Detecting Parkinson's Disease with Prediction: A Novel SVM Approach

In recent years, the prevalence of neurological diseases has been on the rise due to an increasing population and aging. Conditions like Parkinson's disease, stroke, cerebral palsy, and others often lead to dysarthria among patients. Detecting and treating Parkinson's disease promptly is crucial as it can pose challenges to managing the disease's progression and have adverse effects on a patient's mental and physical well-being when symptoms worsen. Previous research has been predominantly using the concept of machine learning for Parkinson's exposure. This study introduces a novel integrated Support Vector Machine archetypal for detecting the disease by gathering data, organizing it followed by training and testing, finally assessing its performance thereby decreasing the causalities. The experimental findings indicate the use of SVM model proposed in the research achieves an accurateness rate of 87 percentages and f1-score of 0.87%.