{"id":"https://openalex.org/W6926129973","doi":"https://doi.org/10.21227/3sk0-2015","title":"SynSUM \u2013 Synthetic Benchmark with Structured and Unstructured Medical Records","display_name":"SynSUM \u2013 Synthetic Benchmark with Structured and Unstructured Medical Records","publication_year":2025,"publication_date":"2025-01-21","ids":{"openalex":"https://openalex.org/W6926129973","doi":"https://doi.org/10.21227/3sk0-2015"},"language":"en","primary_location":{"id":"doi:10.21227/3sk0-2015","is_oa":true,"landing_page_url":"https://doi.org/10.21227/3sk0-2015","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/3sk0-2015","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rabaey, Paloma","orcid":null},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Rabaey, Paloma","raw_affiliation_strings":["Ghent University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Heytens, Stefan","orcid":null},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Heytens, Stefan","raw_affiliation_strings":["Ghent University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"last","author":{"id":null,"display_name":"Demeester, Thomas","orcid":null},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Demeester, Thomas","raw_affiliation_strings":["Ghent University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University","institution_ids":["https://openalex.org/I2801227569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801227569"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T12951","display_name":"Burkholderia infections and melioidosis","score":0.9142000079154968,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T12951","display_name":"Burkholderia infections and melioidosis","score":0.9142000079154968,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T10665","display_name":"Cystic Fibrosis Research Advances","score":0.029500000178813934,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/T12824","display_name":"Infections and bacterial resistance","score":0.01720000058412552,"subfield":{"id":"https://openalex.org/subfields/1310","display_name":"Endocrinology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.5687999725341797},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.567799985408783},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5555999875068665},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5511000156402588},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.3978999853134155},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3693999946117401},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743399977684021},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5511000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/3sk0-2015","is_oa":true,"landing_page_url":"https://doi.org/10.21227/3sk0-2015","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/3sk0-2015","is_oa":true,"landing_page_url":"https://doi.org/10.21227/3sk0-2015","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,76],"present":[1],"the":[2,36,40,49,58,62,65,95,124,144,147,150,158,172],"SynSUM":[3,112],"benchmark,":[4],"a":[5,79,86],"synthetic":[6],"dataset":[7,16,113,184],"linking":[8],"unstructured":[9],"clinical":[10,33,87,161],"notes":[11,34,101],"to":[12,84,90,117,136,140],"structured background":[13],"variables.":[14],"The":[15,45,183],"consists":[17],"of":[18,42,48,126,138,152,160,174],"10,000":[19],"artificial":[20],"patient":[21,92],"records":[22],"containing":[23],"tabular":[24,46,127,165,175],"variables (like":[25],"symptoms,":[26,148],"diagnoses":[27],"and":[28,31,64,167,179,185],"underlying":[29],"conditions)":[30],"associated":[32],"describing":[35,94],"fictional patient":[37],"encounter":[38],"in":[39,123,149,171],"domain":[41,74],"respiratory":[43],"diseases.":[44],"portion":[47],"data":[50,166],"is":[51,114],"generated":[52],"through a":[53],"Bayesian":[54],"network,":[55],"where":[56],"both":[57,164],"causal":[59],"structure":[60],"between":[61],"variables":[63],"conditional":[66],"probabilities are":[67],"proposed":[68],"by":[69],"an":[70],"expert":[71],"based":[72],"on":[73,120,157],"knowledge.":[75],"then":[77],"prompt":[78],"large":[80],"language":[81],"model":[82],"(GPT-4o)":[83],"generate":[85],"note":[88],"related":[89],"this":[91],"encounter,":[93],"patient\u2019s":[96],"symptoms":[97],"and additional":[98],"context.":[99],"These":[100],"are":[102,187],"additionally":[103],"annotated":[104],"with":[105],"spans":[106],"indicating":[107],"which":[108,130],"phrases":[109],"mention which":[110],"symptom. The":[111],"primarily":[115],"designed":[116],"facilitate":[118],"research":[119,156],"clinical information":[121],"extraction":[122],"presence":[125,173],"background":[128],"variables,":[129],"can":[131],"be":[132,141],"linked":[133],"through":[134],"domain knowledge":[135],"concepts":[137],"interest":[139],"extracted":[142],"from":[143],"text":[145],"-":[146],"case":[151],"SynSUM. Secondary":[153],"uses":[154],"include":[155],"automation":[159],"reasoning":[162],"over":[163],"text, causal":[168],"effect":[169],"estimation":[170],"and/or":[176],"textual":[177],"confounders,":[178],"multi-modal":[180],"synthetic data":[181],"generation.":[182],"code":[186],"also":[188],"available":[189],"at":[190],"https://github.com/prabaey/SynSUM.":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}