Emotional Contribution to Parkinson's Disease Diagnosis Using Machine Learning for EEG Dataset Generation

Emotion is the root cause of nearly all harmful illnesses in humans. Emotion affects blood pressure, heart rate, kidney function, and a few disorders of the nervous system. Parkinson's disease, which causes impairment of movement, is one of the brain disorders. This issue is caused by a reduction in dopamine release in the cortex of the brain. Dopamine production deviations have been related to essential hypertension. Dopamine has a crucial role in anxiety modulation in multiple regions of the brain. Patients with Parkinson's disease frequently indicate that acute stress worsens their motor symptoms, especially gait freezing, dyskinesia, and tremors and the emotions play a substantial role in Parkinson's disease. This study focuses on the Classification Learner algorithms and the Electro Encephalogram (EEG) dataset, both of which covered the diagnostic range of PD development. The classifiers were evaluated using key performance indicators such as error rate, accuracy, sensitivity, specificity, and precision. The findings illustrate the convergence of emotional analysis, machine learning (ML), and neuroscience in improving diagnostic capabilities by demonstrating how a combination of EEG datasets with KNN algorithms offers a reliable and accurate approach for early Parkinson's disease identification.