Prediction of Freezing of Gait in Parkinson's Disease Using a Random Forest Model Based on an Orthogonal Experimental Design: A Pilot Study

Zhonelue Chen; Gen Li; Chao Gao; Yuyan Tan; Jun Liu; Jin Zhao; Yun Ling; Xiaoliu Yu; Kang Ren; Shengdi Chen

doi:10.3389/fnhum.2021.636414

Prediction of Freezing of Gait in Parkinson's Disease Using a Random Forest Model Based on an Orthogonal Experimental Design: A Pilot Study

Front Hum Neurosci. 2021 Mar 22:15:636414. doi: 10.3389/fnhum.2021.636414. eCollection 2021.

Authors

Zhonelue Chen¹, Gen Li², Chao Gao², Yuyan Tan², Jun Liu², Jin Zhao³, Yun Ling¹, Xiaoliu Yu¹, Kang Ren¹, Shengdi Chen²

Affiliations

¹ Gyenno Science Co., Ltd., Shenzhen, China.
² Department of Neurology, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, China.
³ School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.

Abstract

Purpose: The purpose of this study was to introduce an orthogonal experimental design (OED) to improve the efficiency of building and optimizing models for freezing of gait (FOG) prediction.

Methods: A random forest (RF) model was developed to predict FOG by using acceleration signals and angular velocity signals to recognize possible precursor signs of FOG (preFOG). An OED was introduced to optimize the feature extraction parameters.

Results: The main effects and interaction among the feature extraction hyperparameters were analyzed. The false-positive rate, hit rate, and mean prediction time (MPT) were 27%, 68%, and 2.99 s, respectively.

Conclusion: The OED was an effective method for analyzing the main effects and interactions among the feature extraction parameters. It was also beneficial for optimizing the feature extraction parameters of the FOG prediction model.

Keywords: Parkinson’s disease; fog prediction; freezing of gait; optimization; orthogonal experimental design.