Detecting Parkinson's Disease using High-Dimensional Feature-Based Support Vector Regression

Parkinson's disease (PD) is a progressive neurological disorder that significantly impacts patients' quality of life. Accurate and early detection of PD is crucial for effective management and treatment. A study proposes a High-Dimensional Feature-Based Support Vector Regression (HDFSVR) method for enhancing the accuracy of PD detection. This method integrates advanced normalization and feature selection techniques to improve diagnostic accuracy. Sensitivity analysis shows a prediction accuracy of 83%, while precision analysis indicates an accuracy of 87%. Recall analysis further highlights the method's efficacy with a prediction accuracy of 92.78%. The HDFSVR method achieves an accuracy of 94.78%, outperforming contemporary approaches such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Adaptive Genetic Weighted Optimizer (AGWO). It represents a substantial advancement in PD diagnostics, addressing the limitations of traditional support vector machines in handling high-dimensional data. The method can be seamlessly adopted in clinical settings, enhancing early and accurate detection of Parkinson's disease.