Algorithmic approach to tremor classification based on EEG and graphomotor signals
Article Sidebar
Main Article Content
Abstract
This study presents an algorithmic framework for tremor classification and differential diagnosis based on multimodal analysis of electroencephalographic (EEG) signals and graphomotor activity recorded during a spiral drawing task on a graphics tablet. Motor deviations were quantified using the ΔR metric, defined as the difference between the actual radial trajectory and its smoothed reference obtained via parametric curve fitting. EEG and graphomotor signals were synchronized and preprocessed through normalization and interpolation. All available EEG channels were included in the analysis to comprehensively capture cortical activity patterns. The method centers on cross-correlation analysis between ΔR and individual EEG channels to reveal spatiotemporal brain activity patterns associated with tremor, and introduces a sinusoidality index of cross-correlation curves as an indicator of cortical synchrony under different clinical conditions. Experimental results from patients with Parkinson’s disease (medicated and unmedicated) and tremor of undetermined origin showed that pronounced tremor corresponds to higher inter-channel synchronization, whereas symptom reduction is marked by more independent EEG activity. The proposed approach combines quantitative computation with adaptability to individual patient profiles, and can serve as the basis for portable or cloud-based systems for automated tremor analysis and monitoring, expanding the capabilities of telemedicine and personalized neurodiagnostics. The proposed algorithmic approach integrates advanced software engineering techniques for multimodal signal synchronization, numerical analysis, and feature extraction, representing an applied solution at the intersection of biomedical data processing and computer science.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
1. Alrawis M., Al-Ahmadi S., Mohammad F. Bridging modalities: A multimodal machine learning approach for Parkinson’s disease diagnosis using EEG and MRI data // Appl. Sci. – 2024. – Vol. 14, No. 9. – Art. 3883.
2. Jain S., Srivastava R. Multi-modality NDE fusion using encoder–decoder networks for identify multiple neurological disorders from EEG signals // Technol. Health Care. – 2024. – Vol. 1. – Art. 09287329241291334.
3. Tang L., Hu Q., Wang X., Liu L., Zheng H., Yu W., Song C. A multimodal fusion network based on a cross-attention mechanism for the classification of Parkinsonian tremor and essential tremor // Sci. Rep. – 2024. – Vol. 14. – Art. 28050.
4. Guo Y., Huang D., Zhang W., Wang L., Li Y., Olmo G., Chan P. High-accuracy wearable detection of freezing of gait in Parkinson’s disease based on pseudo-multimodal features // Comput. Biol. Med. – 2022. – Vol. 146. – Art. 105629.
5. Ma C., Ma Y., Pan L., Li X., Yin C., Zong R., Zhang Z. Automatic diagnosis of multi-task in essential tremor: Dynamic handwriting analysis using multi-modal fusion neural network // Future Gener. Comput. Syst. – 2023. – Vol. 145. – P. 429–441.
6. Raj K.D., Lal G.J., Gopalakrishnan E.A., Sowmya V., Orozco-Arroyave J.R. A visibility graph approach for multi-stage classification of Parkinson’s disease using multimodal data // IEEE Access. – 2024. – Vol. 12. – P. 87077–87096.
7. Miah A.S.M., Suzuki T., Shin J. A methodological and structural review of Parkinson’s disease detection across diverse data modalities // IEEE Access. – 2025. – Vol. 13. – P. 98931–98975.
8. Murtaza G., Hammoud M., Somov A. Multi-modal feature set-based detection of freezing of gait in Parkinson’s disease patients using SVM // IEEE Access. – 2025. – Vol. 13. – P. 114798–114811.
9. Skaramagkas V., Pentari A., Kefalopoulou Z., Tsiknakis M. Multi-modal deep learning diagnosis of Parkinson’s disease — A systematic review // IEEE Trans. Neural Syst. Rehabil. Eng. – 2023. – Vol. 31. – P. 2399–2423.
10. Dhivyaa C.R., Nithya K., Anbukkarasi S. Enhancing Parkinson’s disease detection and diagnosis: A survey of integrative approaches across diverse modalities // IEEE Access. – 2024. – Vol. 12. – P. 158999–159024.
11. Farashi S., Sarihi A., Ramezani M., Kashani H. Parkinson’s disease tremor prediction using EEG data analysis – A preliminary and feasibility study // BMC Neurol. – 2023. – Vol. 23, No. 1. – P. 420.
12. Yu N.Y., Van Gemmert A.W.A., Chang S.H. Characterization of graphomotor functions in individuals with Parkinson’s disease and essential tremor // Behav. Res. Methods. – 2017. – Vol. 49, No. 3. – P. 913–922.
13. Brambilla C., Pirovano I., Mira R.M., Rizzo G., Scano A., Mastropietro A. Combined use of EMG and EEG techniques for neuromotor assessment in rehabilitative applications: A systematic review // Sensors. – 2021. – Vol. 21, No. 21. – Art. 7014.
14. Zhang X., Chen H., Tao L., Zhang X., Wang H., He W., Fang W. Combined multivariate pattern analysis with frequency-dependent intrinsic brain activity to identify essential tremor // Neurosci. Lett. – 2022. – Vol. 776. – Art. 136566.
15. Chyniak O., Dubenko O., Potapov O., Shulha A., Kotsiuba A. Хвороба Паркінсона – огляд сучасних методів лікування // EUMJ. – 2023. – Vol. 11, No. 1. – P. 1–13.
16. Petryk M., Bishchak D., Bachynskyi M., Brevus V., Chyzh V., Mykhalyk D. Аналіз мимовільних рухів пацієнтів із симптомами тремору під впливом когнітивних впливів // Прикладні питання мат. моделювання. – 2024. – Vol. 7, No. 2. – P. 150–165.
17. Osiichuk I., Brevus V., Bishchak D., Mashtaliar Y., Mudryk I. Leveraging graphics tablet and JPen library to detect essential tremor // CEUR Workshop Proc. – 2024. – Vol. 3742. – P. 63–69.
18. Pastukh O., Yatsyshyn V. Brain-computer interaction neurointerface based on artificial intelligence and its parallel programming using high-performance calculation on cluster mobile devices // Visnyk TNTU. – 2023. – No. 4(112). – P. 26–31.
19. Andersen R.A. From thought to action: The brain–machine interface in posterior parietal cortex // Proc. Natl. Acad. Sci. – 2019. – Vol. 116, No. 52. – P. 26274–26279.