Design and Develop an Interface to Predict Parkinson's Disease usingMachine Learning with Voice Parameters and Handwriting Images

Parkinson's Disease (PD) can be described as a neurological condition of the central nervous system (CNS) that affects movement control. It's a neurodegenerative disorder that's characterized by slowness of movement. About 60% of the neurons get degenerated by the time the disease is diagnosed. Parkinson's disease can be seen typically in people well-over 60 years of age. However, there are not any standardized tests for early detection of PD. This leads to a better fatality rate. Thus, detection of PD during the first stages is significant. We will be employing a supervised learning model to coach the machine using the processed data set. the data present within the data set is given as training data for the training model. this is often going to undergo a classification process within which the result's predicted. An appropriate user-friendly interface is going to be built using the python framework ‘Flask’ within which the user may check the prediction results. The proposed system involves the detection of PD in patients using voice parameters and a handwriting dataset. The voice parameters are analyzed using Random Forest and Regression. The handwriting images are made to undergo feature extraction using Principal Component Analysis (PCA). The values, Pressure, X, Y, Z, Grip Angle, Timestamp, and Test ID are extracted from the pictures. The values which are extracted are then analyzed using the Random Forest algorithm, and results are produced. Thus, PD may be detected during the first stages using our experimental results and this facilitates clinical monitoring of patients, hence reducing mortality rates