Parkinson Disease Prediction Using Machine Learning Algorithm

Parkinson disease, the second most common neurological disorder that causes significant disability, reduces the quality of life and has no cure. Approximately, 90% affected people with Parkinson have speech disorders. The medical dataset contains heterogeneous data in the form of text, numbers, and images that can be mined. Big Data has the potential to give valuable information after processing that can be discovered through deep analysis and efficient processing of data by decision-makers. Data mining is the process of selecting, extracting, and modeling the unknown hidden patterns from large datasets. Machine learning algorithm (MLA) can be used for early detection of disease to increase the chances of elderly people's lifespan and improved lifestyle with Parkinson. In this paper, we use various MLAs that can help in improving the performance of datasets and play a vital role in making the early prediction of disease at right time. After comparison of these algorithms, we choose the most effective one in terms of accuracy. From our experimental results, it is analyzed that the accuracy obtained from the combined effect of KNN algorithm with ANN is better as compared to other algorithms.