Combined accelerometer and EMG analysis to differentiate essential tremor from Parkinson's disease
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
In this study, we intended to differentiate patients with essential tremor (ET) from tremor dominant Parkinson disease (PD). Accelerometer and electromyographic signals of hand movement from standardized upper extremity movement tests (resting, holding, carrying weight) were extracted from 13 PD and 11 ET patients. The signals were filtered to remove noise and non-tremor high frequency components. A set of statistical features was then extracted from the discrete wavelet transformation of the signals. Principal component analysis was utilized to reduce dimensionality of the feature space. Classification was performed using support vector machines. We evaluated the proposed method using leave one out cross validation and we report overall accuracy of the classification. With this method, it was possible to discriminate 12/13 PD patients from 8/11 patients with ET with an overall accuracy of 83%. In order to individualize this finding for clinical application we generated a posterior probability for the test result of each patient and compared the misclassified patients, or low probability scores to available clinical follow up information for individual cases. This non-standardized post hoc analysis revealed that not only the technical accuracy but also the clinical accuracy limited the overall classification rate. We show that, in addition to the successful isolation of diagnostic features, longitudinal and larger sized validation is needed in order to prove clinical applicability.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Wold, S., Esbensen, K., & Geladi, P. (1987) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(87)80084-9 · Cited by 11,606
Hughes, A. J., Daniel, S. E., Kilford, L., & Lees, A. J. (1992) · Journal of Neurology, Neurosurgery & Psychiatry · doi:10.1136/jnnp.55.3.181 · Cited by 10,378
Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J., & Scholkopf, B. (1998) · IEEE Intelligent Systems and their Applications · doi:10.1109/5254.708428 · Cited by 7,243
Consensus Statement of the Movement Disorder Society on Tremor
Deuschl, G., Bain, P., & Brin, M. (2008) · Movement Disorders · doi:10.1002/mds.870131303 · Cited by 1,981
How common are the "common" neurologic disorders?
Hirtz, D., Thurman, D. J., Gwinn-Hardy, K., Mohamed, M., Chaudhuri, A. R., & Zalutsky, R. (2007) · Neurology · doi:10.1212/01.wnl.0000252807.38124.a3 · Cited by 1,365 · cited 1×
“5 increasing up to 2% with age [2].”
BackgroundHOW COMMON ARE THE “COMMON” NEUROLOGIC DISORDERS?
Kaplin, A. I., & Williams, M. (2007) · Neurology · doi:10.1212/01.wnl.0000278071.91524.4d · Cited by 1,131
Essential tremor: emerging views of a common disorder
Benito-León, J., & Louis, E. D. (2006) · Nature Clinical Practice Neurology · doi:10.1038/ncpneuro0347 · Cited by 295
Quantitative analysis of tremor time series
Timmer, J., Lauk, M., & Deuschl, G. (1996) · Electroencephalography and Clinical Neurophysiology/Electromyography and Motor Control · doi:10.1016/0924-980x(96)94658-5 · Cited by 117
SPECT imaging evaluation in movement disorders: far beyond visual assessment
Badiavas, K., Molyvda, E., Iakovou, I. P., Tsolaki, M., Psarrakos, K., & Karatzas, N. D. (2010) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-010-1664-1 · Cited by 92
Tremor analysis in two normal cohorts
Raethjen, J., Lauk, M., Köster, B., Fietzek, U. M., Friege, L., Timmer, J., Lücking, C. H., & Deuschl, G. (2004) · Clinical Neurophysiology · doi:10.1016/j.clinph.2004.04.006 · Cited by 66
Research works printed but not linked: 1
- burrus, 1997, Introduction to Wavelets and Wavelet Transforms, A Primer
Cited by
How Wearable Sensors Can Support Parkinson's Disease Diagnosis and Treatment: A Systematic Review
Rovini, E., Maremmani, C., & Cavallo, F. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00555 · Cited by 426
Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature
Mei, J., Desrosiers, C., & Frasnelli, J. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.633752 · Cited by 401
Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification
Elshewey, A. M., Shams, M. Y., El-Rashidy, N. M., Elhady, A. M., Shohieb, S. M., & Tarek, Z. (2023) · Sensors · doi:10.3390/s23042085 · Cited by 125
“The authors in [33] presented an algorithm based on SVM for 13 PD patients and they achieved 83.00% accuracy.”
MethodInfluentialTowards remote monitoring of Parkinson’s disease tremor using wearable motion capture systems
Delrobaei, M., Memar, S., Pieterman, M., Stratton, T. W., McIsaac, K., & Jog, M. (2017) · Journal of the Neurological Sciences · doi:10.1016/j.jns.2017.11.004 · Cited by 120
“Consequently, similar to other such studies [18,31,32,34,35], this study is also lacking the comparison of the proposed high-resolution system with a widely accepted kinematic tool.”
Wearable sensor-based gait analysis to discriminate early Parkinson’s disease from essential tremor
Lin, S., Gao, C., Li, H., Huang, P., Ling, Y., Chen, Z., Ren, K., & Chen, S. (2023) · Journal of Neurology · doi:10.1007/s00415-023-11577-6 · Cited by 88
“Long-term EMG recordings with/without combined accelerometers were used to differentiate the two disorders [9, 11].”
MethodLu, R., Xu, Y., Li, X., Fan, Y., Zeng, W., Tan, Y., Ren, K., Chen, W., & Cao, X. (2020) · Parkinson s Disease · doi:10.1155/2020/4693019 · Cited by 94
“Recent studies show that the misdiagnosis rate of tremor dominant PD or essential tremor is nearly 20–30% [63, 64].”
BackgroundWearable Devices for Assessment of Tremor
Vescio, B., Quattrone, A., Nisticò, R., Crasà, M., & Quattrone, A. (2021) · Frontiers in Neurology · doi:10.3389/fneur.2021.680011 · Cited by 81
“Other authors (39, 40) introduced AI-based analysis techniques for discriminating ET from PD using combined EMG and accelerometer signals acquired in a laboratory setting.”
BackgroundDifferential diagnosis of Parkinson and essential tremor with convolutional LSTM networks
Oktay, A. B., & Kocer, A. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.101683 · Cited by 65
Assessment of movement disorders using wearable sensors during upper limb tasks: A scoping review
Vanmechelen, I., Haberfehlner, H., Vleeschhauwer, J. D., Wonterghem, E. V., Feys, H., Desloovere, K., Aerts, J., & Monbaliu, E. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.1068413 · Cited by 61
Machine Learning in Tremor Analysis: Critique and Directions
De, A., Bhatia, K. P., Volkmann, J., Peach, R. L., & Schreglmann, S. R. (2023) · Movement Disorders · doi:10.1002/mds.29376 · Cited by 47
“Linear discriminant analysis (LDA) 92,93 and support vector machines (SVM) 52,58 are frequently used algorithms for tremor classi fi cation.”
BackgroundMethodInfluentialCNN-Based PD Hand Tremor Detection Using Inertial Sensors
Tong, L., He, J., & Peng, L. (2021) · IEEE Sensors Letters · doi:10.1109/lsens.2021.3074958 · Cited by 42
Kleinholdermann, U., Wullstein, M., & Pedrosa, D. J. (2021) · Clinical Neurophysiology · doi:10.1016/j.clinph.2021.01.031 · Cited by 45
Vescio, B., Nisticò, R., Augimeri, A., Quattrone, A., Crasà, M., & Quattrone, A. (2021) · Diagnostics · doi:10.3390/diagnostics11020200 · Cited by 39
“Due to these overlapping symptoms, misdiagnosis between ET and PD tremor may occur in 20–30% of cases [3].”
BackgroundA deep explainable artificial intelligent framework for neurological disorders discrimination
Shahtalebi, S., Atashzar, S. F., Patel, R. V., Jog, M., & Mohammadi, A. (2021) · Scientific Reports · doi:10.1038/s41598-021-88919-9 · Cited by 39
Spasojevic, S. S., Ilic, T. V., Stojković, I., Potkonjak, V., Rodic, A. D., & Santos-Victor, J. (2017) · Frontiers in Neurology · doi:10.3389/fneur.2017.00388 · Cited by 31
“(14) use the EMG data, along with the readings from the accelerometer, to successfully differentiate essential tremor from Parkinson’s disease.”
MethodLuft, F., Sharifi, S., Mugge, W., Schouten, A., Bour, L., van Rootselaar, A.-F., Veltink, P., & Heida, T. (2019) · Sensors · doi:10.3390/s19194301 · Cited by 27
“[13] used combined accelerometer and EMG measurements to differentiate between an essential tremor (ET) and a Parkinson’s disease (PD) tremor, achieving an overall accuracy of differentiation of 83%.”
MethodWearable Accelerometer and Gyroscope Sensors for Estimating the Severity of Essential Tremor
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., et al. (2024) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2023.3329344 · Cited by 22
Distinguishing essential tremor from Parkinson’s disease: clinical and experimental tools
Angelini, L., Paparella, G., & Bologna, M. (2024) · Expert Review of Neurotherapeutics · doi:10.1080/14737175.2024.2372339 · Cited by 24
“There are potential combinations analyses of EMG and accelerome-try signal [83], and also with machine learning support [84,85], but the evidence is still limited to determining their differential diagnostic efficacy.”
Upper limb intention tremor assessment: opportunities and challenges in wearable technology
Paredes-Acuña, N., Utpadel-Fischler, D., Ding, K., Thakor, N. V., & Cheng, G. (2024) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-023-01302-9 · Cited by 27
Tang, L., Hu, Q., Wang, X., Liu, L., Zheng, H., Yu, W., Luo, N., Liu, J., & Song, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-79111-w · Cited by 24
“…primarily on calculating and fusing predefined coefficients and parameters of multimodal signals, such as acceleration and angular velocity 17 , or acceleration and sEMG 18,19 , to analyze the synergetic neuromuscular control or upper limb muscle coactivation of tremors in patients with PT and ET.”
A Multi-Layer Gaussian Process for Motor Symptom Estimation in People With Parkinson's Disease
Lang, M., Hirche, S., Pfister, F., Fröhner, J., Abedinpour, K., Pichler, D., Fietzek, U. M., Um, T. T., Kulić, D., & Endo, S. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2900002 · Cited by 21
Li, J., Zhu, H., Li, J., Wang, H., Wang, B., Luo, W. F., & Pan, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3306203 · Cited by 21
“Muthuraman [14], WILE [5], Ghassemi [15], Barrantes [16], di Biase [10], Bove [17], Loaiza [18], Duque [8],”
BackgroundIntelligent devices for assessing essential tremor: a comprehensive review
Peng, Y., Ma, C., Li, M., Liu, Y., Yu, J., Pan, L., & Zhang, Z. (2024) · Journal of Neurology · doi:10.1007/s00415-024-12354-9 · Cited by 17
“These parameters carry significant diagnostic value for distinguishing between different conditions [50, 55].”
Barzallo, B., Punín, C., Llumiguano, C., & Huerta, M. (2018) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-981-10-9023-3_156 · Cited by 10
Quantification of Parkinson’s Disease Motor Symptoms: A Wireless Motion Sensing Approach
Kim, M. J., Naydanova, E., Hwang, B. Y., Mills, K. A., Anderson, W. S., & Salimpour, Y. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175616 · Cited by 10
“The dimensionality reduction from PCA allows the extraction of principal components and projects them into the direction of maximum variance [12].”
MethodVisualisation of Parkinsonian, essential and physiological tremor planes in 3Dspace
Jombík, P., Spodniak, P., Bahýľ, V., & Necpál, J. (2020) · Physiological Research · doi:10.33549/physiolres.934066 · Cited by 6
Ciocîrlan, M., Gheorghiu, A., Bilous, D., et al. (2021) · Endoscopy · doi:10.1055/a-1497-6532 · Cited by 4
“The measurement of hand movement using accelerometers has been previously described, for instance in Parkinson’s disease diagnosis or sports medicine (boxing) [8, 9].”
MethodA Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson's DiseasePreprint
Lang, M., Pfister, F., Fröhner, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.10663 · Cited by 3
Phenotypical Differentiation of Tremor Using Time Series Feature Extraction and Machine Learning
Häring, V., Selzam, V., Martin‐Rodríguez, J. F., Schwingenschuh, P., Tamás, G., Köhler, L., Raethjen, J., Paschen, S., Goltz, F., Mulroy, E., et al. (2025) · Movement Disorders · doi:10.1002/mds.70032 · Cited by 6
“38-42 Moreover, issues such as limited sample sizes, monocentric study designs, and the constraints of hypothesis-driven approaches have hindered the identi-fi cation of reliable, generalizable disease-speci fi c tremor characteristics.”
An Optimized Method for the Limb Tremor Measurement
Zeng, W., Su, H., Zhong, H., Cui, H., Sun, L., & Xia, L. (2018) · International Conference on Medical and Health Informatics (ICMHI) · doi:10.1145/3239438.3239478 · Cited by 2
Phenotypical differentiation of tremor using time series feature extraction and machine learningPreprint
Häring, V., Selzam, V., Martin‐Rodríguez, J. F., et al. (2024) · medRxiv · doi:10.1101/2024.03.14.24303988 · Cited by 2
Toader, A. E., Useinovic, N., Shafie, B., Henn, M. C., Joyce, M., Smith, H. D., Neilson, L. E., Safarpour, D., Raslan, A. M. T., & Cleary, D. C. (2026) · Journal of neurosurgery · doi:10.3171/2026.1.jns252047 · Cited by 1
Evaluación del Movimiento a través de Acelerometría en Pacientes con Enfermedad de Parkinson
Bravo, I. G. (2017) · doi:10.24254/cnib.17.18 · Cited by 1
Vanmechelen, I., Haberfehlner, H., Vleeschhauwer, J. D., Wonterghem, E. V., Feys, H., Desloovere, K., Aerts, J., & Monbaliu, E. (2022) · medRxiv · doi:10.1101/2022.10.13.22281023 · Cited by 1
“672 673 # of sensor(s) Location of sensor(s) Type Goal population 1 Index finger tip Accelerometer PD [51, 91, 94, 97] 1 Index finger tip Gyroscope PD [59, 61] 1 Index finger Motion sensor PD [69] 1 Index finger Inertial measurement unit PD [99], tremor [113] 1 Dorsal hand Angular sensor PD [50, 79] 1 Dorsal hand Orie…”
BackgroundInfluentialPalani, P., Panigrahi, S., Renganathan, G., Kurita, Y., & Thondiyath, A. (2025) · Frontiers in Rehabilitation Sciences · doi:10.3389/fresc.2025.1474203 · Cited by 1
Ling, J. Q., Bakibillah, A. S. M., Chan, P. Y., Nurzaman, S. G., & Tan, C. P. (2025) · Scientific Reports · doi:10.1038/s41598-025-08216-7
“For supervised classifiers such as support vector machines (SVM), several researchers have proven their ability to classify PD and HC 8,12,13 .”
Feature Extraction to Classify Parkinsonian Tremor in EMG Signals
Krishnan, S. R. A., Maiti, R., Chandra, S., & Biswas, A. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-96-6414-6_22
Sakib, M., Khanom, S., Nahadi, T. M., Mithu, A. M., Ahmed, N., Islam, M., Sarker, T., Chisty, N., Ahad, A., Hossain, M. M., et al. (2025) · Biomedical Engineering Letters · doi:10.1007/s13534-025-00526-z · Cited by 1
L’analyse de signaux EMG et leur application au diagnostic de la maladie de Parkinson
Bengacemi, H. (2021) · theses.fr (ABES) · doi:10.70675/c9e9d83azeffez4851zbe06z6e079bd7ee64
Low-Cost IMU-EMG Prototype for Real-Time Tremor Classification
Patankar, P. S., Dhawanjewar, S., Dhane, P., et al. (2026) · doi:10.1109/gseact68539.2026.11619942
Metadata
- Authors
- Ghassemi, N. H., Marxreiter, F., Pasluosta, C. F., Kugler, P., Schlachetzki, J., Schramm, A., Eskofier, B. M., & Klucken, J.
- Affiliations
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Universitätsklinikum Erlangen (DE)
- ORCID
- Venue
- 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Publisher
- IEEE
- Published
- 2016-08
- Volume
- 2016
- Pages
- 672-675
- ISSN
- 2375-7477 (ISSN-L)
- OpenAlex
- W2537408572
- Cited by
- 39
- References
- 13
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 4 · 2023: 6 · 2022: 1 · 2021: 8 · 2020: 3 · 2019: 3 · 2018: 2 · 2017: 4
- FWCI
- 22.90
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Clinical Neurology › Deep Brain Stimulation and Movement Disorders
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Clinical Neurology › Parkinson's Disease Mechanisms and Treatments
- Keywords
- essential tremor, Parkinson's disease, tremor-dominant Parkinson's disease, tremor differential diagnosis, accelerometer, electromyography, hand movement analysis, discrete wavelet transform, support vector machine classification, posterior probability
- MeSH terms
- Aged, Aged, 80 and over, Electromyography, Female, Humans, Male, Middle Aged, Parkinson Disease, Discriminant Analysis, Essential Tremor, Principal Component Analysis, Wavelet Analysis, Support Vector Machine, 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.
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
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.