UDC

[616.831-005:616-009.1]+004.9(045)

DOI

https://doi.org/10.37482/2687-1491-Z275

Authors

Vera M. Ezhova* ORCID: https://orcid.org/0009-0000-2009-9042
Sofia A. Fominykh* ORCID: https://orcid.org/0009-0007-9168-5808
Daria E. Koshechko* ORCID: https://orcid.org/0009-0003-3417-1932
Ivan A. Rakhmanenko* ORCID: https://orcid.org/0000-0002-8799-601X
Evgeny Yu. Kostyuchenko* ORCID: https://orcid.org/0000-0001-8000-2716
Anna А. Zharova*/** ORCID: https://orcid.org/0000-0003-2597-3573
Aleksandra Yu. Dish*/** ORCID: https://orcid.org/0000-0003-1574-5243
*Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
**Rehabilitation Centre of the Social Fund of Russia “Klyuchi” (Tomsk, Russia)
Corresponding author: Ivan Rakhmanenko, address: prosp. Lenina 40, Tomsk, 634050, Russia; e-mail: ria@fb.tusur.ru

Abstract

The problem of restoring fine hand motor function remains highly relevant due to the crucial role of upper limbs in self-care, daily activities, and professional performance. Computer technologies for objective assessment and home-based rehabilitation of fine motor skills are urgently needed. The purpose of this study was to develop and evaluate an approach based on machine learning and the use of a digital pen on a graphic tablet to diagnose and, in the future, support recovery of fine motor skills in post-stroke patients. Materials and methods. We evaluated the statistical distinguishability of features differentiating healthy individuals from post-stroke patients based on pen position, height, pressure, and tilt angle on the tablet. Participants traced predefined standard patterns using a digital pen. The control group included 15 healthy volunteers, and the experimental group comprised 15 individuals with post-stroke fine motor impairment. Results. A set of features showing statistically significant differences between healthy participants and post-stroke patients was identified. Both the full dataset and a reduced dataset containing only significant features were used for binary classification. Five machine learning classifiers were compared for distinguishing between “healthy” and “patient” classes. The reduced feature set maintained high classification accuracy. Decision trees with bagging achieved 95.8% accuracy, making the proposed feature set promising for further clinical validation and screening applications.

Funding. The research was performed as part of the Development Programme of Tomsk State University of Control Systems and Radioelectronics for 2025–2036 within the Priority 2030 Strategic Academic Leadership Programme.

For citation: Ezhova V.M., Fominykh S.A., Koshechko D.E., Rakhmanenko I.A., Kostyuchenko E.Yu., Zharova A.A., Dish A.Yu. Development of an Automated Approach for Objective Assessment of Fine Hand Movement Impairments. Journal of Medical and Biological Research, 2026, vol. 14, no. 2, pp. 56–66. DOI: 10.37482/2687-1491-Z275

Keywords

stroke outcome, fine hand movements, computer technology in medicine, machine learning, fine motor impairment diagnosis, tablet-based graphomotor assessment

References

1. Ponomarenko G.N. (ed.). Fizicheskaya i reabilitatsionnaya meditsina [Physical and Rehabilitation Medicine]. Moscow, 2016. 685 p.

2. Stroke. World Health Organization. Available at: https://www.who.int/ru/news-room/fact-sheets/detail/stroke (accessed: 20 February 2026).

3. Khellaf A., Khan D.Z., Helmy A. Recent Advances in Traumatic Brain Injury. J. Neurol., 2019, vol. 266, no. 11, pp. 2878–2889. https://doi.org/10.1007/s00415-019-09541-4

4. Chernikova L.A. (ed.). Vosstanovitel’naya nevrologiya: innovatsionnye tekhnologii v neyroreabilitatsii [Restorative Neurology: Innovative Technologies in Neurorehabilitation]. Moscow, 2016. 344 p.

5. Purk M., Fujarski M., Becker M., Warnecke T., Varghese J. Utilizing a Tablet-Based Artificial Intelligence System to Assess Movement Disorders in a Prospective Study. Sci. Rep., 2023, vol. 13, no. 1. Art. no. 10362. https://doi.org/10.1038/s41598-023-37388-3

6. Willemse I.H.J., Schootemeijer S., van den Bergh R., Dawes H., Nonnekes J.H., van de Warrenburg B.P.C. Smartphone Applications for Movement Disorders: Towards Collaboration and Re-Use. Parkinsonism Relat. Disord., 2024, vol. 120. Art. no. 105988. https://doi.org/10.1016/j.parkreldis.2023.105988

7. Klymenko G., Liu K.P.Y., Bissett M., Fong K.N.K., Welage N., Wong R.S.M. Development and Initial Validity of the In-Hand Manipulation Assessment. Aust. Occup. Ther. J., 2018, vol. 65, no. 2, pp. 135–145. https://doi.org/10.1111/1440-1630.12447

8. Li Q., Gong R., Hase K. A Comprehensive Objective Evaluation Method for Handwriting Assistive Devices Using a Tablet and Digital Pen for Individuals with Upper Limb Dysfunction. Appl. Sci., 2024, vol. 14, no. 23. Art. no. 11190. https://doi.org/10.3390/app142311190

9. Drotár P., Mekyska J., Rektorová I., Masarová L., Smékal Z., Faundez-Zanuy M. Evaluation of Handwriting Kinematics and Pressure for Differential Diagnosis of Parkinson’s Disease. Artif. Intell. Med., 2016, vol. 67, pp. 39–46. https://doi.org/10.1016/j.artmed.2016.01.004

10. Grzhibovskiy A.M., Ivanov S.V., Gorbatova M.A. Opisatel’naya statistika s ispol’zovaniem paketov statisticheskikh programm Statistica i SPSS [Descriptive Statistics Using Statistica and SPSS Software]. Nauka I zdravookhranenie, 2016, no. 1, pp. 7–23. https://doi.org/10.24412/cl-16507658

11. Fadeykina O.V., Volkova R.A., Karpova E.V. Statisticheskaya obrabotka rezul’tatov attestatsii biologicheskikh standartnykh obraztsov: primenenie kriteriya Manna–Uitni [Statistical Processing of the Results of Certification of Biological Standard Samples: Application of the Mann–Whitney Criterion]. Khimiko-farmatsevticheskiy zhurnal, 2019, vol. 53, no. 7, pp. 54–58. https://doi.org/10.30906/0023-1134-2019-53-7-54-58

12. Nelli F. Machine Learning with Scikit-Learn. Nelli F. Python Data Analytics: Data Analysis and Science: With Pandas, Numpy, and Matplotlib. Berkeley, 2023, pp. 259–287.

13. Altman N., Krzywinski M. Ensemble Methods: Bagging and Random Forests. Nat. Methods, 2017, vol. 14, no. 10, pp. 933–934. https://doi.org/10.1038/nmeth.4438

14. Ezhova V.M., Koshechko D.E., Fominykh S.A. Opredelenie statisticheski znachimykh dinamicheskikh parametrov podpisi pri otslezhivanii dinamiki reabilitatsii posle insul’ta [Determining Statistically Significant Dynamic Parameters of the Signature for Monitoring Post-Stroke Rehabilitation Dynamics]. Elektronnye sredstva i sistemy upravleniya. Materialy dokladov Mezhdunarodnoy nauchno-prakticheskoy konferentsii, 2024, no. 1-2, pp. 44–46.

15. Alalayah K.M., Senan E.M., Atlam H.F., Ahmed I.A., Shatnawi H.S.A. Automatic and Early Detection of Parkinson’s Disease by Analyzing Acoustic Signals Using Classification Algorithms Based on Recursive Feature Elimination Method. Diagnostics (Basel), 2023, vol. 13, no. 11. Art. no. 1924. https://doi.org/10.3390/diagnostics13111924