Abstract:

Parkinson's disease (PD) is among the top ten most challenging diseases according to the World Health Organization, placing a substantial burden on patients and their families. Currently, treatment can only offer partial relief from clinical symptoms and cannot achieve a complete cure. Therefore, early auxiliary diagnosis holds significant practical significance for PD patients. This research conducted a comprehensive analysis of computer-aided diagnosis techniques for PD classification prediction both domestically and internationally. It also summarized research endeavors utilizing machine learning models to assist in the early detection of PD, aiming to guide early intervention and prevent disease progression. Common prediction methods involved data preprocessing, feature selection, and classification. Traditional machine learning methods might not be as effective when dealing with large datasets or high data complexity, making deep learning or improved machine learning methods more promising for improving prediction accuracy. Furthermore, there has been a growing focus on diagnosing brain structural images of PD patients with cognitive impairment. Research on cognitive dysfunction followed a progressive trajectory, emphasizing the need for early screening and timely intervention. Future research should further explore computer-assisted diagnostic techniques based on machine learning methods and apply them to the early classification prediction of PD, aiming to enhance the accuracy of medical diagnosis and elevate the quality of diagnosis and treatment.

Key words: Parkinson's disease, computer-aided diagnosis, prediction of disease, progress prediction, machine learning