A Machine Learning Approach to Predict Parkinson’s Disease Using Voting Classifier

Biomarkers derived from human voice can offer insight into neurological disorders, such as Parkinson’s disease (PD), because of their underlying cognitive and neuromuscular function. PD is a progressive neurodegenerative disorder that affects about one million people in the United States, with approximately sixty thousand new clinical diagnoses made each year. Historically, PD has been difficult to quantify and doctors have tended to focus on some symptoms while ignoring others, relying primarily on subjective rating scales. Due to the decrease in motor control that is the hallmark of the disease, voice can be used as a means to detect and diagnose PD. With advancements in technology and the prevalence of audio collecting devices in daily lives, reliable models that can translate this audio data into a diagnostic tool for healthcare professionals would potentially provide diagnoses that are cheaper and more accurate. We provide evidence to validate this concept using a voice dataset collected from people with and without PD. Based on previous research, different machine learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) have been explored, but with limited accuracy (around 81%). Our proposed research achieves a better accuracy of 95% using a Voting Classifier combining XGBoost and Support Vector Classifier, thereby improving diagnostic reliability and advancing Parkinson’s detection methods. IndexTerms: Parkinson’s Disease, Machine Learning, Support Vector Classifier (SVC), Voice Biomarkers, Neurodegenerative Disorder, Disease Prediction, Feature Extraction, Biomedical Signal Processing, Data Preprocessing, Ensemble Learning.