A Study on the Essential and Parkinson’s Arm Tremor Classification

Abstract

In this article, the challenge of discriminating between essential and Parkinson’s tremor is addressed. Although a variety of methods have been proposed for diagnosing the severity of these highly occurring tremor types, their rapid and effective identification, especially in their early stages, proves particularly difficult and complicated due to their wide range of causes and similarity of symptoms. To this goal, a clinical analysis was performed, where a number of volunteers including essential and Parkinson’s tremor-diagnosed patients underwent a series of pre-defined motion patterns, during which a wearable sensing setup was used to measure their lower arm tremor characteristics from multiple selected points. Extracted features from the acquired accelerometer signals were used to train classification algorithms, including decision trees, discriminant analysis, support vector machine (SVM), K-nearest neighbor (KNN) and ensemble learning algorithms, for providing a comparative study and evaluating the potential of utilizing machine learning to accurately discriminate among different tremor types. Overall, SVM related classifiers proved to be the most successful in terms of classifying between Parkinson’s, essential and no tremor diagnosed with percentages reaching up to 100% for a single accelerometer measurement at the metacarpal area. In general and in motion while holding an object position, Coarse Gaussian SVM classifier reached 82.62% accuracy.

Machine Learning in Tremor Analysis: Critique and Directions

“…Traditionally, sensors have been—with some center‐to‐center differences—placed on the back of the hand 68,73,74 . Studies assessing the ideal sensor placement for tremor analysis showed contrasting results 35,83 …”

A Review of Techniques Used to Suppress Tremor

“…Wherein both emerging and developed countries, the total number is increasing annually and it is expected to be twice within the next 15 years [13]. PD is brought on by the dying of dopamine-producing nerve cells in the brain that is used to facilitate communication between nerve cells [14], therefore a lack of motor control results in a poor feedback system. In addition, other factors that may cause PD such as age, gender, and exposure to specific toxins [14].…”

“…PD is brought on by the dying of dopamine-producing nerve cells in the brain that is used to facilitate communication between nerve cells [14], therefore a lack of motor control results in a poor feedback system. In addition, other factors that may cause PD such as age, gender, and exposure to specific toxins [14]. PD symptoms show trembling in one or both hands at rest, which are distributed frequently and asymmetrically [15,16].…”

“…In addition to the above, facial expressions are diminished in the earlier stages of the injury, and change in handwriting, instability, and a decrease in performing movements [17]. As a result, patients experience troubling conditions such as fatigue, mood swings, sleep disturbances, and swallowing problems [14]. Parkinsonian tremor fluctuates around the mean in the time domain.…”

Can Gait Features Help in Differentiating Parkinson’s Disease Medication States and Severity Levels? A Machine Learning Approach

“…There is evidence that gait patterns differentiate between PD patients and healthy controls [15,16]. There has been a surge of interest in using machine learning and deep learning approaches that utilize sensor signals (i.e., accelerometers, gyroscopes, pressure sensors) and/or videos to monitor and forecast PD progression [14,[17][18][19][20][21][22][23][24]. However, video-based motion analysis systems require expensive equipment and are limited in equipped-indoor environments, while wearable sensors are a more affordable solution, providing a method for longterm monitoring under real-life conditions [25][26][27][28].…”