{"id":"https://openalex.org/W4417453809","doi":"https://doi.org/10.1186/s13326-025-00341-6","title":"SimSUM \u2013 simulated benchmark with structured and unstructured medical records","display_name":"SimSUM \u2013 simulated benchmark with structured and unstructured medical records","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W4417453809","doi":"https://doi.org/10.1186/s13326-025-00341-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/41413824"},"language":"en","primary_location":{"id":"doi:10.1186/s13326-025-00341-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-025-00341-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13326-025-00341-6.pdf","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13326-025-00341-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036557773","display_name":"Paloma Rabaey","orcid":"https://orcid.org/0000-0001-6064-0788"},"institutions":[{"id":"https://openalex.org/I12607205","display_name":"HOGENT University of Applied Sciences and Arts","ror":"https://ror.org/00rs45z86","country_code":"BE","type":"education","lineage":["https://openalex.org/I12607205"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Paloma Rabaey","raw_affiliation_strings":["Department of Information Technology, Ghent University - Imec, Ghent, Belgium. paloma.rabaey@ugent.be","Department of Information Technology, Ghent University \u2013 Imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Ghent University - Imec, Ghent, Belgium. paloma.rabaey@ugent.be","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Information Technology, Ghent University \u2013 Imec, Ghent, Belgium","institution_ids":["https://openalex.org/I12607205","https://openalex.org/I32597200","https://openalex.org/I39327780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067370682","display_name":"Stefan Heytens","orcid":"https://orcid.org/0000-0003-1097-4987"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stefan Heytens","raw_affiliation_strings":["Department of Public Health and Primary Care, Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Public Health and Primary Care, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075509168","display_name":"Thomas Demeester","orcid":"https://orcid.org/0000-0002-9901-5768"},"institutions":[{"id":"https://openalex.org/I12607205","display_name":"HOGENT University of Applied Sciences and Arts","ror":"https://ror.org/00rs45z86","country_code":"BE","type":"education","lineage":["https://openalex.org/I12607205"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thomas Demeester","raw_affiliation_strings":["Department of Information Technology, Ghent University - Imec, Ghent, Belgium","Department of Information Technology, Ghent University \u2013 Imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Ghent University - Imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Information Technology, Ghent University \u2013 Imec, Ghent, Belgium","institution_ids":["https://openalex.org/I12607205","https://openalex.org/I32597200","https://openalex.org/I39327780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036557773"],"corresponding_institution_ids":["https://openalex.org/I12607205","https://openalex.org/I32597200","https://openalex.org/I39327780"],"apc_list":{"value":1340,"currency":"USD","value_usd":1340},"apc_paid":{"value":1340,"currency":"USD","value_usd":1340},"fwci":2.5289,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9138562,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3449999988079071,"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":0.3449999988079071,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.3050999939441681,"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/T10350","display_name":"Electronic Health Records Systems","score":0.10740000009536743,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7181000113487244},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6617000102996826},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.42579999566078186},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.40459999442100525},{"id":"https://openalex.org/keywords/clinical-decision-support-system","display_name":"Clinical decision support system","score":0.39469999074935913},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.38429999351501465},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399999737739563},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7181000113487244},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6617000102996826},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4903999865055084},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4652999937534332},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4043000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25450000166893005}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","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":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1186/s13326-025-00341-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-025-00341-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13326-025-00341-6.pdf","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmid:41413824","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41413824","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":"Journal of biomedical semantics","raw_type":null},{"id":"pmh:oai:archive.ugent.be:01KCRY6P1SEVTB77Z91JXJK4C5","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01KCRY6P1SEVTB77Z91JXJK4C5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISSN: 2041-1480","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:archive.ugent.be:01KE702MV1MBTZYKH70S46PPEB","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KE702MV1MBTZYKH70S46PPEB","pdf_url":"https://biblio.ugent.be/publication/01KE702MV1MBTZYKH70S46PPEB/file/01KE703FN7B0Z0BY1V6Q8JV1CJ.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2041-1480","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:148d5e84d2a54e98917650572cac4533","is_oa":true,"landing_page_url":"https://doaj.org/article/148d5e84d2a54e98917650572cac4533","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":"Journal of Biomedical Semantics, Vol 16, Iss 1, Pp 1-30 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12713242","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12713242/","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Biomed Semantics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13326-025-00341-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13326-025-00341-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13326-025-00341-6.pdf","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417453809.pdf","grobid_xml":"https://content.openalex.org/works/W4417453809.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2072063551","https://openalex.org/W2275580678","https://openalex.org/W2283041611","https://openalex.org/W2396881363","https://openalex.org/W2768488789","https://openalex.org/W2805183640","https://openalex.org/W2889764698","https://openalex.org/W2945976633","https://openalex.org/W2973871066","https://openalex.org/W2981363289","https://openalex.org/W2999615587","https://openalex.org/W3017637887","https://openalex.org/W3080429061","https://openalex.org/W3095791468","https://openalex.org/W3160137267","https://openalex.org/W3160838879","https://openalex.org/W3198654417","https://openalex.org/W3216660278","https://openalex.org/W4224022798","https://openalex.org/W4289528791","https://openalex.org/W4307498511","https://openalex.org/W4316499895","https://openalex.org/W4320525813","https://openalex.org/W4381587418","https://openalex.org/W4384071683","https://openalex.org/W4385456320","https://openalex.org/W4385573654","https://openalex.org/W4386778113","https://openalex.org/W4389518633","https://openalex.org/W4390490761","https://openalex.org/W4391940656","https://openalex.org/W4392005379","https://openalex.org/W4392186815","https://openalex.org/W4400123292","https://openalex.org/W4400977241","https://openalex.org/W4404239715","https://openalex.org/W4408031728"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Clinical":[1],"information":[2,26,172],"extraction,":[3],"which":[4,181],"involves":[5],"structuring":[6],"clinical":[7,42,70,121,171,212,242],"concepts":[8,43,189],"from":[9,20,98,195],"unstructured":[10,69],"medical":[11],"text,":[12,46,219],"remains":[13],"a":[14,51,59,79,99,120,256],"challenging":[15],"problem":[16],"that":[17,67],"could":[18],"benefit":[19],"the":[21,45,48,83,124,155,175,196,200,209,224],"inclusion":[22],"of":[23,62,85,177,190,202,211,226],"tabular":[24,90,156,178,216,227],"background":[25,74,179],"available":[27,264],"in":[28,44,82,174,199,223,255],"electronic":[29],"health":[30],"records.":[31],"Existing":[32],"open-source":[33],"datasets":[34],"lack":[35],"explicit":[36],"links":[37],"between":[38],"structured":[39,73],"features":[40],"and":[41,88,104,128,148,157,218,231,258],"motivating":[47],"need":[49],"for":[50,240],"new":[52],"research":[53,169,207,254],"dataset.":[54],"METHODS:":[55],"We":[56,139],"introduce":[57],"SimSUM":[58,162,236],"benchmark":[60],"dataset":[61,163,262],"10,000":[63],"simulated":[64],"patient":[65,80],"records":[66],"link":[68],"notes":[71,132],"with":[72,135],"variables.":[75],"Each":[76],"record":[77],"simulates":[78],"encounter":[81],"domain":[84,109,186],"respiratory":[86],"diseases":[87],"includes":[89],"data":[91,217,234],"(e.g.,":[92],"symptoms,":[93],"diagnoses,":[94],"underlying":[95],"conditions)":[96],"generated":[97],"Bayesian":[100],"network":[101],"whose":[102],"structure":[103],"parameters":[105],"are":[106,133],"defined":[107],"by":[108],"experts.":[110],"A":[111],"large":[112],"language":[113],"model":[114],"(GPT-4o)":[115],"is":[116,164,237,263],"prompted":[117],"to":[118,144,167,188,192,251],"generate":[119],"note":[122,146],"describing":[123],"encounter,":[125],"including":[126],"symptoms":[127,198],"relevant":[129],"context.":[130],"These":[131],"annotated":[134],"span-level":[136],"symptom":[137],"mentions.":[138],"conduct":[140],"an":[141],"expert":[142],"evaluation":[143],"assess":[145],"quality":[147],"run":[149],"baseline":[150],"predictive":[151],"models":[152],"on":[153,170,208],"both":[154,215],"textual":[158,229],"data.":[159],"CONCLUSION:":[160],"The":[161,261],"primarily":[165],"designed":[166],"support":[168,244],"extraction":[173],"presence":[176,225],"variables,":[180],"can":[182],"be":[183,193],"linked":[184],"through":[185],"knowledge":[187],"interest":[191],"extracted":[194],"text\u2014namely,":[197],"case":[201],"SimSUM.":[203],"Secondary":[204],"uses":[205],"include":[206],"automation":[210],"reasoning":[213],"over":[214],"causal":[220],"effect":[221],"estimation":[222],"and/or":[228],"confounders,":[230],"multi-modal":[232],"synthetic":[233],"generation.":[235],"not":[238],"intended":[239],"training":[241],"decision":[243],"systems":[245],"or":[246],"production-grade":[247],"models,":[248],"but":[249],"rather":[250],"facilitate":[252],"reproducible":[253],"simplified":[257],"controlled":[259],"setting.":[260],"at":[265],"https://github.com/prabaey/SimSUM":[266],".":[267]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-12-18T00:00:00"}