MACHINE LEARNING APPROACH FOR PREDICTING PARKINSON’S DISEASE AT EARLY STAGES

Abstract

Parkinson’s Disease (PD) is a progressive neurological disorder that affects movement, speech, and cognitive functions. Early diagnosis of Parkinson’s Disease is challenging due to subtle symptoms appearing during the initial stages. Machine Learning (ML) techniques provide promising solutions for identifying hidden patterns in clinical and biomedical data, enabling early prediction and effective treatment planning. This research proposes a machine learning-based approach for early-stage Parkinson’s Disease prediction using the K-Nearest Neighbor (KNN) algorithm. The proposed model utilizes biomedical voice measurements and clinical attributes to classify patients as healthy individuals or Parkinson’s Disease patients. Data preprocessing techniques, feature selection, and normalization are applied to improve model performance. The KNN classifier predicts disease occurrence by analyzing similarities among patient feature vectors. Experimental evaluation using performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix demonstrates the effectiveness of the proposed approach. The findings indicate that KNN can serve as an efficient and interpretable machine learning technique for supporting early Parkinson’s Disease diagnosis.