2017
DOI: 10.3390/s17092067
|View full text |Cite|
|
Sign up to set email alerts
|

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

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) wer… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

7
86
0
5

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
4
2

Relationship

0
10

Authors

Journals

citations
Cited by 128 publications
(98 citation statements)
references
References 37 publications
7
86
0
5
Order By: Relevance
“…It was found that the decision tree outweighs other classifiers with an accuracy of 85.5%. is research has provided enough evidence that the wearable sensors can be used for the diagnosis of PD, and machine learning techniques can be used to automate the system [23]. Samà et al proposed a study using wearable accelerometer that can detect freezing of gait at real-time environment using a set of features which are related to the previous approaches mentioned by the previous researchers.…”
Section: Related Workmentioning
confidence: 99%
“…It was found that the decision tree outweighs other classifiers with an accuracy of 85.5%. is research has provided enough evidence that the wearable sensors can be used for the diagnosis of PD, and machine learning techniques can be used to automate the system [23]. Samà et al proposed a study using wearable accelerometer that can detect freezing of gait at real-time environment using a set of features which are related to the previous approaches mentioned by the previous researchers.…”
Section: Related Workmentioning
confidence: 99%
“…Once trained, these models are used to detect symptom presence and severity for new data. Modeling motor symptoms of PD is primarily conducted using sensors that record body movements, such as accelerometers, gyroscopes, or electromagnetic motion trackers [12][13][14][15][16]. Other types of sensors, including those measuring bioelectrical activity (electromyography, electroencephalography), have also been used [17][18][19][20].…”
Section: Introductionmentioning
confidence: 99%
“…Due to similarity with human decision making, the algorithm is easy to understand for practitioners (Goldman et al, 1982 ) DT algorithms have been effectively applied for the general classification and evaluation of movement activities collected from wearable sensors (Preece et al, 2009 ), which can provide an assessment of treatments for PD patients. An automatic UPDRS scoring system that uses wearable wrist-watch-type sensor measurements was developed (Jeon et al, 2017 ), in which the authors compared a few ML algorithms. The raw sensor data were parsed using standard signal processing techniques (Oppenheim and Schafer, 1989 ) to generate input features (e.g., mean amplitude, mean frequency, signal power, etc.)…”
Section: Decision Trees and Random Forest Algorithmsmentioning
confidence: 99%