Evaluation of normal postural control system and deteriorated postural control system due to brain stroke in altered sensory conditions to investigate sensory dysfunctions using deep learning approaches

Subject Areas : Sports Science and Healthy

Armin Najipour ¹ , Siamak Khoramimehr ² , Mahdi Razeghi ³ , kamran hasani ⁴

1 - 1 Department of Biomedical Engineering, College of Medical Science and Technologises, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - 1 Department of Biomedical Engineering, College of Medical Science and Technologises, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran
3 - 1 Department of Biomedical Engineering, College of Medical Science and Technologises, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran.
4 - 1 Department of Biomedical Engineering, College of Medical Science and Technologises, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran.

Received: 2024-05-12 Accepted : 2024-06-08

Keywords: Postural control system, sensory disorders, stroke, machine learning, balance.,

Abstract :

The ability to stand is very important to perform a variety of daily activities. This ability, which humans learn automatically from childhood, has received widespread attention from researchers in recent years, opening doors to study and investigate the ability to maintain. The situation becomes more balanced and controllable. Despite its apparent simplicity, the control of standing balance and the nature of the control mechanism that stabilizes postural fluctuations have been studied from various angles, and numerous studies have shown that multiple mechanisms and sensory systems are systematically involved in maintaining and controlling body posture. The purpose of this study is to assess the posture control system of healthy subjects and stroke patients in stimulated sensory conditions in order to detect sensory dysfunction using deep learning methods. After collecting the database, a combination of deep convolutional networks and type 2 fuzzy networks was used. The results demonstrated that deep learning network approaches, due to their high capability in selecting/extracting automatic features, can accurately classify collected data to diagnose the condition of healthy and sick people. Based on this, stroke patients were diagnosed and classified in stimulated sensory conditions using the proposed deep network with an accuracy greater than 98%, demonstrating that the proposed model is very effective at class separation, and it has looked promising.

References:

Arienti, C., Lazzarini, S. G., Pollock, A., & Negrini, S. (2019). Rehabilitation interventions for improving balance following stroke: An overview of systematic reviews. PloS one, 14(7), e021978.

Blaszczyk, J. W., Prince, F., Raiche, M., & Hébert, R. (2000). Effect of ageing and vision on limb load asymmetry during quiet stance. Journal of biomechanics, 33(10), 1243-1248

Chamberlin, C., Marmelat, V., Rosen, A. B., & Burcal, C. J. (2021). The effects of visual biofeedback and visual biofeedback scale size on single limb balance. Journal of Bodywork and Movement Therapies, 26, 268-272.

Chiari, L., Rocchi, L., & Cappello, A. (2002). Stabilometric parameters are affected by anthropometry and foot placement. Clinical biomechanics, 17(9-10), 666-677.

de Oliveira, M. R., Fabrin, L. F., de Oliveira Gil, A. W., Benassi, G. H., Camargo, M. Z., da Silva, R. A., & de Lima, R. R. (2021). Acute effect of core stability and sensory-motor exercises on postural control during sitting and standing positions in young adults. Journal of Bodywork and Movement Therapies, 28, 98-103.

Gad, A. G. (2022). Particle swarm optimization algorithm and its applications: a systematic review. Archives of computational methods in engineering, 29(5), 2531-2561.

Ghnemat, R., Khalil, A., & Abu Al-Haija, Q. (2023). Ischemic stroke lesion segmentation using mutation model and generative adversarial network. Electronics, 12(3), 590.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning: MIT press.

Keyvanara, M., Sadigh, M. J., Meijer, K., & Esfahanian, M. (2021). A model of human postural control inspired by separated human sensory systems. Biocybernetics and Biomedical Engineering, 41(1), 255-264.

Kim, S., & Moon, J. (2022). The effect of visual biofeedback balance training on time to stabilization and kinetic variables in patients with chronic ankle instability. Korean Journal of Sport Science, 33(3), 359-368.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.

Li, L., Zhang, S., & Dobson, J. (2019). The contribution of small and large sensory afferents to postural control in patients with peripheral neuropathy. Journal of sport and health science, 8(3), 218-227.

Murugeswari, P., & Vijayalakshmi, S. (2021). A New Method of Interval Type-2 Fuzzy-Based CNN for Image Classification. Paper presented at the Computational Vision and Bio-Inspired Computing: ICCVBIC 2020
.
Nichols, D. S. (1997). Balance retraining after stroke using force platform biofeedback. Physical therapy, 77(5), 553-558.

Norris, J. A., Marsh, A. P., Smith, I. J., Kohut, R. I., & Miller, M. E. (2005). Ability of static and statistical mechanics posturographic measures to distinguish between age and fall risk. Journal of biomechanics, 38(6), 1263-1272
.
Richmond, S. B., Whittier, T. T., Peterson, D. S., & Fling, B. W. (2021). Advanced characterization of static postural control dysfunction in persons with multiple sclerosis and associated neural mechanisms. Gait & posture, 83, 114-120.

Sadura-Sieklucka, T., Czerwosz, L. T., Kądalska, E., Kożuchowski, M., Księżopolska-Orłowska, K., & Targowski, T. (2023). Is balance training using biofeedback effective in the prophylaxis of falls in women over the age of 65? Brain sciences, 13(4), 629
.
Shen, T., Wang, J., Gou, C., & Wang, F.-Y. (2020). Hierarchical fused model with deep learning and type-2 fuzzy learning for breast cancer diagnosis. IEEE Transactions on Fuzzy Systems, 28(12), 3204-3218.

Soltanpour, M., Greiner, R., Boulanger, P., & Buck, B. (2021). Improvement of automatic ischemic stroke lesion segmentation in CT perfusion maps using a learned deep neural network. Computers in biology and medicine, 137, 104849.

Talis, V., & Kazennikov, O. (2019). Effects of body turn on postural sway during symmetrical and asymmetrical standing. Experimental brain research, 237, 2231-2237.

Tuncer, D., Gurses, H. N., Senaran, H., Uzer, G., & Tuncay, I. (2022). Evaluation of postural control in children with increased femoral anteversion. Gait & posture, 95, 109-114.

Vouriot, A., Gauchard, G. C., Chau, N., Benamghar, L., Lepori, M.-L., Mur, J.-M., & Perrin, P. P. (2004). Sensorial organisation favouring higher visual contribution is a risk factor of falls in an occupational setting. Neuroscience research, 48(3), 239-247.

Xu, Y., Zeng, Z., Oliveria, C., Munoz, R., de Almeida, R., Quezada, A., . . . de Albuquerque, V. H. C. (2022). Postural evaluation based on body movement and mapping sensors. Measurement, 190, 110538.