{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:13:55Z","timestamp":1773965635181,"version":"3.50.1"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"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. Robot. AI"],"abstract":"<jats:p>Parkinson\u2019s Disease is a progressively advancing neurological condition. Its severity is evaluated by utilizing the Hoehn and Yahr staging scale. Such assessments may be inconsistent, are more time-consuming, and expensive for patients. To address these shortcomings, this article introduces a machine learning-based gait classification system to assist doctors in identifying the stages of Parkinson\u2019s disease. This study utilizes two open-access benchmark datasets from PhysioNet and Figshare to assess ground reaction force collected from patients diagnosed with Parkinson\u2019s Disease. This study presents experiments conducted using machine learning algorithms namely Decision Tree, Random Forest, Extreme Gradient Boost, and Light Gradient Boosting Machine classification algorithms to predict severity of Parkinson\u2019s Disease. Among all the four algorithms, Light Gradient Boosting Machine classification algorithm have proven its supremacy. It gave an accuracy of 98.25%, Precision of 98.35%, Recall of 98.25%, and F1 Score of 98% for dataset 1. The performance of the algorithm slightly declines on dataset 2. It reports accuracy of 85%, Precision of 95%, Recall of 85% and F1 Score of 89% for dataset 2. Furthermore, this study used Explainable Artificial Intelligence to display the LightGBM classifier\u2019s classification pathways for Parkinson\u2019s disease severity prediction using Hoehn and Yahr staging on the scale from 0 to 5. This is helps the health experts in decision making. This work provides automated assistance to doctors for the rapid screening of Parkinson\u2019s disease patients based on disease severity. This work leaves a scope for integrating wearable sensors and developing real-time monitoring system for screening of Parkinson\u2019s Disease patients.<\/jats:p>","DOI":"10.3389\/frobt.2025.1623529","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:26:03Z","timestamp":1765344363000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning approach to gait analysis for Parkinson\u2019s disease detection and severity classification"],"prefix":"10.3389","volume":"12","author":[{"given":"Rohit","family":"Mittal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikunj","family":"Agarwal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manan","family":"Dubey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vibhakar","family":"Pathak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Praveen","family":"Shukla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geeta","family":"Rani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugenio","family":"Vocaturo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ester","family":"Zumpano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.future.2018.02.009","article-title":"Gait and tremor investigation using machine learning techniques for the diagnosis of parkinson disease","volume":"83","author":"Abdulhay","year":"2018","journal-title":"Future Gener. Comput. Syst."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/fg59268.2024.10581933","article-title":"Benchmarking skeleton-based motion encoder models for clinical applications: estimating parkinson\u2019s disease severity in walking sequences","author":"Adeli","year":"2024","journal-title":"arXiv [cs.CV]"},{"key":"B3","first-page":"1","article-title":"Plantar pressure response for classification of parkinson\u2019s disease patients with gait abnormalities using machine learning","volume-title":"2023 3rd international conference on digital futures and transformative technologies (ICoDT2)","author":"Afzal","year":"2023"},{"key":"B4","doi-asserted-by":"publisher","first-page":"102117","DOI":"10.1016\/j.rineng.2024.102117","article-title":"Deep learning for enhanced brain tumor detection and classification","volume":"22","author":"Agarwal","year":"2024","journal-title":"Results Eng."},{"key":"B5","doi-asserted-by":"publisher","first-page":"e0175951","DOI":"10.1371\/journal.pone.0175951","article-title":"Vertical ground reaction force marker for parkinson\u2019s disease","volume":"12","author":"Alam","year":"2017","journal-title":"PloS One"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/jsen.2020.3018262","article-title":"Gait spatiotemporal signal analysis for parkinson\u2019s disease detection and severity rating","volume":"21","author":"Alharthi","year":"2020","journal-title":"IEEE Sensors J."},{"key":"B7","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1016\/j.bbe.2018.06.002","article-title":"Parkinson\u2019s disease monitoring from gait analysis via foot-worn sensors","volume":"38","author":"A\u015furo\u011flu","year":"2018","journal-title":"Biocybern. Biomed. Eng."},{"key":"B8","doi-asserted-by":"publisher","first-page":"106494","DOI":"10.1016\/j.asoc.2020.106494","article-title":"Supervised machine learning based gait classification system for early detection and stage classification of parkinson\u2019s disease","volume":"94","author":"Balaji","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"B9","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.medengphy.2021.03.005","article-title":"Data-driven gait analysis for diagnosis and severity rating of parkinson\u2019s disease","volume":"91","author":"Balaji","year":"","journal-title":"Med. Eng. and Phys."},{"key":"B10","doi-asserted-by":"publisher","first-page":"107463","DOI":"10.1016\/j.asoc.2021.107463","article-title":"Automatic and non-invasive parkinson\u2019s disease diagnosis and severity rating using lstm network","volume":"108","author":"Balaji","year":"","journal-title":"Appl. Soft Comput."},{"key":"B11","doi-asserted-by":"publisher","first-page":"129187","DOI":"10.1109\/access.2024.3456438","article-title":"Information set based decision tree for parkinson\u2019s disease severity assessment using multidimensional gait dataset","volume":"12","author":"Balakrishnan","year":"2024","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3389\/fnagi.2018.00434","article-title":"Motoric cognitive risk syndrome: could it be defined through increased gait variability? Findings from the \u201cgait and alzheimer interactions tracking\u201d study","volume":"8","author":"Beauchet","year":"2016","journal-title":"Front. Aging Neurosci."},{"key":"B13","article-title":"A dataset of overground walking full-body kinematics and kinetics in individuals with parkinson\u2019s disease","author":"Boari","year":"2022"},{"key":"B14","doi-asserted-by":"publisher","first-page":"7094","DOI":"10.3390\/s22187094","article-title":"Gait detection from a wrist-worn sensor using machine learning methods: a daily living study in older adults and people with parkinson\u2019s disease","volume":"22","author":"Brand","year":"2022","journal-title":"Sensors"},{"key":"B15","doi-asserted-by":"publisher","first-page":"113075","DOI":"10.1016\/j.eswa.2019.113075","article-title":"Deep 1d-convnet for accurate parkinson disease detection and severity prediction from gait","volume":"143","author":"El Maachi","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"B16","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/978-3-031-59091-7_3","article-title":"Assessment of parkinson\u2019s disease severity using gait data: a deep learning-based multimodal approach","volume-title":"Nordic conference on digital health and wireless solutions","author":"Faiem","year":"2024"},{"key":"B17","doi-asserted-by":"publisher","first-page":"109961","DOI":"10.1016\/j.compbiomed.2025.109961","article-title":"Deep learning models for improving parkinson\u2019s disease management regarding disease stage, motor disability and quality of life","volume":"189","author":"Gon\u00e7alves","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B18","article-title":"Gait in parkinson\u2019s disease","author":"Hausdorff","year":"2008"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e0319826","DOI":"10.1371\/journal.pone.0319826","article-title":"Efficient quantification of parkinson\u2019s disease severity using augmented time-series data","volume":"20","author":"Huo","year":"2025","journal-title":"PloS One"},{"key":"B20","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1515\/revneuro-2013-0006","article-title":"Gait and cognition in Parkinson\u2019s disease: implications for rehabilitation","volume":"24","author":"Iansek","year":"2013","journal-title":"Rev. Neurosci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1136\/jnnp.2007.131045","article-title":"Parkinson\u2019s disease: clinical features and diagnosis","volume":"79","author":"Jankovic","year":"2008","journal-title":"J. Neurology, Neurosurgery and Psychiatry"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1003595","DOI":"10.3389\/fnagi.2022.1003595","article-title":"Mild cognitive impairment is associated with poor gait performance in patients with Parkinson\u2019s disease","volume":"14","author":"Kang","year":"2022","journal-title":"Front. Aging Neurosci."},{"key":"B23","doi-asserted-by":"publisher","first-page":"242","DOI":"10.3390\/s19020242","article-title":"Data-driven based approach to aid parkinson\u2019s disease diagnosis","volume":"19","author":"Khoury","year":"2019","journal-title":"Sensors"},{"key":"B24","doi-asserted-by":"publisher","first-page":"801","DOI":"10.3390\/e24060801","article-title":"P2p lending default prediction based on ai and statistical models","volume":"24","author":"Ko","year":"2022","journal-title":"Entropy"},{"key":"B25","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1109\/ICCMC48092.2020.ICCMC-000142","article-title":"Machine learning and iot based disease predictor and alert generator system","volume-title":"2020 fourth international conference on computing methodologies and communication (ICCMC)","author":"Kundu","year":"2020"},{"key":"B26","doi-asserted-by":"publisher","first-page":"200514","DOI":"10.1016\/j.iswa.2025.200514","article-title":"Explainable ai based lightgbm prediction model to predict default borrower in social lending platform","volume":"26","author":"Li","year":"2025","journal-title":"Intelligent Syst. Appl."},{"key":"B27","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1159\/000110320","article-title":"Projected neurodegenerative disease mortality in the United States, 1990\u20132040","volume":"12","author":"Lilienfeld","year":"1993","journal-title":"Neuroepidemiology"},{"key":"B28","doi-asserted-by":"publisher","first-page":"110076","DOI":"10.1016\/j.compbiomed.2025.110076","article-title":"A lightweight approach to gait abnormality detection for at home health monitoring","volume":"190","author":"Lochhead","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"105439","DOI":"10.1016\/j.bspc.2023.105439","article-title":"Multiscale svd entropy for the analysis of gait dynamics","volume":"87","author":"Marin-Lopez","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3340293","article-title":"A survey on gait recognition via wearable sensors","volume":"52","author":"Marsico","year":"2019","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2127","DOI":"10.1111\/j.1532-5415.2012.04209.x","article-title":"Gait and cognition: a complementary approach to understanding brain function and the risk of falling","volume":"60","author":"Montero-Odasso","year":"2012","journal-title":"J. Am. Geriatrics Soc."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1543282","DOI":"10.3389\/fnagi.2025.1543282","article-title":"Modulated theta band frequency with binaural beat stimulation correlates with improved cognitive scores in alzheimer\u2019s patients","volume":"17","author":"Mujib","year":"2025","journal-title":"Front. Aging Neurosci."},{"key":"B33","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1093\/comjnl\/bxaa111","article-title":"Machine learning model for multi-view visualization of medical images","volume":"65","author":"Pradhan","year":"2022","journal-title":"Comput. J."},{"key":"B34","doi-asserted-by":"publisher","first-page":"35673","DOI":"10.1109\/jsen.2024.3456907","article-title":"Gait wear: an augmented wearable system for gait quantification","volume":"24","author":"Raghuvanshi","year":"2024","journal-title":"IEEE Sensors J."},{"key":"B35","doi-asserted-by":"publisher","first-page":"109603","DOI":"10.1016\/j.mehy.2020.109603","article-title":"Early diagnosis of parkinson\u2019s disease using machine learning algorithms","volume":"138","author":"Senturk","year":"2020","journal-title":"Med. Hypotheses"},{"key":"B36","doi-asserted-by":"publisher","first-page":"587057","DOI":"10.3389\/fphys.2020.587057","article-title":"Parkinson\u2019s disease diagnosis and severity assessment using ground reaction forces and neural networks","volume":"11","author":"Veeraragavan","year":"2020","journal-title":"Front. Physiology"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1056\/NEJMoa020441","article-title":"Abnormality of gait as a predictor of non-alzheimer\u2019s dementia","volume":"357","author":"Verghese","year":"2007","journal-title":"N. Engl. J. Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11571-022-09925-9","article-title":"Gait classification for early detection and severity rating of parkinson\u2019s disease based on hybrid signal processing and machine learning methods","volume":"18","author":"Wang","year":"2024","journal-title":"Cogn. Neurodynamics"},{"key":"B39","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/tnsre.2009.2033062","article-title":"Statistical analysis of gait rhythm in patients with parkinson\u2019s disease","volume":"18","author":"Wu","year":"2009","journal-title":"IEEE Trans. Neural Syst. Rehabilitation Eng."},{"key":"B40","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1109\/tnsre.2025.3561942","article-title":"A graph-based multimodal fusion framework for assessment of freezing of gait in parkinson\u2019s disease","volume":"33","author":"Xu","year":"2025","journal-title":"IEEE Trans. Neural Syst. Rehabilitation Eng."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1016\/j.neuroimage.2006.11.047","article-title":"Role of hyperactive cerebellum and motor cortex in parkinson\u2019s disease","volume":"25","author":"Yu","year":"2007","journal-title":"Mov. Disord."},{"key":"B42","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.neulet.2016.09.043","article-title":"Parkinson\u2019s disease classification using gait analysis via deterministic learning","volume":"633","author":"Zeng","year":"2016","journal-title":"Neurosci. Letters"},{"key":"B43","doi-asserted-by":"publisher","first-page":"116113","DOI":"10.1016\/j.eswa.2021.116113","article-title":"Severity level diagnosis of parkinson\u2019s disease by ensemble k-nearest neighbor under imbalanced data","volume":"189","author":"Zhao","year":"2022","journal-title":"Expert Syst. Appl."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1623529\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:26:04Z","timestamp":1765344364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2025.1623529\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":43,"alternative-id":["10.3389\/frobt.2025.1623529"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2025.1623529","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"article-number":"1623529"}}