.org/W4283024551","https://openalex.org/W4327965792","https://openalex.org/W4378417237","https://openalex.org/W6930143750"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1],"clinical":[2,111,260,303],"research,":[3],"there":[4],"is":[5,91,190],"a":[6,123,133,182,216,264],"strong":[7],"drive":[8],"to":[9,22,77,92,229,286],"leverage":[10,287],"big":[11,82,257,288],"data":[12,83,107,258,284,289,301],"from":[13,150,300],"population":[14],"cohort":[15],"studies":[16,296],"and":[17,29,48,58,63,72,86,96,132,247,254,292,297],"routine":[18],"electronic":[19],"healthcare":[20,34],"records":[21],"design":[23],"new":[24],"interventions,":[25],"improve":[26],"health":[27,283],"outcomes":[28],"increase":[30],"the":[31,65,79,101,151,206,239,252,270,273,280],"efficiency":[32],"of":[33,67,81,103,109,137,155,164,172,184,195,208,218,241,256,275],"delivery.":[35],"However,":[36],"realising":[37],"these":[38],"potential":[39,240],"demands":[40],"requires":[41],"substantial":[42],"efforts":[43],"in":[44,198,250,294],"harmonising":[45],"source":[46],"datasets":[47],"curating":[49],"study":[50,236],"data,":[51],"which":[52,189],"currently":[53],"relies":[54],"on":[55,191],"costly,":[56],"time-consuming":[57],"labour-intensive":[59],"methods.":[60],"We":[61,113,141,160],"explore":[62],"assess":[64],"use":[66],"natural":[68],"language":[69],"processing":[70],"(NLP)":[71],"unsupervised":[73,248],"machine":[74],"learning":[75],"(ML)":[76],"address":[78],"challenges":[80],"semantic":[84,121,178],"harmonisation":[85,253],"curation.":[87],"METHODS:":[88],"Our":[89,177,235],"aim":[90],"establish":[93],"an":[94,170],"efficient":[95],"robust":[97,265],"technological":[98,266],"foundation":[99],"for":[100,119,125,128,135,259,272,302],"development":[102,274],"automated":[104,120,225,276],"tools":[105,277],"supporting":[106],"curation":[108,255],"large":[110],"datasets.":[112],"propose":[114],"two":[115],"AI":[116,242],"based":[117],"pipelines":[118],"harmonisation:":[122],"pipeline":[124,134,143,180],"semantics-aware":[126],"search":[127],"domain":[129],"relevant":[130,200],"variables":[131],"clustering":[136,179],"semantically":[138],"similar":[139],"variables.":[140],"evaluate":[142],"performance":[144],"using":[145],"94,037":[146],"textual":[147],"variable":[148],"descriptions":[149,220,231],"English":[152],"Longitudinal":[153],"Study":[154],"Ageing":[156],"(ELSA)":[157],"database.":[158],"RESULTS:":[159],"observe":[161],"high":[162],"accuracy":[163],"our":[165,224],"Semantic":[166],"Search":[167],"pipeline,":[168],"with":[169,193,223],"AUC":[171],"0.899":[173],"(SD":[174,186],"=":[175,187],"0.056).":[176],"achieves":[181],"V-measure":[183],"0.237":[185],"0.157),":[188],"par":[192],"that":[194,278],"leading":[196],"implementations":[197],"other":[199],"domains.":[201],"Automation":[202],"can":[203],"significantly":[204],"accelerate":[205],"process":[207],"dataset":[209],"harmonisation.":[210],"Manual":[211],"labelling":[212,226],"was":[213],"performed":[214],"at":[215],"speed":[217,228],"2.1":[219],"per":[221,232],"minute,":[222],"increasing":[227],"245":[230],"minute.":[233],"CONCLUSIONS:":[234],"findings":[237],"underscore":[238],"technologies,":[243],"such":[244],"as":[245],"NLP":[246],"ML,":[249],"automating":[251],"research.":[261],"By":[262],"establishing":[263],"foundation,":[267],"we":[268],"pave":[269],"way":[271],"streamline":[279],"process,":[281],"enabling":[282],"scientists":[285],"more":[290],"efficiently":[291],"effectively":[293],"their":[295],"accelerating":[298],"insights":[299],"benefit.":[304]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
