{"id":"https://openalex.org/W7131084352","doi":"https://doi.org/10.3389/fcomp.2026.1700489","title":"Bursting the bubble: data leakage and inflated deep learning accuracy in multivariate time-series frailty classification","display_name":"Bursting the bubble: data leakage and inflated deep learning accuracy in multivariate time-series frailty classification","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W7131084352","doi":"https://doi.org/10.3389/fcomp.2026.1700489"},"language":null,"primary_location":{"id":"doi:10.3389/fcomp.2026.1700489","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2026.1700489","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2026.1700489/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2026.1700489/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027295639","display_name":"Charmayne Hughes","orcid":"https://orcid.org/0000-0002-0575-3939"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Charmayne Mary Lee Hughes","raw_affiliation_strings":["Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126646930","display_name":"Yan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":{"value":1175,"currency":"CHF","value_usd":1418},"apc_paid":{"value":1175,"currency":"CHF","value_usd":1418},"fwci":4.8671,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91082702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"8","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11011","display_name":"Frailty in Older Adults","score":0.8450000286102295,"subfield":{"id":"https://openalex.org/subfields/2717","display_name":"Geriatrics and Gerontology"},"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/T11011","display_name":"Frailty in Older Adults","score":0.8450000286102295,"subfield":{"id":"https://openalex.org/subfields/2717","display_name":"Geriatrics and Gerontology"},"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/T12246","display_name":"Chronic Disease Management Strategies","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T13553","display_name":"Age of Information Optimization","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/robustness","display_name":"Robustness (evolution)","score":0.628000020980835},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5763000249862671},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.515500009059906},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.4242999851703644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.38580000400543213},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.365200012922287},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5838000178337097},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241000056266785},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49790000915527344},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C38180746","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate analysis","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C98559332","wikidata":"https://www.wikidata.org/wiki/Q492762","display_name":"Recall bias","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25859999656677246},{"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:10.3389/fcomp.2026.1700489","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2026.1700489","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2026.1700489/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3389/fcomp.2026.1700489","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2026.1700489","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2026.1700489/pdf","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324094","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7131084352.pdf","grobid_xml":"https://content.openalex.org/works/W7131084352.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2164059021","https://openalex.org/W2595557058","https://openalex.org/W2802940482","https://openalex.org/W2849202363","https://openalex.org/W3110113050","https://openalex.org/W3180073572","https://openalex.org/W3199348281","https://openalex.org/W3210630407","https://openalex.org/W4389625408","https://openalex.org/W4393430925","https://openalex.org/W4396619951","https://openalex.org/W4400969489","https://openalex.org/W4404272163","https://openalex.org/W4405187229","https://openalex.org/W4409689399","https://openalex.org/W4410784954"],"related_works":[],"abstract_inverted_index":{"Background":[0],"Accurate":[1],"prediction":[2,37,168],"of":[3,55,62,91,121,141,182,191],"frailty":[4,36,167,206],"in":[5,44,196,214],"older":[6],"adults":[7],"is":[8,169],"crucial":[9],"for":[10,172,179,205],"preventing":[11],"adverse":[12],"outcomes,":[13],"yet":[14],"distinguishing":[15],"frail,":[16],"pre-frail,":[17],"and":[18,32,53,75,108,112,219],"non-frail":[19],"states":[20],"remains":[21],"challenging.":[22],"A":[23],"recent":[24],"study":[25,187],"applied":[26,80],"InceptionTime":[27],"to":[28,58,82,85,135,158,210],"the":[29,60,92,96,103,138,159,173,177,189],"GSTRIDE":[30],"dataset":[31],"reported":[33,63,98,161],"near-perfect":[34],"multi-class":[35],"(>98%":[38],"accuracy),":[39],"exceeding":[40],"values":[41],"typically":[42],"observed":[43],"comparable":[45],"studies.":[46],"Methods":[47],"We":[48],"conducted":[49],"a":[50,116,202],"methodological":[51,150],"re-evaluation":[52],"replication":[54],"this":[56],"pipeline":[57,94],"assess":[59],"robustness":[61],"performance.":[64,163],"Corrections":[65],"included":[66],"subject-wise":[67],"data":[68,154],"partitioning,":[69],"feature":[70],"scaling":[71],"within":[72],"training":[73],"folds,":[74],"non-overlapping":[76],"sliding":[77],"time":[78],"windows":[79],"separately":[81],"each":[83],"subset":[84],"prevent":[86],"potential":[87],"leakage.":[88],"Results":[89],"Reimplementation":[90],"original":[93],"reproduced":[95],"previously":[97,160],"high":[99,162],"accuracy.":[100],"After":[101],"applying":[102],"corrected":[104],"framework,":[105],"overall":[106],"recall":[107,133],"precision":[109],"decreased":[110],"(50.9":[111],"52.3%,":[113],"respectively),":[114],"providing":[115,201],"more":[117],"conservative,":[118],"data-specific":[119],"estimate":[120],"model":[122,183],"generalizability.":[123,184],"Per-class":[124],"analysis":[125],"indicated":[126],"reductions":[127],"across":[128],"all":[129],"categories,":[130],"with":[131],"Frail-class":[132],"dropping":[134],"21.4%,":[136],"highlighting":[137],"particular":[139],"challenge":[140],"identifying":[142],"high-risk":[143],"individuals.":[144],"Conclusion":[145],"The":[146],"findings":[147],"suggest":[148],"that":[149],"factors,":[151],"such":[152],"as":[153],"leakage,":[155],"likely":[156],"contributed":[157],"Under":[164],"rigorous":[165],"controls,":[166],"challenging,":[170],"particularly":[171],"frail":[174],"class,":[175],"underscoring":[176],"need":[178],"careful":[180],"evaluation":[181],"Significance":[185],"This":[186],"illustrates":[188],"importance":[190],"transparent,":[192],"methodologically":[193],"sound":[194],"pipelines":[195],"clinical":[197],"AI":[198],"research.":[199],"By":[200],"reproducible":[203],"framework":[204],"prediction,":[207],"we":[208],"aim":[209],"support":[211],"future":[212],"studies":[213],"obtaining":[215],"realistic":[216],"performance":[217],"estimates":[218],"developing":[220],"clinically":[221],"meaningful":[222],"models.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-24T00:00:00"}