Automatic Classification of Tremor Severity in Parkinson’s Disease Using a Wearable Device
| Autor: | Hyo Seon Jeon, Kwang Suk Park, Beom S. Jeon, Hong Ji Lee, Sang Kyong Kim, Hyeyoung Park, Woong-Woo Lee, Hanbyul Kim |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
automatic scoring
Engineering Speech recognition 0206 medical engineering Decision tree wearable device Angular velocity 02 engineering and technology lcsh:Chemical technology Accelerometer Biochemistry Analytical Chemistry 03 medical and health sciences Acceleration 0302 clinical medicine lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation UPDRS business.industry Linear discriminant analysis tremor 020601 biomedical engineering Atomic and Molecular Physics and Optics nervous system diseases Random forest Support vector machine machine learning algorithm Parkinson’s disease Feature (computer vision) business 030217 neurology & neurosurgery |
| Zdroj: | Sensors, Vol 17, Iss 9, p 2067 (2017) Sensors; Volume 17; Issue 9; Pages: 2067 |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s17092067 |
| Popis: | Although there is clinical demand for new technology that can accurately measure Parkinsonian tremors, automatic scoring of Parkinsonian tremors using machine-learning approaches has not yet been employed. This study aims to fill this gap by proposing machine-learning algorithms as a way to predict the Unified Parkinson’s Disease Rating Scale (UPDRS), which are similar to how neurologists rate scores in actual clinical practice. In this study, the tremor signals of 85 patients with Parkinson’s disease (PD) were measured using a wrist-watch-type wearable device consisting of an accelerometer and a gyroscope. The displacement and angle signals were calculated from the measured acceleration and angular velocity, and the acceleration, angular velocity, displacement, and angle signals were used for analysis. Nineteen features were extracted from each signal, and the pairwise correlation strategy was used to reduce the number of feature dimensions. With the selected features, a decision tree (DT), support vector machine (SVM), discriminant analysis (DA), random forest (RF), and k-nearest-neighbor (kNN) algorithm were explored for automatic scoring of the Parkinsonian tremor severity. The performance of the employed classifiers was analyzed using accuracy, recall, and precision, and compared to other findings in similar studies. Finally, the limitations and plans for further study are discussed. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|