{"id":"https://openalex.org/W6891884690","doi":"https://doi.org/10.48550/arxiv.2505.00228","title":"ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports","display_name":"ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-text Reports","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W6891884690","doi":"https://doi.org/10.48550/arxiv.2505.00228"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.00228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00228","pdf_url":"https://arxiv.org/pdf/2505.00228","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":"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.00228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhang, Xiaoman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Xiaoman","raw_affiliation_strings":["Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Acosta, Juli\u00e1n N.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Acosta, Juli\u00e1n N.","raw_affiliation_strings":["Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147139416","display_name":"Josh Miller","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miller, Josh","raw_affiliation_strings":["Gradient Health , Durham , NC , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradient Health , Durham , NC , USA,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018524234","display_name":"Ouwen Huang","orcid":"https://orcid.org/0000-0003-1670-4179","observed_orcids":["https://orcid.org/0000-0003-1670-4179"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Ouwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajpurkar, Pranav","raw_affiliation_strings":["Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics , Harvard Medical School , Boston , MA , USA,","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":36,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4027999937534332,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4027999937534332,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.33809998631477356,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.1914999932050705,"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/chest-x-ray","display_name":"chest radiography","score":0.8450000286102295},{"id":"https://openalex.org/keywords/radiology-reports","display_name":"radiology reports","score":0.7559999823570251},{"id":"https://openalex.org/keywords/automatic-report-generation","display_name":"automated reporting","score":0.9139999747276306},{"id":"https://openalex.org/keywords/medical-imaging-ai","display_name":"medical imaging AI","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C190892606","wikidata":"https://www.wikidata.org/wiki/Q3512464","display_name":"Radiological weapon","level":2,"score":0.6823999881744385},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.6270999908447266},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C36454342","wikidata":"https://www.wikidata.org/wiki/Q245341","display_name":"Radiography","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2994024180","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Radiological imaging","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3418000042438507},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C2989540662","wikidata":"https://www.wikidata.org/wiki/Q1418000","display_name":"Radiology information systems","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23909999430179596},{"id":"https://openalex.org/C3018822202","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Patient data","level":2,"score":0.22210000455379486},{"id":"https://openalex.org/C545542383","wikidata":"https://www.wikidata.org/wiki/Q2751242","display_name":"Medical emergency","level":1,"score":0.21230000257492065},{"id":"https://openalex.org/C3020132585","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic accuracy","level":2,"score":0.20819999277591705},{"id":"https://openalex.org/C2781137159","wikidata":"https://www.wikidata.org/wiki/Q1283318","display_name":"Chest radiograph","level":3,"score":0.20819999277591705},{"id":"https://openalex.org/C82157600","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic test","level":2,"score":0.2037000060081482},{"id":"https://openalex.org/C2909566329","wikidata":"https://www.wikidata.org/wiki/Q994554","display_name":"Thoracic diseases","level":2,"score":0.1899999976158142},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.181099995970726},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.17649999260902405},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.17560000717639923},{"id":"https://openalex.org/C2779231881","wikidata":"https://www.wikidata.org/wiki/Q5977147","display_name":"Medical literature","level":2,"score":0.17339999973773956},{"id":"https://openalex.org/C3019060180","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automated method","level":2,"score":0.17190000414848328},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.17110000550746918},{"id":"https://openalex.org/C2984538763","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring system","level":2,"score":0.17030000686645508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1647000014781952},{"id":"https://openalex.org/C2779549770","wikidata":"https://www.wikidata.org/wiki/Q1122413","display_name":"Computer-aided diagnosis","level":2,"score":0.16429999470710754},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.15940000116825104},{"id":"https://openalex.org/C2988170871","wikidata":"https://www.wikidata.org/wiki/Q11000047","display_name":"Healthcare system","level":3,"score":0.15850000083446503},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.15800000727176666},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.15549999475479126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.00228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00228","pdf_url":"https://arxiv.org/pdf/2505.00228","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":"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"},{"id":"doi:10.48550/arxiv.2505.00228","doi":"https://doi.org/10.48550/arxiv.2505.00228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.00228","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.00228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00228","pdf_url":"https://arxiv.org/pdf/2505.00228","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":"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"},"sustainable_development_goals":[{"score":0.8048999905586243,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6891884690.pdf","grobid_xml":"https://content.openalex.org/works/W6891884690.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4389261383","https://openalex.org/W4396914177","https://openalex.org/W4399251815","https://openalex.org/W4399510493","https://openalex.org/W4404987850"],"related_works":["https://openalex.org/W2912664121","https://openalex.org/W4399251815","https://openalex.org/W2913279579","https://openalex.org/W4394659038","https://openalex.org/W2995225687","https://openalex.org/W7155088129","https://openalex.org/W4404389169","https://openalex.org/W3114128166","https://openalex.org/W3086523768","https://openalex.org/W7220661233"],"abstract_inverted_index":{"We":[0],"present":[1],"ReXGradient-160K,":[2],"representing":[3],"the":[4,16,60,105,124],"largest":[5],"publicly":[6],"available":[7],"chest":[8,24],"X-ray":[9,25],"dataset":[10,21,45,76,131],"to":[11,115],"date":[12],"in":[13,118,126],"terms":[14],"of":[15,18,64],"number":[17],"patients.":[19],"This":[20,43],"contains":[22],"160,000":[23],"studies":[26],"with":[27,92],"paired":[28],"radiological":[29,128],"reports":[30],"from":[31],"109,487":[32],"unique":[33],"patients":[34],"across":[35],"3":[36],"U.S.":[37],"health":[38],"systems":[39,66],"(79":[40],"medical":[41,68,119],"sites).":[42],"comprehensive":[44],"includes":[46],"multiple":[47],"images":[48],"per":[49],"study":[50],"and":[51,62,70,86,122],"detailed":[52],"radiology":[53],"reports,":[54],"making":[55],"it":[56],"particularly":[57],"valuable":[58],"for":[59,67,101],"development":[61],"evaluation":[63,103],"AI":[65,121],"imaging":[69,120],"automated":[71,127],"report":[72],"generation":[73],"models.":[74],"The":[75],"is":[77],"divided":[78],"into":[79],"training":[80],"(140,000":[81],"studies),":[82,85],"validation":[83],"(10,000":[84,89,98],"public":[87],"test":[88,96],"studies)":[90,99],"sets,":[91],"an":[93],"additional":[94],"private":[95],"set":[97],"reserved":[100],"model":[102],"on":[104],"ReXrank":[106],"benchmark.":[107],"By":[108],"providing":[109],"this":[110],"extensive":[111],"dataset,":[112],"we":[113],"aim":[114],"accelerate":[116],"research":[117],"advance":[123],"state-of-the-art":[125],"analysis.":[129],"Our":[130],"will":[132],"be":[133],"open-sourced":[134],"at":[135],"https://huggingface.co/datasets/rajpurkarlab/ReXGradient-160K.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}