A Parkinson’s Disease Detection Using Support Vector Machine in Machine Learning

A neurological condition that affects a lot of people and significantly decreases their quality of life is Parkinson’s disease. It mostly impacts human motor functions. The terms “parkinsonism” and “parkinsonian syndrome” refer to the main motor symptoms. Parkinson’s disease will gradually cause its symptoms, which include shaking with strength, slowness of movement, and trouble walking. It also can lead to changes in thinking and behaviour, as well as anxiety and depression. There is a voice-based model for Parkinson’s disease recognition. The vocal deflections will confirm the symptoms of Parkinson’s disease. This project focuses on predicting machine learning methods, mainly Support Vector Machine (SVM), to treat Parkinson’s disease. We employ a dataset containing various clinical features related to the Parkinson’s illness, such as audio recordings as well as motor functions. Our approach begins with data preprocessing to handle missing values and normalize features. We then implement the SVM algorithm to classify individuals based on their likelihood of having Parkinson’s disease. In parallel, we apply KNN and Decision Tree algorithms for comparative analysis. Each model’s performance is evaluated using measures like precision and accuracy. This comparison aims to identify the most effective algorithm to predict Parkinson’s illness. Our findings will contribute to the field of medical informatics by providing insights about the suitability of machine learning methods for early diagnosis & potentially improving outcomes for patients.