PREDICTION OF PARKINSON DISEASE USING MACHINE LEARNING

Parkinson Disease is an increasing problem in the modern period. It might be difficult for a clinician to identify this neurological illness in its early stages. However, early illness detection is critical since therapies have a higher chance of improving patients’ quality of life. Since there is no recognized test to identify the symptoms, we propose a statistical technique employing the gait, tremors, and micrographics, which are the most common symptoms of Parkinson disease. This entails examining the link between the two symptoms and classifying the resulting data using multiple classification algorithms in order to identify the classification algorithm that offers the maximum accuracy in diagnosing the patients. Early identification may lead to better medical treatment and improved standards of care.