Early Detection of Parkinson's Disease through Patient Questionnaire and Predictive Modelling

TL;DR

This study develops machine learning models using patient questionnaire data to accurately identify early Parkinson's disease, potentially aiding clinicians in early diagnosis and intervention.

Contribution

It introduces predictive models based on the MDS-UPDRS questionnaire with high accuracy for early PD detection, utilizing various machine learning techniques.

Findings

Models achieved >95% accuracy and ROC AUC in classifying early PD.

Logistic regression showed statistically significant fit.

Machine learning models can assist in clinical diagnosis.

Abstract

Early detection of Parkinson's disease (PD) is important which can enable early initiation of therapeutic interventions and management strategies. However, methods for early detection still remain an unmet clinical need in PD. In this study, we use the Patient Questionnaire (PQ) portion from the widely used Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) to develop prediction models that can classify early PD from healthy normal using machine learning techniques that are becoming popular in biomedicine: logistic regression, random forests, boosted trees and support vector machine (SVM). We carried out both subject-wise and record-wise validation for evaluating the machine learning techniques. We observe that these techniques perform with high accuracy and high area under the ROC curve (both >95%) in classifying early PD and healthy normal. The logistic model demonstrated statistically significant fit to the data indicating its usefulness as a predictive model. It is inferred that these prediction models have the potential to aid clinicians in the diagnostic process by joining the items of a questionnaire through machine learning.