Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

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

Hyoseon Jeon1, Woongwoo Lee, Hyeyoung Park

  • 1The Interdisciplinary Program for Bioengineering, Seoul National University, Seoul, Republic of Korea.

Physiological Measurement
|September 22, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

<i>GCH1</i> p.Ser80Asn Confers Risk for Parkinson's Disease in East Asian Populations.

medRxiv : the preprint server for health sciences·2026
Same author

Ultrasound-based monitoring of early mesenchymal stem cell therapy mitigates severe radiation-induced soft tissue injury in minipigs.

International journal of radiation biology·2026
Same author

Cycling exercise for autonomic symptoms in early Parkinson's disease.

Autonomic neuroscience : basic & clinical·2026
Same author

Unobtrusive sleep posture estimation using pressure sensor in home sleep.

Computers in biology and medicine·2026
Same author

Amantadine: a first option for symptomatic relief in young-onset Parkinson's disease?

Parkinsonism & related disorders·2026
Same author

First Korean Case of <i>C9orf72</i>-Related Amyotrophic Lateral Sclerosis With Progressive Supranuclear Palsy-Like Features.

Journal of clinical neurology (Seoul, Korea)·2026

Machine learning accurately scores Parkinsonian tremor severity using wearable sensors. This automated system shows high accuracy, offering a potential clinical decision tool for tremor assessment.

Area of Science:

  • Biomedical Engineering
  • Neurology
  • Machine Learning

Background:

  • Clinical diagnosis of Parkinsonian tremors lacks objective, automated severity scoring.
  • Existing methods rely on subjective assessments, limiting accuracy and consistency.

Purpose of the Study:

  • To develop and validate a machine learning system for automatic Parkinsonian tremor severity scoring.
  • To achieve scoring comparable to the Unified Parkinson's Disease Rating Scale (UPDRS) for clinical utility.

Main Methods:

  • Utilized wearable sensors (accelerometer, gyroscope) to collect tremor data from 85 Parkinson's disease patients during four tasks.
  • Extracted 19 features from tremor signals and employed feature selection algorithms (wrapper, PCA).
  • Trained and evaluated machine learning models (decision tree, SVM, discriminant analysis, k-NN) for UPDRS prediction, comparing results to neurologist ratings.

Related Experiment Videos

Main Results:

  • Achieved high classification accuracies: 92.3% (resting), 86.2% (resting with mental stress), 92.1% (postural), and 89.2% (intention) tremors.
  • Demonstrated strong agreement with neurologist ratings, with weighted Cohen's kappa values indicating almost perfect to moderate agreement across tremor types.

Conclusions:

  • The proposed machine learning system demonstrates feasibility for automated Parkinsonian tremor severity scoring.
  • This technology holds potential as a clinical decision support tool for objective tremor assessment in Parkinson's disease.