{"id":"https://openalex.org/W4386443636","doi":"https://doi.org/10.1093/jamia/ocad178","title":"A framework for understanding label leakage in machine learning for health care","display_name":"A framework for understanding label leakage in machine learning for health care","publication_year":2023,"publication_date":"2023-09-05","ids":{"openalex":"https://openalex.org/W4386443636","doi":"https://doi.org/10.1093/jamia/ocad178","pmid":"https://pubmed.ncbi.nlm.nih.gov/37669138"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocad178","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocad178","pdf_url":"https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocad178/51360453/ocad178.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocad178/51360453/ocad178.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063516544","display_name":"Sharon E. Davis","orcid":"https://orcid.org/0000-0003-0792-8867"},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharon E Davis","raw_affiliation_strings":["Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37232, United States"],"raw_orcid":"https://orcid.org/0000-0003-0792-8867","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011689338","display_name":"Michael E. Matheny","orcid":"https://orcid.org/0000-0003-3217-4147"},"institutions":[{"id":"https://openalex.org/I2799886695","display_name":"Veterans Health Administration","ror":"https://ror.org/05eq41471","country_code":"US","type":"government","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695"]},{"id":"https://openalex.org/I4210101790","display_name":"VA Tennessee Valley Healthcare System","ror":"https://ror.org/01c9rqr26","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210101790","https://openalex.org/I4210112672"]},{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E Matheny","raw_affiliation_strings":["Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37232, United States","Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37232, United States","Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232, United States","Tennessee Valley Healthcare System VA Medical Center, Veterans Health Administration , Nashville, TN 37232, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I901861585"]},{"raw_affiliation_string":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I901861585"]},{"raw_affiliation_string":"Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I901861585"]},{"raw_affiliation_string":"Tennessee Valley Healthcare System VA Medical Center, Veterans Health Administration , Nashville, TN 37232, United States","institution_ids":["https://openalex.org/I2799886695","https://openalex.org/I4210101790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009455981","display_name":"Suresh Balu","orcid":"https://orcid.org/0000-0003-4929-9130"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210124077","display_name":"Duke Institute for Health Innovation","ror":"https://ror.org/031n1rn61","country_code":"US","type":"other","lineage":["https://openalex.org/I4210124077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Balu","raw_affiliation_strings":["Duke Institute for Health Innovation, Duke University School of Medicine , Durham, NC 27701, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Institute for Health Innovation, Duke University School of Medicine , Durham, NC 27701, United States","institution_ids":["https://openalex.org/I170897317","https://openalex.org/I4210124077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089062751","display_name":"Mark Sendak","orcid":"https://orcid.org/0000-0001-5828-4497"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210124077","display_name":"Duke Institute for Health Innovation","ror":"https://ror.org/031n1rn61","country_code":"US","type":"other","lineage":["https://openalex.org/I4210124077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark P Sendak","raw_affiliation_strings":["Duke Institute for Health Innovation, Duke University School of Medicine , Durham, NC 27701, United States"],"raw_orcid":"https://orcid.org/0000-0001-5828-4497","affiliations":[{"raw_affiliation_string":"Duke Institute for Health Innovation, Duke University School of Medicine , Durham, NC 27701, United States","institution_ids":["https://openalex.org/I170897317","https://openalex.org/I4210124077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5089062751"],"corresponding_institution_ids":["https://openalex.org/I170897317","https://openalex.org/I4210124077"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":3.4485,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93945733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"1","first_page":"274","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.3330000042915344,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.3330000042915344,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.3176000118255615,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.08579999953508377,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6868481636047363},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.6039119958877563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5209042429924011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5041595697402954},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.46566155552864075},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.41282302141189575},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1610260009765625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868481636047363},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.6039119958877563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5209042429924011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041595697402954},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.46566155552864075},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.41282302141189575},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1610260009765625},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003695","descriptor_name":"Delivery of Health Care","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006268","descriptor_name":"Health Facilities","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocad178","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocad178","pdf_url":"https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocad178/51360453/ocad178.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:37669138","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37669138","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 the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10746313","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10746313","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10746313/pdf/ocad178.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/jamia/ocad178","is_oa":true,"landing_page_url":"https://doi.org/10.1093/jamia/ocad178","pdf_url":"https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocad178/51360453/ocad178.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G6399140587","display_name":null,"funder_award_id":"P50 HD103537","funder_id":"https://openalex.org/F4320337611","funder_display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development"}],"funders":[{"id":"https://openalex.org/F4320337611","display_name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","ror":"https://ror.org/04byxyr05"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386443636.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1983342498","https://openalex.org/W2168490582","https://openalex.org/W2736287575","https://openalex.org/W2811374795","https://openalex.org/W2901997892","https://openalex.org/W2914586904","https://openalex.org/W2992144222","https://openalex.org/W2998524378","https://openalex.org/W3005410610","https://openalex.org/W3011721937","https://openalex.org/W3012875567","https://openalex.org/W3015460073","https://openalex.org/W3029078373","https://openalex.org/W3128540648","https://openalex.org/W4200109803","https://openalex.org/W6758825812","https://openalex.org/W6771659168"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"INTRODUCTION:":[0],"The":[1],"pitfalls":[2],"of":[3,7,32,60,74],"label":[4,19,78],"leakage,":[5],"contamination":[6],"model":[8,48,101],"input":[9],"features":[10,49],"with":[11,100],"outcome":[12],"information,":[13],"are":[14],"well":[15],"established.":[16],"Unfortunately,":[17],"avoiding":[18],"leakage":[20,51,79,97],"in":[21,80],"clinical":[22,69,89,121],"prediction":[23,122],"models":[24,70],"requires":[25],"more":[26],"nuance":[27],"than":[28],"the":[29,55,96,120],"common":[30,109],"advice":[31],"applying":[33],"\"no":[34],"time":[35],"machine":[36,135],"rule.\"":[37],"FRAMEWORK:":[38],"We":[39],"provide":[40,85],"a":[41],"framework":[42],"for":[43],"contemplating":[44],"whether":[45],"and":[46,58,76,90,104,111,132],"when":[47,115],"pose":[50],"concerns":[52],"by":[53],"considering":[54],"cadence,":[56],"perspective,":[57],"applicability":[59],"predictions.":[61],"To":[62],"ground":[63],"these":[64],"concepts,":[65],"we":[66,84,118],"use":[67],"real-world":[68],"to":[71,87,113,128],"highlight":[72],"examples":[73],"appropriate":[75],"inappropriate":[77],"practice.":[81],"RECOMMENDATIONS:":[82],"Finally,":[83],"recommendations":[86],"support":[88],"technical":[91],"stakeholders":[92],"as":[93],"they":[94],"evaluate":[95],"tradeoffs":[98],"associated":[99],"design,":[102],"development,":[103],"implementation":[105],"decisions.":[106],"By":[107],"providing":[108],"language":[110],"dimensions":[112],"consider":[114],"designing":[116],"models,":[117],"hope":[119],"community":[123],"will":[124],"be":[125],"better":[126],"prepared":[127],"develop":[129],"statistically":[130],"valid":[131],"clinically":[133],"useful":[134],"learning":[136],"models.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
