Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index; 12 of the 21 sources its claims cite were checked for support.

Wearable Accelerometer and Gyroscope Sensors for Estimating the Severity of Essential Tremor

Open access
Ali, Sheik Mohammed, Arjunan, Sridhar Poosapadi, Peter, James, Perju-Dumbrava, Laura, Ding, Catherine, Eller, Michael, Raghav, Sanjay, Kempster, Peter, Motin, Mohammod Abdul, Radcliffe, P. J., Kumar, Dinesh Kant · 2024 · IEEE Journal of Translational Engineering in Health and Medicine

Abstract

BACKGROUND: Several validated clinical scales measure the severity of essential tremor (ET). Their assessments are subjective and can depend on familiarity and training with scoring systems. METHOD: We propose a multi-modal sensing using a wearable inertial measurement unit for estimating scores on the Fahn-Tolosa-Marin tremor rating scale (FTM) and determine the classification accuracy within the tremor type. 17 ET participants and 18 healthy controls were recruited for the study. Two movement disorder neurologists who were blinded to prior clinical information viewed video recordings and scored the FTM. Participants drew a guided Archimedes spiral while wearing an inertial measurement unit placed at the mid-point between the lateral epicondyle of the humerus and the anatomical snuff box. Acceleration and gyroscope recordings were analyzed. The ratio of the power spectral density between frequency bands 0.5-4 Hz and 4-12 Hz, and the sum of power spectrum density over the entire spectrum of 2-74 Hz, for both accelerometer and gyroscope data, were computed. FTM was estimated using regression model and classification using SVM was validated using the leave-one-out method. RESULTS: Regression analysis showed a moderate to good correlation when individual features were used, while correlation was high ([Formula: see text] = 0.818) when suitable features of the gyro and accelerometer were combined. The accuracy for two-class classification of the combined features using SVM was 91.42% while for four-class it was 68.57%. CONCLUSION: Potential applications of this novel wearable sensing method using a wearable Inertial Measurement Unit (IMU) include monitoring of ET and clinical trials of new treatments for the disorder.

Overview

CoChat Summary

TL;DR

This study combined wearable accelerometer and gyroscope data from a forearm IMU during spiral drawing to estimate Fahn-Tolosa-Marin (FTM) tremor severity in essential tremor (ET). A regression model estimated FTM with \(r^2 = 0.818\), and SVM classification achieved 91.42% accuracy for ET vs controls but only 68.57% across four classes.

Key findings

  • Multiple regression using accelerometer ratio (AR), gyroscope ratio (GR), and summed gyroscope PSD (GS) estimated clinical FTM score with \(r^2 = 0.818\) and RMSE = 5.25.
  • SVM classification for two classes (ET vs age-matched controls) reached 91.42% accuracy with several feature combinations, including (AS, GS), (AS, GS, GR), (AR, GR, Tt), and (AR, GR, AS, GS).
  • Four-class classification (controls, ET-0, ET+1, ET+2) achieved best mean accuracy of 68.57% using AS, GS, and Tt.
  • Combining accelerometer and gyroscope improved classification over accelerometer alone: two-class accuracy increased from 85% to 91.42%, and four-class accuracy increased from 57.14% to 68.57%.
  • Inter-rater FTM scoring by two blinded neurologists showed very strong correlation (\(r^2 = 0.95\)), and all computerized sensor features had significantly higher mean values in ET than controls.

Methods

  • Seventeen participants with ET (eight male; mean age 67.28 ± 13.39 years; mean tremor duration 22.94 ± 19.65 years) and 18 healthy age-matched controls (eight male; mean age 62.8 ± 11.6 years) were recruited. ET participants were classified as ET-0 (6), ET+1 (5), or ET+2 (6) based on Consensus Axis 1 plus features.
  • Participants drew a guided Archimedes spiral on a digital tablet while wearing a Delsys Trigno IMU at the midpoint between the lateral epicondyle of the humerus and the anatomical snuff box; accelerometer and gyroscope data were recorded at 148.1 samples/sec. Features included PSD ratios AR and GR (4–12 Hz / 0.5–4 Hz), summed PSD AS and GS (2–74 Hz), and total task time Tt.
  • Statistical analysis used Mann-Whitney U tests, linear and multiple least-squares regression, and SVM classifiers with both leave-one-out and 5-fold cross-validation, using linear and radial basis function kernels.

Limitations

  • The paper states that further improvement is necessary for the four-class problem, where accuracy was 68.57%.
  • Evident from the text: the sample was small (17 ET participants and 18 controls), with very small ET-plus subgroups (5 ET+1 and 6 ET+2), limiting robustness of the four-class classification.
  • Evident from the text: assessment relied on a single drawing task and one forearm sensor location, so findings may not generalize to other tasks, sensor placements, or free-living movement.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/jtehm.2023.3329344

Cites

73 of 73 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

FIGURE 1. (a) Position of the wearable sensor placement, best suited for the data collection mounted on the upper limb. (b) Examples of spiral drawing by study participants. Note the 4 o’clock – 10 o’clock tremor axis typical of left-handed spirals produced in essential tremor.
FIGURE 1. (a) Position of the wearable sensor placement, best suited for the data collection mounted on the upper limb. (b) Examples of spiral drawing by study participants. Note the 4 o’clock – 10 o’clock tremor axis typical of left-handed spirals produced in essential tremor.CC BY-NC-ND · PubMed Central
FIGURE 2. Comparison plot of Controls and ET participants for five parameters, 2.(a) AR, 2.(b) AS, 2.(c) GR, 2.(d) GS, 2.(e) Tt.
FIGURE 2. Comparison plot of Controls and ET participants for five parameters, 2.(a) AR, 2.(b) AS, 2.(c) GR, 2.(d) GS, 2.(e) Tt.CC BY-NC-ND · PubMed Central
FIGURE 3. The regression plot of the ET sensors features vs FTM, 3.(a) ET AR vs FTM, 3.(b) ET AS vs FTM, 3.(c) ET GR vs FTM, 3.(d) ET GS vs FTM, 3.(e) ET Tt vs FTM.
FIGURE 3. The regression plot of the ET sensors features vs FTM, 3.(a) ET AR vs FTM, 3.(b) ET AS vs FTM, 3.(c) ET GR vs FTM, 3.(d) ET GS vs FTM, 3.(e) ET Tt vs FTM.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

9 Valid · 0 Not valid · 6 Not checked · 19 Own results and interpretations

12 more claims

Create a free account to see all 34 claims and every source verdict.

See all claims — free account
  • Borderline: one of the tests for a substantial claim is unclear. 1
  • It may state two separate claims as one. 10
  • Probably not a substantial claim. 7

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

2 of 2

Citations

Cites

Show all 71 references

Research works printed but not linked: 2

  1. Donald, 2015, Biomedical Engineering Handbook—Biomedical Engineering Fundamentals
  2. 10.3389/fneur.2012.00146 · DOI · Paper page

Cited by

See all 22

Metadata

Authors
Ali, S. M., Arjunan, S. P., Peter, J., Perju-Dumbrava, L., Ding, C., Eller, M., Raghav, S., Kempster, P., Motin, M. A., Radcliffe, P. J., & Kumar, D. K.
Affiliations
  • RMIT University (AU)
  • SRM Institute of Science and Technology (IN)
  • Monash Medical Centre (AU)
  • Neurosciences Department, Monash Health, Clayton, VIC, Australia
  • Monash Health (AU)
  • Rajshahi University of Engineering and Technology (BD)
Corresponding author
Kumar, Dinesh Kant
Venue
IEEE Journal of Translational Engineering in Health and Medicine
Published
2024
Volume
12
Pages
194-203
ISSN
2168-2372 (ISSN-L)
OpenAlex
W4388125269
Cited by
22
References
71
Citations by year
2026: 7 · 2025: 11 · 2024: 4
FWCI
1.64
Type
journal article
Language
en
Open access
Locations
  • IEEE Journal of Translational Engineering in Health and Medicine (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by-nc-nd)
Funders
  • Scheme for Promotion of Academic and Research Collaboration (S134)
  • Stiftelsen Promobilia (Wearable sensors)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Health Sciences › Medicine › Clinical Neurology › Deep Brain Stimulation and Movement Disorders
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
essential tremor, wearable inertial sensors, accelerometer, gyroscope, Fahn-Tolosa-Marin Tremor Rating Scale, tremor classification, power spectral density features, multimodal sensing, tremor monitoring
MeSH terms
Acceleration, Wearable Electronic Devices, Humans, Tremor, Essential Tremor, Accelerometry

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Wearable Accelerometer and Gyroscope Sensors for Estimating the Severity of Essential Tremor. https://app.cochat.ai/papers/10.1109/jtehm.2023.3329344
The paper
Ali, S. M., Arjunan, S. P., Peter, J., Perju-Dumbrava, L., Ding, C., Eller, M., Raghav, S., Kempster, P., Motin, M. A., Radcliffe, P. J., & Kumar, D. K. (2024). Wearable Accelerometer and Gyroscope Sensors for Estimating the Severity of Essential Tremor. IEEE Journal of Translational Engineering in Health and Medicine. https://doi.org/10.1109/jtehm.2023.3329344

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.