CoChat

Detection and Quantification of Resting Tremor in Parkinson's Disease Using Long-Term Acceleration Data

Open access
Yuan, Han, Liu, Sen, Liu, Jiali, Lin, Hai, Yang, Cuiwei, Cai, Xiaodong, Zeng, Lepeng, Li, Siman · 2021 · Mathematical Problems in Engineering

The DOI matches its Crossref record; 46 of the 51 references it cites were found in a registry or an index; 6 of the 19 sources its claims cite were checked for support.

Abstract

Long-term monitoring of resting tremor is key to assess the status of patients suffering from Parkinson’s disease (PD), which is of vital importance for reasonable medication. The detection and quantification of resting tremor in reported works rely heavily on specified movements and are not appropriate for long-term monitoring in real-life condition. The purpose of this study is to develop a detection model for long-term monitoring of resting tremor and explore an effective indicator for tremor quantification. This study included long-term acceleration data from PD patients and proposed a resting tremor detection model based on machine learning classifiers and Synthetic Minority Oversampling Technique (SMOTE). Four machine learning classifiers, K-Nearest Neighbor (KNN), Random Forest (RF), Adaptive Boosting (AdaBoost), and Support Vector Machine (SVM), were compared. Furthermore, an indicator called tremor timing ratio (TTR) was defined and calculated for tremor quantification. The detection model with RF classifier achieved the highest overall accuracy of 94.81%. The sample entropy of the acceleration signal was proved most influential in the classification by exploring the feature importance. Through the Kruskal-Wallis test and the Mann-Whitney U test, the TTR had a strong correlation with the subscore of resting tremor in Unified Parkinson Disease Rating Scale (UPDRS). Such two-step evaluation process for resting tremor can detect the tremor effectively and is expected to be applied in long-term monitoring of PD patients in daily life to realize a more comprehensive assessment of PD.

Overview

CoChat Summary

TL;DR

This paper develops a two-step evaluation process for Parkinson’s disease resting tremor using long-term wrist acceleration data: a machine-learning detection model and a new quantification indicator, tremor timing ratio (TTR). The Random Forest model achieved 94.81% overall accuracy, and TTR was significantly associated with UPDRS resting tremor subscores.

Key findings

  • The Random Forest classifier gave the best detection performance among KNN, RF, AdaBoost, and SVM, with 94.81% overall accuracy, 95.18% sensitivity, 94.44% specificity, 94.83% F1 score, and a Kappa coefficient of 0.90.
  • Sample entropy (SampEn) was the most influential feature for classification, followed by signal energy, based on out-of-bag permuted predictor importance in the RF classifier.
  • TTR differed significantly across UPDRS resting tremor scores: Kruskal-Wallis p = 0.0034; Mann-Whitney U p = 0.022 for score 1 vs 2, p = 0.0048 for score 1 vs 3, and p = 0.026 for score 2 vs 3. Median TTR values were 0.46 (SD 0.22) for score 1, 0.67 (SD 0.14) for score 2, and 0.85 (SD 0.15) for score 3.
  • Under an interpatient paradigm, the RF model still achieved a weighted average accuracy of 89.70%; without preprocessing, RF accuracy fell to 89.38%, a reduction of 5.43%.

Methods

  • Long-term triaxial acceleration data were collected from 20 PD patients wearing wrist devices at 100 Hz in home settings, with synchronous video and UPDRS ratings as labels; mean tremor prevalence was 16.9%.
  • A 5-second sliding window with 1-second step was used; signals were bandpass filtered at 0.65–12.5 Hz, and five features were extracted: mean amplitude, sample entropy, dominant frequency, energy, and spectrum concentration. SMOTE balanced the dataset, and KNN, RF, AdaBoost, and SVM were compared using fivefold cross-validation.
  • For quantification, 8 patients with valid long-term tremor data contributed 33 cases of 15-minute continuous recordings scored as 1, 2, or 3 (9, 18, and 6 cases, respectively); TTR was calculated as detected tremor samples divided by all samples, then tested with Kruskal-Wallis and Mann-Whitney U tests.

Limitations

  • The paper states that the main limitation is data size: although long-duration data were collected, the number of subjects is limited and the dataset needs to be extended to verify the findings.
  • The paper states that only three resting tremor severity scores were quantified, lacking score 4, because few patients scored 4 while on medication and those diagnosed as 4 were too severe to participate; TTR differences for score 4 were not validated.
  • Evident from the text: the quantification sample is small (8 patients, 33 cases), and interpatient detection performance varied widely across patients, with one patient showing only 53.16% accuracy despite the high average accuracy.

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

Integrity signals

Registry

Crossref · 10.1155/2021/5669932

Cites

46 of 46 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

4 Valid · 2 Not valid · 9 Not checked · 56 Own results and interpretations

30 more claims

Create a free account to see all 71 claims and to verify the 1 reference still open.

See all claims — free account
  • It may state two separate claims as one. 25
  • Probably not a substantial claim. 17

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.

1 of 1

Citations

Cites

Show all 46 references

Cited by

See all 10

Metadata

Authors
Yuan, H., Liu, S., Liu, J., Lin, H., Yang, C., Cai, X., Zeng, L., & Li, S.
Affiliations
  • Fudan University (CN)
  • Shenzhen University (CN)
  • Lifetech Scientific (China) (CN)
Corresponding author
  • Yang, Cuiwei
  • Cai, Xiaodong
Venue
Mathematical Problems in Engineering
Publisher
Wiley
Published
2021-10-11
Volume
2021
Pages
1-12
ISSN
  • 1024-123X (ISSN-L)
  • 1563-5147
OpenAlex
W3205582452
Cited by
10
References
51
Citations by year
2026: 1 · 2025: 3 · 2024: 2 · 2023: 2 · 2022: 1 · 2021: 1
FWCI
0.54
Type
journal article
Language
en
Open access
Locations
  • Mathematical Problems in Engineering (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • National Natural Science Foundation of China (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
  • Shanghai Municipal Special Project of Industry Transformation and Upgrading (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
  • Shanghai Municipal Science and Technology Major Project (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
  • The Project of Shanghai Engineering Research Center (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
  • The Basic Research Projects (Subject Arrangement) of the Shenzhen Science and Technology Program (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
  • The Guangdong Basic and Applied Basic Research Foundation (61071004, GYQJ-2020-1-31, 2017SHZDZX01, 15DZ2251700, JCYJ20180228162928828, 2019A1515111106)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
Keywords
resting tremor, Parkinson's disease, long-term monitoring, accelerometer data, tremor detection, tremor quantification, sample entropy, SMOTE, random forest, Unified Parkinson's Disease Rating Scale, wearable sensors

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: Detection and Quantification of Resting Tremor in Parkinson's Disease Using Long-Term Acceleration Data. https://app.cochat.ai/papers/10.1155/2021/5669932
The paper
Yuan, H., Liu, S., Liu, J., Lin, H., Yang, C., Cai, X., Zeng, L., & Li, S. (2021). Detection and Quantification of Resting Tremor in Parkinson's Disease Using Long-Term Acceleration Data. Mathematical Problems in Engineering. https://doi.org/10.1155/2021/5669932

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.