{"id":"https://openalex.org/W3160155166","doi":"https://doi.org/10.48550/arxiv.2105.03020","title":"Structured dataset documentation: a datasheet for CheXpert","display_name":"Structured dataset documentation: a datasheet for CheXpert","publication_year":2021,"publication_date":"2021-05-07","ids":{"openalex":"https://openalex.org/W3160155166","doi":"https://doi.org/10.48550/arxiv.2105.03020","mag":"3160155166"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2105.03020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03020","pdf_url":"https://arxiv.org/pdf/2105.03020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.03020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079476397","display_name":"Christian Garbin","orcid":"https://orcid.org/0000-0002-4261-5447","observed_orcids":["https://orcid.org/0000-0002-4261-5447"]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garbin, Christian","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001094226","display_name":"Pranav Rajpurkar","orcid":"https://orcid.org/0000-0002-8030-3727","observed_orcids":["https://orcid.org/0000-0002-8030-3727"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajpurkar, Pranav","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039154483","display_name":"Jeremy Irvin","orcid":"https://orcid.org/0000-0002-0395-4403","observed_orcids":["https://orcid.org/0000-0002-0395-4403"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irvin, Jeremy","raw_affiliation_strings":["Department of Computer Science Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038969629","display_name":"Matthew P. Lungren","orcid":"https://orcid.org/0000-0002-8591-5861","observed_orcids":["https://orcid.org/0000-0002-8591-5861","https://orcid.org/0000-0002-8457-9034"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lungren, Matthew P.","raw_affiliation_strings":["Department of Radiology Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology Stanford University","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073925867","display_name":"Oge Marques","orcid":"https://orcid.org/0000-0003-4321-2719","observed_orcids":["https://orcid.org/0000-0003-4321-2719"]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marques, Oge","raw_affiliation_strings":["Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Electrical Engineering and Computer Science Florida Atlantic University","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"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":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8353999853134155,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8353999853134155,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.11680000275373459,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.009700000286102295,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chexpert","display_name":"CheXpert","score":0.8659999966621399},{"id":"https://openalex.org/keywords/chest-x-ray-images","display_name":"chest X-ray images","score":0.8460000157356262},{"id":"https://openalex.org/keywords/medical-image-annotation","display_name":"medical image annotation","score":0.6449999809265137},{"id":"https://openalex.org/keywords/dataset-documentation","display_name":"dataset documentation","score":0.5099999904632568},{"id":"https://openalex.org/keywords/deep-learning-for-medical-diagnosis","display_name":"deep learning for medical diagnosis","score":0.531000018119812}],"concepts":[{"id":"https://openalex.org/C2781384022","wikidata":"https://www.wikidata.org/wiki/Q1172383","display_name":"Datasheet","level":2,"score":0.8328930139541626},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.8196491599082947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882938385009766},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7233108282089233},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6021534204483032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5766583681106567},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5737814903259277},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.5069591999053955},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49285006523132324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4771142303943634},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.43250808119773865},{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.4128419756889343},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C194828623","wikidata":"https://www.wikidata.org/wiki/Q2861470","display_name":"Emergency medicine","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2105.03020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03020","pdf_url":"https://arxiv.org/pdf/2105.03020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3160155166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.03020v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2105.03020","doi":"https://doi.org/10.48550/arxiv.2105.03020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.03020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.03020","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03020","pdf_url":"https://arxiv.org/pdf/2105.03020","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2102634410","https://openalex.org/W2811374795","https://openalex.org/W2913279579","https://openalex.org/W2933063649","https://openalex.org/W2963466845","https://openalex.org/W2971686358","https://openalex.org/W3016623626","https://openalex.org/W3030030520","https://openalex.org/W3123343728","https://openalex.org/W4288076040"],"related_works":["https://openalex.org/W4399251815","https://openalex.org/W2963466845","https://openalex.org/W3114128166","https://openalex.org/W3086523768","https://openalex.org/W7222725672","https://openalex.org/W6908287002","https://openalex.org/W2912664121","https://openalex.org/W4291021452","https://openalex.org/W4399453989","https://openalex.org/W3143195296"],"abstract_inverted_index":{"Billions":[0],"of":[1,43,62,88,97,118,124,130,136,152,160,174,179],"X-ray":[2],"images":[3],"are":[4],"taken":[5],"worldwide":[6],"each":[7],"year.":[8],"Machine":[9],"learning,":[10],"and":[11,23,74,91,115,122,157,172,181],"deep":[12,27,55],"learning":[13,28,56,114],"in":[14,47,85,101,111],"particular,":[15],"has":[16],"shown":[17],"potential":[18],"to":[19,53,77,92,107,140,149,154],"help":[20],"radiologists":[21,84],"triage":[22],"diagnose":[24],"images.":[25],"However,":[26],"requires":[29],"large":[30],"datasets":[31,175],"with":[32,40],"reliable":[33,89,182],"labels.":[34],"The":[35],"CheXpert":[36,72],"dataset":[37,99,144],"was":[38],"created":[39],"the":[41,48,59,70,79,86,94,98,109,112,119,128,150,167,170,177],"participation":[42],"board-certified":[44],"radiologists,":[45],"resulting":[46],"strong":[49],"ground":[50],"truth":[51],"needed":[52],"train":[54],"networks.":[57],"Following":[58],"structured":[60,104,158],"format":[61],"Datasheets":[63],"for":[64],"Datasets,":[65],"this":[66,137,143],"paper":[67,73,138],"expands":[68],"on":[69],"original":[71],"other":[75],"sources":[76],"show":[78],"critical":[80],"role":[81],"played":[82],"by":[83],"creation":[87,168,178],"labels":[90],"describe":[93],"different":[95],"aspects":[96],"composition":[100],"detail.":[102],"Such":[103],"documentation":[105],"intends":[106],"increase":[108],"awareness":[110],"machine":[113],"medical":[116,131],"communities":[117],"strengths,":[120],"applications,":[121],"evolution":[123],"CheXpert,":[125],"thereby":[126],"advancing":[127],"field":[129],"image":[132],"analysis.":[133],"Another":[134],"objective":[135],"is":[139],"put":[141],"forward":[142],"datasheet":[145],"as":[146],"an":[147],"example":[148],"community":[151],"how":[153],"create":[155],"detailed":[156],"descriptions":[159],"datasets.":[161],"We":[162],"believe":[163],"that":[164],"clearly":[165],"documenting":[166],"process,":[169],"contents,":[171],"applications":[173],"accelerates":[176],"useful":[180],"models.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2021-05-24T00:00:00"}