{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:27:52Z","timestamp":1783441672770,"version":"3.54.6"},"reference-count":19,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate prediction of frailty in older adults is crucial for preventing adverse outcomes, yet distinguishing frail, pre-frail, and non-frail states remains challenging. A recent study applied InceptionTime to the GSTRIDE dataset and reported near-perfect multi-class frailty prediction (&amp;gt;98% accuracy), exceeding values typically observed in comparable studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a methodological re-evaluation and replication of this pipeline to assess the robustness of reported performance. Corrections included subject-wise data partitioning, feature scaling within training folds, and non-overlapping sliding time windows applied separately to each subset to prevent potential leakage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Reimplementation of the original pipeline reproduced the previously reported high accuracy. After applying the corrected framework, overall recall and precision decreased (50.9 and 52.3%, respectively), providing a more conservative, data-specific estimate of model generalizability. Per-class analysis indicated reductions across all categories, with Frail-class recall dropping to 21.4%, highlighting the particular challenge of identifying high-risk individuals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The findings suggest that methodological factors, such as data leakage, likely contributed to the previously reported high performance. Under rigorous controls, frailty prediction is challenging, particularly for the frail class, underscoring the need for careful evaluation of model generalizability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Significance<\/jats:title>\n                    <jats:p>This study illustrates the importance of transparent, methodologically sound pipelines in clinical AI research. By providing a reproducible framework for frailty prediction, we aim to support future studies in obtaining realistic performance estimates and developing clinically meaningful models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcomp.2026.1700489","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T06:31:20Z","timestamp":1771828280000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Bursting the bubble: data leakage and inflated deep learning accuracy in multivariate time-series frailty classification"],"prefix":"10.3389","volume":"8","author":[{"given":"Charmayne Mary Lee","family":"Hughes","sequence":"first","affiliation":[{"name":"Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin","place":["Berlin, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Age-Appropriate Human-Machine Systems, Institute of Psychology and Ergonomics, Technische Universit\u00e4t Berlin","place":["Berlin, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s11760-024-03719-8","article-title":"Inertial measurement unit signal-based machine learning methods for frailty assessment in geriatric health","volume":"19","author":"Amjad","year":"2025","journal-title":"Signal Image Video Process"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"8451","DOI":"10.3390\/app10238451","article-title":"Wearable sensors technology as a tool for discriminating frailty levels during instrumented gait analysis","volume":"10","author":"Ap\u0161ega","year":"2020","journal-title":"Appl. Sci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"13891","DOI":"10.1038\/s41598-025-65046-0","article-title":"Frailty identification using a sensor-based upper-extremity function test: a deep learning approach","volume":"15","author":"Asghari","year":"2025","journal-title":"Sci. Rep."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1373515","DOI":"10.3389\/fnins.2024.1373515","article-title":"Data leakage in deep learning studies of translational EEG","volume":"18","author":"Brookshire","year":"2024","journal-title":"Front. Neurosci."},{"key":"ref14","first-page":"54","article-title":"A permutation approach to assess confounding in machine learning applications for digital health. In proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","author":"Chaibub Neto","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1186\/s12877-023-04477-x","article-title":"Application of machine learning in measurement of ageing and geriatric diseases: a systematic review","volume":"23","author":"Das","year":"2023","journal-title":"BMC Geriatr."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"M146","DOI":"10.1093\/gerona\/56.3.m146","article-title":"Frailty in older adults: evidence for a phenotype","volume":"56","author":"Fried","year":"2001","journal-title":"J. Gerontol. A Biol. Sci. Med. Sci."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1038\/s41597-023-02531-w","article-title":"A database with frailty, functional and inertial gait metrics for the research of fall causes in older adults","volume":"10","author":"Garc\u00eda-de-Villa","year":"2023","journal-title":"Sci. Data"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6883292","article-title":"Gstride: A database of frailty and functional assessments with inertial gait data from elderly fallers and non-fallers populations [Dataset]","author":"Garc\u00eda-Villamil Neira","year":"2022","journal-title":"Zenodo"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"3351","DOI":"10.3390\/s25113351","article-title":"Retrospective frailty assessment in older adults using inertial measurement unit-based deep learning on gait spectrograms","volume":"25","author":"Gri\u0161kevi\u010dius","year":"2025","journal-title":"Sensors"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1501168","DOI":"10.3389\/fragi.2025.1501168","article-title":"A comparative analysis of binary and multi-class classification machine learning algorithms to detect current frailty status using the English longitudinal study of ageing (ELSA)","volume":"6","author":"Hughes","year":"2025","journal-title":"Front. Aging"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e57298","DOI":"10.2196\/57298","article-title":"Development and validation of a machine learning method using vocal biomarkers for identifying frailty in community-dwelling older adults: cross-sectional study","volume":"13","author":"Kim","year":"2025","journal-title":"JMIR Med. Inform."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.cmpb.2018.04.026","article-title":"Mobile and wearable technologies in healthcare for the ageing population","volume":"161","author":"Malwade","year":"2018","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1712.03120","article-title":"Learning disease vs participant signatures: a permutation test approach to detect identity confounding in machine learning diagnostic applications","author":"Neto","year":"2017","journal-title":"arXiv."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3459666","article-title":"Applying machine learning for sensor data analysis in interactive systems: common pitfalls of pragmatic use and ways to avoid them","volume":"54","author":"Pl\u00f6etz","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/gigascience\/gix019","article-title":"The need to approximate the use-case in clinical machine learning","volume":"6","author":"Saeb","year":"2017","journal-title":"GigaScience"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.3390\/cells10112924","article-title":"Role of deep learning in predicting aging-related diseases: a scoping review","volume":"10","author":"Wassan","year":"2021","journal-title":"Cells"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/s41576-021-00418-9","article-title":"Navigating the pitfalls of applying machine learning in genomics","volume":"23","author":"Whalen","year":"2022","journal-title":"Nat. Rev. Genet."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"109466","DOI":"10.1016\/j.compeleceng.2024.109466","article-title":"Development of gravitationally aligned pendant IMU frailty identifier","volume":"118","author":"Yang","year":"2024","journal-title":"Comput. Electr. Eng."}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2026.1700489\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T06:31:22Z","timestamp":1771828282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2026.1700489\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":19,"alternative-id":["10.3389\/fcomp.2026.1700489"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2026.1700489","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,23]]},"article-number":"1700489"}}