An Efficient Rotation Forest-Based Ensemble Approach for Predicting Severity of Parkinson's Disease

Area of Science:

• Neurology
• Computer Science
• Biomedical Engineering

Background:

• Parkinson's disease (PD) is a common neurodegenerative disorder affecting motor function, particularly in the elderly.
• Accurate and early assessment of PD severity is crucial for effective patient management and treatment.

Purpose of the Study:

• To develop and evaluate a novel machine learning approach for predicting Parkinson's disease severity.
• To classify PD patients into 'severe' and 'non-severe' categories using voice telemonitoring data.

Main Methods:

• Feature selection was performed on the UCI Parkinson's telemonitoring voice dataset.
• A hybrid model combining Rotation Forest and Random Forest was applied to classify disease severity.
• The proposed model was compared against several existing machine learning algorithms.

Main Results:

• The proposed machine learning approach demonstrated high accuracy in classifying Parkinson's disease severity.
• The model successfully identified early-stage PD severity.
• The hybrid Rotation Forest and Random Forest model outperformed other methods in classification accuracy and F1-measure.

Conclusions:

• The developed machine learning model offers a promising tool for early and accurate prediction of Parkinson's disease severity.
• Voice analysis using this novel approach can significantly aid in the early detection and management of PD.
• The hybrid model's superior performance highlights its potential for clinical application in PD assessment.