Parkinson’s disease is a progressive disorder of the Central Nervous System affecting movement and inducing tremors and stiffness. The name of this disease was coined by a British doctor, James Parkinson, after he published a paper on it in 1817. This disease affects the brain leading to shaking, stiffness, and difficulty with walking, balance, and coordination. The symptoms of this disease vary from anxiety, sleeping and memory-related issues to depression, loss of sense of smell, along with balance problems. As the disease progresses, people may have difficulty walking and talking. This disease mainly affects people around age 60 or older. Both men and women can have Parkinson’s disease. However, the disease affects 50 percent more men than women. It has 5 stages to it and affects more than 1 million individuals in India per year. In this paper, a machine learning-based diagnosis of Parkinson’s disease is presented. By using the python libraries • scikit-learn • NumPy • pandas • xgboost, We will be able to build a model using an XGB Classifier. By loading the data, getting the features and labels, scaling the features, splitting the dataset, we can build an XGB Classifier, and then calculate the accuracy of our model. A 94.87% accuracy was achieved for Parkinson’s diagnosis after implementing and testing the data.



Software And Hardware