Information Set-Based Decision Tree for Parkinson's Disease Severity Assessment Using Multidimensional Gait Dataset

Abstract

Parkinson's Disease (PD) diagnosis with an explicit severity level assessment is essential for timely medical intervention. Gait analysis has been proven to assist in defining PD progression and Machine Learning algorithms aid in predicting the PD severity by learning intricate details from multidimensional gait datasets. Classifiers that best predict the severity level with better explainability of results are thus a requisite. This paper proposes an Information Set-based Decision Tree (IFS-DT), a classification algorithm that adopts a probabilistic-possibilistic approach for predicting the target variable. Information carried by each feature of the dataset is utilized rather than the possibility of its occurrence which reduces uncertainty in determining the outcome. PD gait dataset built from VGRF signals obtained from the PhysioNet database is utilized for analyzing the proposed work. The IFS-DT classifier performs better than conventional DTs and provides results comparable to that obtained by an ensemble of classifiers. Statistical analyses such as the Wilcoxon signed-rank test are conducted to validate the significance of the findings. Moreover, the importance of training a model with a balanced dataset with optimal sample size for obtaining reliable prediction results is also discussed.