Parkinson’s Disease Prediction System

Abstract

Parkinson’s disease (PD) is a chronic and progressive neurological disorder that predominantly impacts motor functions, speech, and overall movement coordination. The traditional diagnostic approach to Parkinson’s relies heavily on clinical observations and subjective evaluations, which often result in delayed detection or misdiagnosis. In response to this gap, this project proposes a machine learning-based Parkinson’s Disease Prediction System that utilizes biomedical voice measurements as key biomarkers for early diagnosis. Features such as jitter, shimmer, and harmonic-to-noise ratio (HNR) are extracted from patient voice samples and analyzed using various machine learning algorithms including Logistic Regression, Support Vector Classifier (SVC), and Random Forest. The project evaluates the models rigorously and selects the best-performing one based on precision, recall, F1-score, and ROC-AUC metrics. Furthermore, the project leverages cloud computing for secure data storage, scalable deployment, and real-time remote access, ensuring that healthcare providers can easily utilize the prediction system. The system not only provides an efficient and scalable solution but also demonstrates a practical application of AI and cloud technologies in revolutionizing early-stage medical diagnostics.