{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:04:14Z","timestamp":1791921854258,"version":"4.3.4"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Parkinson\u2019s disease (PD) is a rapidly growing neurodegenerative disorder associated with gait impairment, functional decline, and increased fall risk. Conventional clinical assessments rely heavily on brief observational scales and are limited by subjectivity and environmental bias. There is a pressing need for objective, quantitative, and scalable digital assessment tools to support precision management of PD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and validate a smartphone-video-based gait assessment system aligned with a clinically meaningful pathway encompassing PD screening, functional evaluation, and fall risk classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this cross-sectional observational study, patients with mild-to-moderate PD and age-matched healthy controls were recruited following Institutional Review Board approval. Gait videos were recorded using smartphone cameras and processed through a silhouette extraction pipeline. Spatiotemporal gait features were subsequently extracted using a MoviNet-based deep learning framework. A multi-task framework was developed to perform PD screening, activities of daily living functional grading based on the Schwab and England Activities of Daily Living (S&amp;amp;E ADL) scale, and fall risk classification. Model performance and generalizability were evaluated using subject-independent data partitioning and independent cross-site validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 40 participants were recruited. For PD screening, the model achieved an accuracy of 95.7%, a sensitivity of 96.6%, a specificity of 92.2%, and an AUC of 0.994 on the independent test set. For S&amp;amp;E ADL functional grading, the model achieved an overall accuracy of 88.5% across three functional categories (80, 90, and 100%). For fall risk classification, the model achieved an accuracy of 91.1%, a sensitivity of 68.4%, a specificity of 98.3%, and an AUC of 0.909. Overall, the framework demonstrated robust performance across PD screening, functional stratification, and fall risk classification tasks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed a smartphone-video-based gait assessment framework using computer vision and deep learning. The proposed framework demonstrated strong performance in PD identification, severity estimation, and fall risk classification. Future work will expand validation across diverse populations and disease stages, while advancing toward multimodal integration and long-term home monitoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1944666","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:58:06Z","timestamp":1790690286000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A deep learning-based silhouette gait detection framework for fall risk classification in Parkinson\u2019s disease"],"prefix":"10.3389","volume":"17","author":[{"given":"Slo-Li","family":"Chu","sequence":"first","affiliation":[{"name":"Department of Information and Computer Engineering, Chung Yuan Christian University","place":["Taoyuan, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Ju","family":"Kuo","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Engineering, Chung Yuan Christian University","place":["Taoyuan, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Yen","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Engineering, Chung Yuan Christian University","place":["Taoyuan, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiaching","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Engineering, Chung Yuan Christian University","place":["Taoyuan, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shey-Lin","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Show Chwan and Chang Bing Show Chwan Memorial Hospitals","place":["Changhua, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping-Yi","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Nursing, Hungkuang University","place":["Taichung, Taiwan"]},{"name":"Department of Medical Research, China Medical University Hospital","place":["Taichung, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/S1474-4422(24)00038-3","article-title":"Global, regional, and national burden of disorders affecting the nervous system, 1990-2021: a systematic analysis for the global burden of disease study 2021","volume":"23","year":"1990","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/S1474-4422(17)30299-5","article-title":"Global, regional, and national burden of neurological disorders during 1990-2015: a systematic analysis for the global burden of disease study 2015","volume":"16","year":"1990","journal-title":"Lancet Neurol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson's disease","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov Disord"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1136\/jnnp.2007.131045","article-title":"Parkinson's disease: clinical features and diagnosis","volume":"79","author":"Jankovic","year":"2008","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1002\/ana.24011","article-title":"Therapeutic prospects for Parkinson disease","volume":"74","author":"Olanow","year":"2013","journal-title":"Ann Neurol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1002\/mds.24973","article-title":"Motor signs in the prodromal phase of Parkinson's disease","volume":"27","author":"Maetzler","year":"2012","journal-title":"Mov Disord"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s00508-016-1096-4","article-title":"Gait disorders in adults and the elderly: a clinical guide","volume":"129","author":"Pirker","year":"2017","journal-title":"Wien Klin Wochenschr"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"661676","DOI":"10.3389\/fcomp.2021.661676","article-title":"Wearable devices for gait analysis in intelligent healthcare","volume":"3","author":"Liu","year":"2021","journal-title":"Front Comput Sci"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/TPAMI.2022.3151865","article-title":"Deep gait recognition: a survey","volume":"45","author":"Sepas-Moghaddam","year":"2023","journal-title":"Ieee T Pattern Anal"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.gaitpost.2024.04.029","article-title":"Vision-based motion capture for the gait analysis of neurodegenerative diseases: a review","volume":"112","author":"Vun","year":"2024","journal-title":"Gait Posture"},{"key":"ref11","volume-title":"Clinical gait Analysis: Theory and Practice","author":"Kirtley","year":"2006"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/s41746-025-02150-8","article-title":"Deep learning-enabled accurate assessment of gait impairments in Parkinson's disease using smartphone videos","volume":"9","author":"Han","year":"2025","journal-title":"NPJ Digit Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1093\/jcde\/qwab054","article-title":"Recent use of deep learning techniques in clinical applications based on gait: a survey","volume":"8","author":"Matsushita","year":"2021","journal-title":"J Comput Des Eng"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"5957","DOI":"10.3390\/s24185957","article-title":"The role of deep learning and gait analysis in Parkinson's disease: a systematic review","volume":"24","author":"Franco","year":"2024","journal-title":"Sensors"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e0000467","DOI":"10.1371\/journal.pdig.0000467","article-title":"Clinical gait analysis using video-based pose estimation: multiple perspectives, clinical populations, and measuring change","volume":"3","author":"Stenum","year":"2024","journal-title":"PLOS Digit Health"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1186\/s12883-023-03385-2","article-title":"Gait video-based prediction of unified Parkinson's disease rating scale score: a retrospective study","volume":"23","author":"Eguchi","year":"2023","journal-title":"BMC Neurol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2288","DOI":"10.1109\/JBHI.2022.3144917","article-title":"Estimating Parkinsonism severity in natural gait videos of older adults with dementia","volume":"26","author":"Sabo","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2912","DOI":"10.1109\/TNSRE.2023.3291359","article-title":"Video-based quantification of gait impairments in Parkinson's disease using skeleton-Silhouette fusion convolution network","volume":"31","author":"Zeng","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/tnsre.2024.3352004","article-title":"Cross-spatiotemporal graph convolution networks for skeleton-based parkinsonian gait MDS-UPDRS score estimation","volume":"32","author":"Tian","year":"2024","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1109\/TNSRE.2025.3613967","article-title":"Skeleton-based continuous scale parkinsonian gait score estimation using Omni-dimensional self-attention convolution networks","volume":"33","author":"Tian","year":"2025","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/B978-0-12-374105-9.00070-8","article-title":"Schwab and England activities of daily living scale","volume-title":"Encyclopedia of Movement Disorders","author":"Siderowf","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.08430","article-title":"Yolox: exceeding yolo series in 2021","author":"Ge","year":"2021","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.06175","article-title":"Paddleseg: a high-efficient development toolkit for image segmentation","author":"Liu","year":"2021","journal-title":"arXiv"},{"key":"ref24","author":"Kondratyuk","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41597-024-04327-4","article-title":"Health & Gait: a dataset for gait-based analysis","volume":"12","author":"Zafra-Palma","year":"2025","journal-title":"Sci Data"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.3390\/diagnostics11101824","article-title":"Remote gait type classification system using markerless 2D video","volume":"11","author":"Albuquerque","year":"2021","journal-title":"Diagnostics"},{"key":"ref27","author":"Loureiro","year":"2020"},{"key":"ref28","volume-title":"Gait Dataset for Knee Osteoarthritis and Parkinson\u2019s Disease Analysis with Severity Levels","author":"Kour","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"20552076241294110","DOI":"10.1177\/20552076241294110","article-title":"Telerehabilitation solutions in patient pathways: an overview of systematic reviews","volume":"10","author":"Nicolas","year":"2024","journal-title":"Digit Health"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e0001004","DOI":"10.1371\/journal.pdig.0001004","article-title":"Classifying simulated gait impairments using privacy-preserving explainable artificial intelligence and mobile phone videos","volume":"4","author":"Reddy","year":"2025","journal-title":"PLoS Digit Health"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.2522\/ptj.20050387","article-title":"Gait characteristics of elderly people with a history of falls: a dynamic approach","volume":"86","author":"Barak","year":"2006","journal-title":"Phys Ther"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1111\/j.1532-5415.2005.00580.x","article-title":"Epidemiology of gait disorders in community-residing older adults","volume":"54","author":"Verghese","year":"2006","journal-title":"J Am Geriatr Soc"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"e69627","DOI":"10.1371\/journal.pone.0069627","article-title":"Prevalence and burden of gait disorders in elderly men and women aged 60-97 years: a population-based study","volume":"8","author":"Mahlknecht","year":"2013","journal-title":"PLoS One"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1519\/00139143-200932020-00002","article-title":"White paper: \"walking speed: the sixth vital sign\"","volume":"32","author":"Fritz","year":"2009","journal-title":"J Geriatr Phys Ther"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"901331","DOI":"10.3389\/fmedt.2022.901331","article-title":"Present and future of gait assessment in clinical practice: towards the application of novel trends and technologies","volume":"4","author":"Hulleck","year":"2022","journal-title":"Front Med Technol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1002\/mds.25672","article-title":"Classification of gait disturbances: distinguishing between continuous and episodic changes","volume":"28","author":"Giladi","year":"2013","journal-title":"Movement Disord"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s40035-020-00191-5","article-title":"Freezing of gait in Parkinson's disease: pathophysiology, risk factors and treatments","volume":"9","author":"Gao","year":"2020","journal-title":"Transl Neurodegener"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1212\/WNL.0b013e3181e7b688","article-title":"Predictors of future falls in Parkinson disease","volume":"75","author":"Kerr","year":"2010","journal-title":"Neurology"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/tbiom.2024.3486345","article-title":"A comprehensive survey on deep gait recognition: algorithms, datasets, and challenges","volume":"7","author":"Shen","year":"2025","journal-title":"IEEE Trans Biometrics Behav Identity Sci"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1007\/978-0-387-73003-5_36","volume-title":"Encyclopedia of Biometrics","author":"Boyd","year":"2009"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime multi-person 2D pose estimation using part affinity fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.05418","article-title":"Generalization in medical AI: a perspective on developing scalable models","author":"Zvuloni","year":"2023","journal-title":"arXiv"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1186\/s12877-021-02113-0","article-title":"Perceived walking difficulties in Parkinson's disease - predictors and changes over time","volume":"21","author":"Lindh-Rengifo","year":"2021","journal-title":"BMC Geriatr"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1944666\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:58:08Z","timestamp":1790690288000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1944666\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":43,"alternative-id":["10.3389\/fneur.2026.1944666"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1944666","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"1944666"}}