Ibitoye Morufu Olusola, Hamzaid Nur Azah, Abdul Wahab Ahmad Khairi, Hasnan Nazirah, Olatunji Sunday Olusanya, Davis Glen M
Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, Malaysia; Department of Biomedical Engineering, Faculty of Engineering and Technology, University of Ilorin, P.M.B 1515, Ilorin, Nigeria.
Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur, 50603, Malaysia.
Comput Biol Med. 2020 Feb;117:103614. doi: 10.1016/j.compbiomed.2020.103614. Epub 2020 Jan 11.
Using traditional regression modelling, we have previously demonstrated a positive and strong relationship between paralyzed knee extensors' mechanomyographic (MMG) signals and neuromuscular electrical stimulation (NMES)-assisted knee torque in persons with spinal cord injuries. In the present study, a method of estimating NMES-evoked knee torque from the knee extensors' MMG signals using support vector regression (SVR) modelling is introduced and performed in eight persons with chronic and motor complete spinal lesions.
The model was developed to estimate knee torque from experimentally derived MMG signals and other parameters related to torque production, including the knee angle and stimulation intensity, during NMES-assisted knee extension.
When the relationship between the actual and predicted torques was quantified using the coefficient of determination (R), with a Gaussian support vector kernel, the R value indicated an estimation accuracy of 95% for the training subset and 94% for the testing subset while the polynomial support vector kernel indicated an accuracy of 92% for the training subset and 91% for the testing subset. For the Gaussian kernel, the root mean square error of the model was 6.28 for the training set and 8.19 for testing set, while the polynomial kernels for the training and testing sets were 7.99 and 9.82, respectively.
These results showed good predictive accuracy for SVR modelling, which can be generalized, and suggested that the MMG signals from paralyzed knee extensors are a suitable proxy for the NMES-assisted torque produced during repeated bouts of isometric knee extension tasks. This finding has potential implications for using MMG signals as torque sensors in NMES closed-loop systems and provides valuable information for implementing this method in research and clinical settings.
我们之前利用传统回归模型，证明了脊髓损伤患者中，瘫痪的膝伸肌肌机械图（MMG）信号与神经肌肉电刺激（NMES）辅助下的膝关节扭矩之间存在正向且强烈的关系。在本研究中，我们引入了一种使用支持向量回归（SVR）模型从膝伸肌的MMG信号估计NMES诱发膝关节扭矩的方法，并在8名患有慢性运动完全性脊髓损伤的患者中进行了测试。
开发该模型以根据实验得出的MMG信号以及与扭矩产生相关的其他参数（包括膝关节角度和刺激强度）来估计NMES辅助膝关节伸展过程中的膝关节扭矩。
当使用决定系数（R）对实际扭矩和预测扭矩之间的关系进行量化时，对于高斯支持向量核，R值表明训练子集的估计准确率为95%，测试子集为94%；而多项式支持向量核表明训练子集的准确率为92%，测试子集为91%。对于高斯核，模型训练集的均方根误差为6.28，测试集为8.19；而多项式核训练集和测试集的均方根误差分别为7.99和9.82。
这些结果表明SVR建模具有良好的预测准确性，且可推广应用，这表明瘫痪膝伸肌的MMG信号是重复等长膝关节伸展任务期间NMES辅助扭矩的合适替代指标。这一发现对于在NMES闭环系统中使用MMG信号作为扭矩传感器具有潜在意义，并为在研究和临床环境中实施该方法提供了有价值的信息。
