An Artificial Intelligence Based Effective Diagnosis of Parkinson Disease Using EEG Signal

This study focuses on the use of human bio-signals for the early diagnosis of PD (Parkinson’s disease). EEG (Electroencephalography) and EMG have been used to examine human brain and muscle signals to learn more about the functional and neurological alterations of Parkinson’s patients. Parkinson disease (PD) is a neurological illness that typically affects people over the age of 50. Dopamine, a neurotransmitter, is depleted in the substantia nigra as a result. As this neurotransmitter is released, the person’s muscles begin to contract. Reduced dopamine production causes a loss of brain and muscle coordination, which manifests as unsteady limb movement in a person with PD. The underlying aetiology of PD can be validated by studying the functional and neural alterations using EEG and correlating the results with EMG. It will explain the origin of the wide range of early-stage motor and non-motor PD symptoms. The EEG and EMG results for detecting early-stage PD were validated using other radiological data, such as a Brain Magnetic Imaging signal. The mathematical model for PD diagnosis was developed utilising an ANN and a graphical user interface. The ANN-designed classifier achieved a near-perfect accuracy rate of 100% while testing its ability to distinguish between an early-stage PD patient and a control subject using a dataset consisting of electroencephalogram and electromyogram readings as input features.