Improving accuracy in noninvasive telemonitoring of progression of Parkinson'S Disease using two-step predictive model

Parkinson's disease has affected over 6.3 million people across the globe. It is estimated that by 2030, the number would rise to 9 million. Almost twenty percent of the people still remain undiagnosed. Parkinson's is the second most common neurodegenerative disease after Alzheimer's. It not only claims the lives of the patients suffering from it but also adversely impacts the lives of their loved ones. A lot of research is being conducted to find modern medical techniques to tackle the ill effects of the disease. Monitoring the progression of the disease plays a vital role in controlling its various symptoms. Non-conventional ways of monitoring PD (Parkinson's Disease) provide an edge over the existing techniques as it reduces the financial burden and also limits the number of clinical visits required for it. In this research paper, we aim to build a predictive model that accurately predicts the UPDRS (Unified Parkinson's Disease Rating Scale) of patients using the data collected through noninvasive speech tests. The research hopes to propose a more efficient technique to monitor Parkinson's disease leading to beneficial treatment of the patients.