Early Prediction of Parkinson's Disease with Machine Learning: A KNN Approach

Parkinson's disease is a degenerative condition of the nervous system that significantly affects the quality of life of many people. Most of these disorders impact human motor functions. This research study employs machine learning (ML) to predict Parkinson's disease (PD), utilizing the Parkinson’s dataset. The dataset encompasses biomedical voice measurements from 31 individuals, distinguishing between healthy and Parkinson’s Disease subjects. Their predictive performance was evaluated using a variety of machine learning methods, such as Decision Tree, K-Nearest Neighbors (KNN), Random Forest, Naïve Bayes, Support Vector Machines (SVM), and Logistic Regression. Among these, the KNN model exhibited remarkable accuracy, exceeding 98%. This robust performance underscores its potential for accurate Parkinson’s disease prediction. We improved accessibility to diagnosis by utilizing the top-performing KNN model to create an intuitive web application with the Streamlit open-source framework. This research is significant because it could help with early intervention, which would improve patient care. The implementation involves predicting Parkinson’s disease with an accuracy score of 98% using the KNN model and deploying it in a web app. This innovative approach ensures wider accessibility and encourages patient self-management. In summary, this machine learning-driven research promises to improve patient outcomes by encouraging early intervention and offering an efficient Parkinson's disease prediction tool.