{"id":"https://openalex.org/W3172351367","doi":"https://doi.org/10.1137/20m1333110","title":"Test Data Reuse for the Evaluation of Continuously Evolving Classification Algorithms Using the Area under the Receiver Operating Characteristic Curve","display_name":"Test Data Reuse for the Evaluation of Continuously Evolving Classification Algorithms Using the Area under the Receiver Operating Characteristic Curve","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3172351367","doi":"https://doi.org/10.1137/20m1333110","mag":"3172351367"},"language":"en","primary_location":{"id":"doi:10.1137/20m1333110","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1333110","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1137/20m1333110","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091213912","display_name":"Alexej Gossmann","orcid":"https://orcid.org/0000-0001-9068-3877"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexej Gossmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074995495","display_name":"Aria Pezeshk","orcid":"https://orcid.org/0000-0002-3570-3051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aria Pezeshk","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339104","display_name":"Yuping Wang","orcid":"https://orcid.org/0000-0001-6868-0004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Ping Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073468417","display_name":"Berkman Sahiner","orcid":"https://orcid.org/0000-0003-2804-2264"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berkman Sahiner","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091213912"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9518,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79874023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":"2","first_page":"692","last_page":"714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9979000091552734,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9979000091552734,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9957000017166138,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9932000041007996,"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/overfitting","display_name":"Overfitting","score":0.9656169414520264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371693849563599},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6402846574783325},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.624616265296936},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6210780143737793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6203200221061707},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5506986975669861},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5478286147117615},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5397601127624512},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.5392365455627441},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5213505029678345},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5159419178962708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47508159279823303},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4078201949596405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.150351881980896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13633528351783752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09271550178527832}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9656169414520264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371693849563599},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6402846574783325},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.624616265296936},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6210780143737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6203200221061707},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5506986975669861},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5478286147117615},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5397601127624512},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5392365455627441},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5213505029678345},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5159419178962708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47508159279823303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4078201949596405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.150351881980896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13633528351783752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09271550178527832},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/20m1333110","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1333110","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1137/20m1333110","is_oa":true,"landing_page_url":"https://doi.org/10.1137/20m1333110","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1262297082","display_name":null,"funder_award_id":"R01GM109068","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4407193152","display_name":null,"funder_award_id":"1539067","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4888031145","display_name":null,"funder_award_id":"R01MH104680","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6394284677","display_name":null,"funder_award_id":"R01AR059781","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6653621909","display_name":null,"funder_award_id":"R01MH107354","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332163","display_name":"U.S. Food and Drug Administration","ror":"https://ror.org/034xvzb47"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W27434444","https://openalex.org/W158824538","https://openalex.org/W1555759181","https://openalex.org/W1798749056","https://openalex.org/W1873763122","https://openalex.org/W2015056255","https://openalex.org/W2015866962","https://openalex.org/W2112076978","https://openalex.org/W2112467442","https://openalex.org/W2122441470","https://openalex.org/W2122825543","https://openalex.org/W2153635508","https://openalex.org/W2154776925","https://openalex.org/W2155653793","https://openalex.org/W2157825442","https://openalex.org/W2167191085","https://openalex.org/W2225981128","https://openalex.org/W2322006099","https://openalex.org/W2602562802","https://openalex.org/W2745075853","https://openalex.org/W2896817483","https://openalex.org/W2911964244","https://openalex.org/W2946813150","https://openalex.org/W2946868854","https://openalex.org/W2949650786","https://openalex.org/W2951851906","https://openalex.org/W2952304018","https://openalex.org/W2962955763","https://openalex.org/W2970131854","https://openalex.org/W2991486856","https://openalex.org/W3023284086","https://openalex.org/W3138073787","https://openalex.org/W4205228770","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W2791137381","https://openalex.org/W1504988876","https://openalex.org/W2973011565","https://openalex.org/W3172351367","https://openalex.org/W2074765259"],"abstract_inverted_index":{"Performance":[0],"evaluation":[1,50],"of":[2,56,127,131,136,150,162,197,226,242],"continuously":[3],"evolving":[4],"machine":[5],"learning":[6],"algorithms":[7],"presents":[8],"new":[9,32,48,77],"challenges,":[10],"especially":[11],"for":[12,75,147,179],"high-risk":[13],"application":[14],"domains":[15],"such":[16,91],"as":[17,172],"medicine.":[18],"In":[19],"principle,":[20],"to":[21,27,62,68,95,106,159,184,228],"obtain":[22],"performance":[23,49,78,175,196],"measures":[24],"that":[25,218],"generalize":[26],"a":[28,31,47,70,76,92,112,128,243],"target":[29,40],"population,":[30],"independent":[33],"test":[34,54,73,96,108,153,230,235,250],"dataset":[35,74,236],"randomly":[36],"drawn":[37],"from":[38],"the":[39,104,107,120,125,132,151,160,164,167,173,198,224,229,234,240,248],"population":[41],"should":[42],"be":[43],"used":[44,72],"each":[45],"time":[46],"is":[51,66,237],"required.":[52],"However,":[53,190],"datasets":[55],"sufficient":[57],"quality":[58],"are":[59,182],"often":[60],"hard":[61],"acquire,":[63],"and":[64,85,115,209],"it":[65],"tempting":[67],"utilize":[69],"previously":[71],"evaluation.":[79],"With":[80,205],"extensive":[81,206],"experiments":[82,210],"on":[83,202,211,247],"simulated":[84],"real":[86,212],"data":[87,97,215],"we":[88,216],"illustrate":[89],"how":[90],"\"naive\"":[93],"approach":[94,158],"reuse":[98,149],"can":[99],"inadvertently":[100],"result":[101],"in":[102,111,186],"overfitting":[103,227],"algorithm":[105,121],"data,":[109,231],"resulting":[110],"generalization":[113],"loss":[114],"overly":[116],"optimistic":[117],"conclusions":[118],"about":[119],"performance.":[122,251],"We":[123,155],"investigate":[124],"use":[126,161],"modified":[129],"version":[130],"reusable":[133],"holdout":[134],"mechanism":[135],"Dwork":[137],"et":[138],"al.":[139],"[Science,":[140],"349":[141],"(2015),":[142],"pp.":[143],"636--638],":[144],"which":[145],"allows":[146],"repeated":[148],"same":[152],"dataset.":[154],"extend":[156],"their":[157],"AUC,":[163],"area":[165],"under":[166],"receiver":[168],"operating":[169],"characteristic":[170],"curve,":[171],"reported":[174,249],"metric.":[176],"Theoretical":[177],"guarantees":[178],"our":[180,191,219],"method":[181],"proven":[183],"hold":[185],"extremely":[187],"data-rich":[188],"scenarios.":[189],"empirical":[192],"results":[193],"indicate":[194],"promising":[195],"proposed":[199],"technique":[200],"even":[201,232],"small":[203],"data.":[204],"simulation":[207],"studies":[208],"medical":[213],"imaging":[214],"show":[217],"procedure":[220],"indeed":[221],"substantially":[222],"reduces":[223],"problem":[225],"when":[233],"small,":[238],"at":[239],"cost":[241],"mild":[244],"additional":[245],"uncertainty":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}