{"id":"https://openalex.org/W6944950402","doi":"https://doi.org/10.21227/kh7n-8n28","title":"MedCD: A Medical Clinical Dataset","display_name":"MedCD: A Medical Clinical Dataset","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W6944950402","doi":"https://doi.org/10.21227/kh7n-8n28"},"language":"en","primary_location":{"id":"doi:10.21227/kh7n-8n28","is_oa":true,"landing_page_url":"https://doi.org/10.21227/kh7n-8n28","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/kh7n-8n28","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen, Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110462","display_name":"Tiger Optics (United States)","ror":"https://ror.org/01mzcg363","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110462"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen, Ye","raw_affiliation_strings":["Tiger Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tiger Research","institution_ids":["https://openalex.org/I4210110462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210110462"],"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":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.597000002861023},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.5199000239372253},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4162999987602234},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.38119998574256897},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.374099999666214},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3675999939441681},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626800000667572},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289000272750854},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C106977388","wikidata":"https://www.wikidata.org/wiki/Q2752427","display_name":"Medical research","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C3018822202","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Patient data","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/kh7n-8n28","is_oa":true,"landing_page_url":"https://doi.org/10.21227/kh7n-8n28","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/kh7n-8n28","is_oa":true,"landing_page_url":"https://doi.org/10.21227/kh7n-8n28","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":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.451244592666626}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,248],"curated":[1],"and":[2,39,53,71,113,136,211,213,226,246,257,264,272],"release":[3],"a":[4,42,116,154,194,202,232],"real-world":[5,61],"medical":[6,195],"clinical":[7,23,66,92,122,159,206,220,236,260],"dataset,":[8],"namely":[9],"MedCD,":[10],"in":[11,21,41,46,55,138,262,274],"the":[12,22,31,49,74,95,125,170,178,254,265],"context":[13],"of":[14,30,98,107,127,145,156,164,173,205,234,240],"building":[15],"generative":[16,133,174,269],"artificial":[17],"intelligence":[18],"(AI)":[19],"applications":[20,207,237],"setting.":[24],"The":[25,101,109],"MedCD":[26,140,179,251],"dataset":[27,50,75,129,180,261],"is":[28,51,76,103,130,191,252],"one":[29],"accomplishments":[32],"from":[33,60,90],"our":[34],"longitudinal":[35],"applied":[36],"AI":[37,134,175,270],"research":[38,135,271],"deployment":[40],"tertiary":[43],"care":[44],"hospital":[45],"China.":[47],"First,":[48],"real":[52,157],"comprehensive,":[54],"that":[56,78,106,250],"it":[57],"was":[58,111],"sourced":[59],"electronic":[62],"health":[63],"records":[64],"(EHRs),":[65],"notes,":[67],"lab":[68],"examination":[69],"reports":[70],"more.":[72],"Second,":[73],"large,":[77],"contains":[79,143],"1\u00b77":[80],"million":[81],"EHR":[82],"examples":[83],"involving":[84],"more":[85],"than":[86],"250K":[87],"patients,":[88],"collected":[89],"30":[91],"departments":[93],"over":[94],"first":[96,266],"quarter":[97],"year":[99],"2024.":[100],"scale":[102,259],"comparable":[104],"to":[105,119,131],"MIMIC-IV.":[108],"data":[110,152,186,190,200,216],"de-identified":[112],"organized":[114,192],"into":[115],"format":[117],"similar":[118],"MIMIC-IV":[120],"free-text":[121],"notes.":[123],"Moreover,":[124],"objective":[126],"this":[128,241],"accelerate":[132],"development":[137,273],"healthcare.":[139,275],"not":[141],"only":[142],"millions":[144],"patients'":[146],"data,":[147,242],"but":[148],"also":[149],"features":[150],"supervised":[151,198],"for":[153,201,217,268],"variety":[155],"fundamental":[158,219],"tasks":[160,221],"with":[161],"months'":[162],"worth":[163],"annotation":[165],"endeavors":[166],"by":[167],"clinicians.":[168],"Following":[169],"general":[171],"paradigm":[172],"application":[176],"development,":[177],"consists":[181],"of:":[182],"(1)":[183],"unsupervised":[184],"pretraining":[185],"where":[187],"each":[188],"patient":[189,224],"as":[193,223,243],"document,":[196],"(2)":[197],"fine-tuning":[199],"wide":[203],"spectrum":[204,233],"including":[208],"NER,":[209],"retrieval":[210],"summarization,":[212],"(3)":[214],"benchmark":[215],"evaluating":[218],"such":[222],"triage":[225],"notes":[227],"generation.":[228],"Further,":[229],"we":[230],"describe":[231],"deployed":[235],"making":[238],"use":[239],"reference":[244],"implementation":[245],"baseline.":[247],"believe":[249],"to-date":[253],"most":[255],"comprehensive":[256],"largest":[258],"Chinese,":[263],"designed":[267]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}