Application of Machine learning technique in the computational model of STN and GP network to predict Parkinson Disease at an early stage

Parkinson Disease is one type of Neurological disorders that affect the human brain and nerves throughout the human body and spinal cord. The abnormality in the biochemical or electrical, structural or nervous system can cause the neurological disorders. In 2015, Global Burden of Disease estimated that the one third population of the world is affected by neurological disorders. These disorders are complex in nature and involves different diagnosis methods due to their heterogeneity. This heterogeneity range from dysregulation of immune system to neurodegeneration or pathological protein aggregation to development of functional abnormalities. These disorders involves both genetic and environmental factors.Due to their complex behaviour the diagnosis becomes erroneous as the accurate diagnosis requires correct results from clinical research. Clinical research is handicapped in a way to contribute in the better treatment of the disease as most of the neurological disorders display their symptoms at the secondary stage of the disease. One of such disorder is Parkinson disease that exhibit symptoms after 60 years of age in most of the cases. Hence it becomes utmost important to identify ways to provide better tools and technologies in this specific area to diagnose Parkinson Disease at an early stage to provide timely treatment to the patient.Predicting Parkinson’s disease at an early stage can have significant benefits for patients and healthcare providers. Early detection allows for earlier treatment and management of the disease, which can slow the progression of symptoms and improve the overall quality of life for patients.In this paper we are presenting the role of Machine Learning technique in the prediction of Parkinson disease at an early stage. We are proposing a model that make predictions on the bases of data computed from conductance based computational model of STN and GP network of basal ganglia using machine learning techniques.