Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification.

Area of Science:

• Neurology
• Computer Science
• Biomedical Engineering

Background:

• Parkinson's disease (PD) is a widespread neurodegenerative disorder affecting the nervous system globally.
• Accurate classification of PD is crucial for timely intervention and management.
• Existing diagnostic methods can be invasive or lack specificity.

Purpose of the Study:

• To develop and evaluate an advanced machine learning model for classifying individuals with and without Parkinson's disease.
• To compare the performance of various machine learning models, optimized with Bayesian Optimization (BO), for PD classification.

Main Methods:

• A dataset with 23 features and 195 instances was utilized, with class labels indicating the presence (1) or absence (0) of PD.
• Six machine learning models were optimized using Bayesian Optimization (BO): Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Ridge Classifier (RC), and Decision Tree (DT).
• Model performance was evaluated using accuracy, F1-score, recall, and precision before and after hyperparameter tuning.

Main Results:

• The Support Vector Machine (SVM) model, optimized with Bayesian Optimization (BO), demonstrated superior performance compared to other models.
• The optimized SVM model achieved the highest accuracy of 92.3% in classifying Parkinson's disease.
• Hyperparameter tuning using BO significantly improved the classification performance across tested models.

Conclusions:

• Bayesian Optimization is an effective technique for enhancing the performance of machine learning models in PD classification.
• The BO-SVM model presents a promising, accurate, and data-driven approach for Parkinson's disease diagnosis.
• Further research with larger datasets could validate the clinical applicability of this approach.