A Game-Based Approach to Monitor Parkinson's Disease: The Bradykinesia Symptom Classification

摘要

Parkinson's disease (PD) is a degenerative neurological disorder. It causes motor symptoms such as resting tremor, bradykinesia and gait disorders. The disease's progressive nature requires continuous monitoring of the motor symptoms to assist the neurologist in managing medication. With this purpose, Health Monitoring Systems (HMS) are used as a decentralized healthcare approach. On the other hand, most patients reject the current HMS solutions because they are invasive and stigmatizing. In this work, we present a non-invasive HMS for PD motor symptoms based on games. Because of the nature of games, the approach is able to collect data from patients without reminding them that they are under a disease's treatment. We validated our approach with 30 research subjects divided between PD group and Control group. We used Support Vector Machine (SVM) to identify the occurrence of PD's bradykinesia motor symptoms and reached a classification precision of 92.31%. Furthermore, 90,00% of the patients approved our HMS considering it as non-invasive and easily integrated into their routine.