IMU-Based Gait Analysis for Detection of Parkinson Disease Using Machine and Deep Learning Models
Digital Government: Research and Practice · 06.11.2026
DOI: 10.1145/3859276 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Government: Research and Practice, online erschienen am 06.11.2026. Verfasst von Ricardo Molina-Coronel und 10 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben.
Abstract (Originalsprache)
Parkinson's disease (PD) is the second most common neurodegenerative disorder worldwide, affecting especially elderly. Early diagnosis of PD remains challenging due to the subtle onset of symptoms. Traditional motor assessment tools, such as the MDS-UPDRS, often lack objectivity and sensitivity. This study evaluates Machine Learning (ML) and Deep Learning (DL) techniques combined with wearable inertial measurement unit IMU sensors to detect gait abnormalities associated with Parkinson. Several shallow ML models and DL architectures were trained on preprocessed IMU gait data partitioned at the subject level. Data augmentation techniques were applied exclusively to the training dataset to address class imbalance without information leakage. The LSTM model trained on augmented temporal signals achieved the highest performance, reaching an accuracy of 93.79%, a recall of 94.84%, a balanced accuracy of 93.78%, and a Matthews correlation coefficient (MCC) of 0.876. The MLP and Random Forest with DWT features achieved an accuracy of 92.48%, a recall of 93.55%, and an MCC of 0.850. Model robustness was further confirmed on an independent cross-site cohort achieving, LSTM: 93.10% accuracy, 94.16% recall; MLP: 92.13% accuracy, 93.07% recall. Furthermore, Explainable AI revealed that model decisions were predominantly driven by wrist rotational dynamics, physiologically corroborating asymmetric arm-swing reduction.
Zitieren
APA
Molina-Coronel, R., Moscoso-Esquivel, A., Loayza, F., Tapia-Rosero, A., Pelaez, E., Navarro-Cadavid, A., Orozco, J. L., Salazar, N., Muñoz, B., Madriñan, P., & Añazco, E. V. (2026). IMU-Based Gait Analysis for Detection of Parkinson Disease Using Machine and Deep Learning Models. Digital Government: Research and Practice. https://doi.org/10.1145/3859276
Vancouver
Molina-Coronel R, Moscoso-Esquivel A, Loayza F, Tapia-Rosero A, Pelaez E, Navarro-Cadavid A, et al. IMU-Based Gait Analysis for Detection of Parkinson Disease Using Machine and Deep Learning Models. Digital Government: Research and Practice. 2026. doi:10.1145/3859276
BibTeX
@article{MolinaCoronel2026,
author = {Molina-Coronel, Ricardo and Moscoso-Esquivel, Andres and Loayza, Francis and Tapia-Rosero, Ana and Pelaez, Enrique and Navarro-Cadavid, Andrés and Orozco, Jorge Luis and Salazar, Nicolas and Muñoz, Beatriz and Madriñan, Patricia and Añazco, Edwin Valarezo},
title = {IMU-Based Gait Analysis for Detection of Parkinson Disease Using Machine and Deep Learning Models},
journal = {Digital Government: Research and Practice},
year = {2026},
doi = {10.1145/3859276}
}
EUVIMED