Category
Clinical Biomechanics
Document Type
Paper
Abstract
This study aimed to create a digital biomarker for assessing the severity of Parkinson's disease (PD) using multimodal features from 50 PD patients and 50 healthy controls. They underwent clinical tests, gait analysis using a motion capture system, postural and functional evaluations, and lifestyle questionnaires. These multimodal features underwent dimensionality reduction techniques such as logistic regression and principal component analysis to identify PD severity using the MDS-UPDRS total score. The results developed six models using machine learning algorithms (Linear Regression and Random Forest), with Model 1 performing the best; spatiotemporal variables from gait analysis were crucial in identifying PD severity. We aim to identify important features correlated with MDS-UPDRS and expect to be applied in clinical settings to monitor the severity of PD.
Recommended Citation
Park, Hwayoung; Youm, Changhong; Kim, Bohyun; Choi, Hyejin; Hwang, Juseon; and Kim, Minsoo
(2024)
"MACHINE LEARNING APPROACHES FOR IDENTIFICATION OF PARKINSON’S DISEASE SEVERITY USING MULTIMODAL FEATURES,"
ISBS Proceedings Archive: Vol. 42:
Iss.
1, Article 25.
Available at:
https://commons.nmu.edu/isbs/vol42/iss1/25