Enhancing Parkinson’s Disease Diagnosis the Using Logistic Regression and KNN

A neurogenerative disease, Parkinson's disease impairs motor control. The disease seems to develop as brain neurons generating dopamine start to fail, hence impairing regulation of smooth muscle. Early detection of motor signs of Parkinson's disease enables a patient to get suitable treatment at the right time. This paper contrasts logistic regression and k-nearest neighbor (KNN) in terms of their relative appropriateness as machine learning techniques for diagnosing Parkinson disease. Among the many clinical and demographic information about the study dataset participants, voice measures are among them. Composed of 31 individuals, 23 of whom have Parkinson's disease. Moreover, the speech feature data utilized to identify the illness include MDVP: Fo (Hz), MDVP: Fhi (Hz), himmer: DDA, and many more. Though K-Nearest neighbor algorithm beat Logistic Regression by reaching 86% accuracy, preliminary findings indicate that both Logistic Regression and K- Nearest Neighbor can differentiate between people with Parkinson disease and healthy individuals. The results imply that KNN and Logistic Regression are possible predictive techniques for Parkinson disease. The research indicates that early detection of Parkinson's disease may benefit greatly from machine learning techniques.