Abstract: A neurological condition called Parkinson's disease (PD) affects 60% of persons over 50. Parkinson's disease (PD) patients struggle with speech impairment and movement issues, which makes it difficult for them to travel for appointments for treatment and monitoring. Early discovery of PD enables treatment, allowing patients to live normal lives. The necessity to identify PD early, remotely, and correctly is highlighted by the world's aging population. The application of machine learning techniques in telemedicine to identify PD in its early stages is highlighted in this research.

During the training of 3 ML models, research was done using the MDVP audio data of 195 PD and healthy individuals. When Random Forest classifier, AdaBoost and Decision Tree results are compared, ADaBoost is found to be the best Machine Learning (ML) technique for PD identification. The AdaBoost classifier model has a good f-beta Score. We hope to encourage the use of machine learning (ML) in telemedicine through the findings of this paper, giving Parkinson's disease patients a new lease of life.

Keywords: Parkinson’s Disease, MDVP Data, AdaBoost, Random Forest Classifier.

| DOI: 10.17148/IARJSET.2023.10761