High-accuracy automatic classification of Parkinsonian tremor severity using machine learning method.

MOTIVATION: Although clinical aspirations for new technology to accurately measure and diagnose Parkinsonian tremors exist, automatic scoring of tremor severity using machine learning approaches has not yet been employed. OBJECTIVE: This study aims to maximize the scientific validity of automatic tremor-severity classification using machine learning algorithms to score Parkinsonian tremor severity in the same manner as the unified Parkinson's disease rating scale (UPDRS) used to rate scores in real clinical practice. APPROACH: Eighty-five PD patients perform four tasks for severity assessment of their resting, resting with mental stress, postural, and intention tremors. The tremor signals are measured using a wristwatch-type wearable device with an accelerometer and gyroscope. Displacement and angle signals are obtained by integrating the acceleration and angular-velocity signals. Nineteen features are extracted from each of the four tremor signals. The optimal feature configuration is decided using the wrapper feature selection algorithm or principal component analysis, and decision tree, support vector machine, discriminant analysis, and k-nearest neighbour algorithms are considered to develop an automatic scoring system for UPDRS prediction. The results are compared to UPDRS ratings assigned by two neurologists. MAIN RESULTS: The highest accuracies are 92.3%, 86.2%, 92.1%, and 89.2% for resting, resting with mental stress, postural, and intention tremors, respectively. The weighted Cohen's kappa values are 0.745, 0.635 and 0.633 for resting, resting with mental stress, and postural tremors (almost perfect agreement), and 0.570 for intention tremors (moderate). SIGNIFICANCE: These results indicate the feasibility of the proposed system as a clinical decision tool for Parkinsonian tremor-severity automatic scoring.

Automatic Classification of Tremor Severity in Parkinson's Disease Using a Wearable Device.

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.

Distance estimation from acceleration for quantitative evaluation of Parkinson tremor.

The purpose of this paper is to assess Parkinson tremor estimating actual distance amplitude. We propose a practical, useful and simple method for evaluating Parkinson tremor with distance value. We measured resting tremor of 7 Parkinson Disease (PD) patients with triaxial accelerometer. Resting tremor of participants was diagnosed by Unified Parkinson's Disease Rating Scale (UPDRS) by neurologist. First, we segmented acceleration signal during 7 seconds from recorded data. To estimate a displacement of tremor, we performed double integration from the acceleration. Prior to double integration, moving average method was used to reduce an error of integral constant. After estimation of displacement, we calculated tremor distance during 1s from segmented signal using Euclidean distance. We evaluated the distance values compared with UPDRS. Averaged moving distance during 1 second corresponding to UPDRS 1 was 11.52 mm, that of UPDRS 2 was 33.58 mm and tremor distance of UPDRS 3 was 382.22 mm. Estimated moving distance during 1s was proportional to clinical rating scale--UPDRS.

Classification of Parkinson gait and normal gait using Spatial-Temporal Image of Plantar pressure.

The purpose of this paper is the classification of Spatial-Temporal Image of Plantar pressure (STIP) among normal step and the patients step of Parkinson disease. For this, we created a new image data, STIP, that have information of the change of plantar pressure during heel to toe motion (i.e., contain spatial and temporal information for plantar pressure). To get STIP, the walking of 21 patients with Parkinson disease and 17 age-matched healthy subjects were recorded and analyzed using in-shoe dynamic pressure measuring system with comfort walking. For feature extraction of gait, we applied Principal component analysis (PCA) to STIP and calculated weights of STIP on each principal components. Then, we build hard margin Support Vector Machine (SVM) classifier for gait recognition and test of generalization performance using normalized weights on PCs of STIP. SVM result indicated an overall accuracy of 91.73% by the RBF(Radial Basis Function) kernel function. These results demonstrate considerable potential in applying SVMs in gait classification for many applications.