Predictive Models for Early Diagnosis of Parkinsons Disease in Men

The recent developments in data analysis and artificial intelligence have been increasingly employed in various fields to solve our day-to-day problems. These techniques have been used in the field of medicine to ensure a high level of accuracy in the diagnosis of diseases. Parkinson's disease (PD) is among the conditions that can be accurately diagnosed using these methods. PD is a neurodegenerative illness common among the elderly in the United States- it is more rampant in older men than in women. There are several symptoms of this disease that can be used for diagnosing this disease in the early stages. However, many people neglect the initial signs as a consequence of age. Moreover, these symptoms are often mistaken with other diseases, thereby resulting in a delayed cure. This research aims to build three models for early detection of Parkinson's disease by comparing symptoms in diagnosed patients against unaffected individuals in order to predict whether a person will get tremors as they become older. Furthermore, it also analyzes the duration of the hold time, the flight time, and variations in the press duration to predict if a person will get Parkinson's disease. Finally, it aims to predict the consequences of PD based on tremors, hand, and directions as the disease progresses over time. This research and data analysis seek to assist the community and the medical field in general to discovering symptoms of a silent epidemic as early as possible to guarantee early treatment.