Parkinson's Disease Prediction Using Machine Learning Algorithm

Parkinson's disease (PD) is a progressive central nervous system disorder characterized by tremors, vocal cord disorders, bradykinesia, and slurred, slow speech. After Alzheimer's disease, it is the second most prevalent neurological disorder. Approximately 6,3 million people worldwide are affected by this disease. It is caused by the death of dopamine-producing neurons and primarily affects those over the age of 60. Parkinson's disease does not have a cure, but early detection may be able to slow the disease's progression. Using speech analysis and gait analysis data, researchers have spent the past few years working on the detection and monitoring of Parkinson's disease. Machine learning and artificial intelligence (AI) techniques are gaining popularity because they can automate the process of accurate pattern recognition. Approximately 90% of patients with PD suffer from motor impairments. Then, datasets are obtained, and using Histogram of Oriented Gradients, specific features are extracted (HOG). The datasets are examined to determine if the individual has Parkinson's disease. Using an artificial neural network's Random Forest Classifier and a patient dataset containing spiral and wave-like drawings, we intend to predict this disease. The result of the computing method is then computed, analyzed, and improved output is obtained.