Quantitative assessment of essential tremor based on machine learning methods using wearable device

Ma, Chenbin; Li, Deyu; Pan, Longsheng; Li, Xuemei; Yin, Chunyue; Li, Ailing; Zhang, Zhengbo; Zong, Rui

doi:10.1016/j.bspc.2021.103244

Cited by 22 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in signal processing, frequency domain analysis might yield more comprehensible parameter characteristics than time domain research. Nave Bayesian, and k-nearest neighbor (KNN) algorithms were combined to create an autonomous scoring system for tremor severity with kinematic information [13].…”

Section: Machine Learning Based Methodsmentioning

confidence: 99%

“…However, choosing K value is difficult owing to a lack of data pre-processing. In general, an odd integer is used for the K value because selecting an odd number avoids selection ambiguity when the K value is even [13,14]. Its benefits include easy and effective computation, cheap retraining costs, and suitability for automatic class field categorization with high sample sizes [14].…”

Section: Machine Learning Based Methodsmentioning

confidence: 99%

“…In this case, present therapeutic DBS devices cannot deal with an emergency like sudden or irregular potential alterations occurring in patients' brain. At present, there are several methods to achieve adaptive deep brain stimulation [6,12,13], including the method based on signal event, the method based on nonlinear model predictive control and the method using machine learning.…”

Section: Mechanism Of Dbs Devicementioning

confidence: 99%

“…Following the testing, the upper computer program can alter the stimulation parameters of the adaptive deep brain stimulation device's hardware in real time based on the established threshold value. Simultaneously, the experimental algorithm must investigate the control algorithm further through animal tests and evaluate the algorithm's real-time performance and applicability [6,7,13].…”

Section: Event-related Control Mode Microcontroller Unitmentioning

confidence: 99%

See 3 more Smart Citations

Progress of DBS devices in treating essential tremor with self-adaptation function

2022

International Conference on Intelligent and Human-Computer Interaction Technology (IHCIT 2022)

View full text Add to dashboard Cite

Nowadays, Deep Brain Stimulation (DBS) has been used in the surgical treatment of various neurological diseases, such as Essential Tremor (ET). For severe cases, surgical treatment with DBS can suppress the disease better than drug therapy. However, existing DBS devices require the physician to manually set the parameters frequently to achieve the desired therapeutic effect. In this case, adaptive DBS devices become a possible solution for this problem. Adaptive DBS equipment still faces some problems, such as the choice of implementation method, data security and how to ensure that it will not cause serious damage to human body in clinical trials. In this paper, three kinds of adaptive DBS are analyzed, including their mechanism and core algorithms. This paper can provide reference for those who study DBS devices, those who study the application of machine learning algorithms to adaptive devices, and those who want to know about adaptive DBS devices.

show abstract

Section: Machine Learning Based Methodsmentioning

confidence: 99%

Section: Machine Learning Based Methodsmentioning

confidence: 99%

Section: Mechanism Of Dbs Devicementioning

confidence: 99%

Section: Event-related Control Mode Microcontroller Unitmentioning

confidence: 99%

See 2 more Smart Citations

Progress of DBS devices in treating essential tremor with self-adaptation function

2022

International Conference on Intelligent and Human-Computer Interaction Technology (IHCIT 2022)

View full text Add to dashboard Cite

show abstract

“…Recently, wearable robotic systems have shown promising results in providing rehabilitation and assistance in movement problems [ 9 ]. Wearable devices have shown high accuracy in assessing the severity of tremor [ 10 ]. However, tremor management can be more challenging.…”

Section: Introductionmentioning

confidence: 99%

Using Deep Learning for Task and Tremor Type Classification in People with Parkinson’s Disease

Farhani

Zhou

Jenkins

et al. 2022

Sensors

View full text Add to dashboard Cite

Hand tremor is one of the dominating symptoms of Parkinson’s disease (PD), which significantly limits activities of daily living. Along with medications, wearable devices have been proposed to suppress tremor. However, suppressing tremor without interfering with voluntary motion remains challenging and improvements are needed. The main goal of this work was to design algorithms for the automatic identification of the tremor type and voluntary motions, using only surface electromyography (sEMG) data. Towards this goal, a bidirectional long short-term memory (BiLSTM) algorithm was implemented that uses sEMG data to identify the motion and tremor type of people living with PD when performing a task. Moreover, in order to automate the training process, hyperparamter selection was performed using a regularized evolutionary algorithm. The results show that the accuracy of task classification among 15 people living with PD was 84±8%, and the accuracy of tremor classification was 88±5%. Both models performed significantly above chance levels (20% and 33% for task and tremor classification, respectively). Thus, it was concluded that the trained models, based on using purely sEMG signals, could successfully identify the task and tremor types.

show abstract

Signal Processing

McNames

2023

Contemporary Clinical Neuroscience

View full text Add to dashboard Cite

Quantitative assessment of essential tremor based on machine learning methods using wearable device

Cited by 22 publications

References 48 publications

Progress of DBS devices in treating essential tremor with self-adaptation function

Progress of DBS devices in treating essential tremor with self-adaptation function

Using Deep Learning for Task and Tremor Type Classification in People with Parkinson’s Disease

Signal Processing

Contact Info

Product

Resources

About