Abstract
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.
Highlights
Despite the growing body of literature about tremor quantification for objective and quantitative diagnosis, automatic scoring of the Parkinsonian tremor severity using machine-learning algorithms for routine clinical assessments has yet to be investigated
The decision tree returning the highest accuracy showed the highest probability of 99.24%, which means that the tremor severity can be estimated within a difference of one compared to the clinician’s decisions with a probability of 99.24% using our proposed method
The features selected by the pairwise correlation method and principal component analysis was (PCA) were added to each classifier in order; the optimized feature configuration was determined at the highest accuracy of each classifier, as mentioned above
Summary
Despite the growing body of literature about tremor quantification for objective and quantitative diagnosis, automatic scoring of the Parkinsonian tremor severity using machine-learning algorithms for routine clinical assessments has yet to be investigated. Seeking to address this deficit in research, this paper expounds upon a machine-learning approach to objectively measure and accurately evaluate. A Parkinsonian tremor is defined as an involuntary, rhythmic, oscillatory, and back-and-forth action [2] It is certainly one of the most disabling symptoms of PD. On the basis of the UPDRS, neurologists use digits to evaluate the severity of a total of 42 motor abilities by observing patients’ conditions and their performance at various tasks [4].
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call