Parkinson’s Disease Detection And Classification Of Stages From Drawing Patterns Using Deep Learning

Parkinson’s disease (PD) is a common neurodegenerative disease by which millions of people are affected worldwide. Early detection of PD and accurate classification of the disease stage is a prerequisite for effective therapy and management. In this study, we propose a new approach to detect and classify PD phases using drawing models and the universal You Only Look Once (YOLO) object recognition framework. Data used in the study were collected from 70 patients with mild PD, 70 patients with moderate PD, 70 patients with severe PD, and 70 healthy controls, who were asked to draw certain shapes with pen and paper. The images are pre-processed and fed into the YOLO object recognition model, which has been trained to recognize and classify patterns into different stages of PD. The results of the study show that the proposed approach achieved high accuracy in PD detection and disease stage classification. These results show the potential of using drawing patterns and the YOLO object recognition framework for the early detection and classification of PD. The proposed approach could have a significant impact on the early diagnosis and treatment of PD and possibly improve the quality of life of people with this disease.