A Novel Quantitative Spasticity Evaluation Method Based on Surface Electromyogram Signals and Adaptive Neuro Fuzzy...

Area of Science:

• Biomedical Engineering
• Neurorehabilitation
• Signal Processing

Background:

• Stroke survivors frequently experience muscle spasticity, necessitating objective and quantitative assessment methods.
• Current quantitative spasticity assessment, like the tonic stretch reflex threshold (TSRT), is cumbersome and time-intensive due to multiple passive stretches.
• There is a need for convenient and accurate spasticity evaluation tools to guide rehabilitation.

Purpose of the Study:

• To introduce and validate a novel spasticity evaluation method combining surface electromyogram (sEMG) signals with an adaptive neuro fuzzy inference system (sEMG-ANFIS).
• To compare the performance of the sEMG-ANFIS method against the conventional TSRT method in stroke patients with spasticity.

Main Methods:

• Eleven stroke patients with spasticity and four healthy subjects participated.
• Surface electromyogram (sEMG) signals from elbow flexors/extensors were recorded during 4-5 passive stretches.
• Time-domain and frequency-domain sEMG features were extracted and analyzed using the ANFIS classifier.
• Modified Ashworth Scale (MAS) scores were also obtained for correlation.

Main Results:

• The sEMG-ANFIS method demonstrated excellent regression performance with a mean accuracy of 0.96 and a mean RMSE of 0.13.
• This significantly outperformed the TSRT method, which achieved an accuracy of 0.88 and an RMSE of 0.28.
• The novel method requires fewer passive stretch repetitions, enhancing convenience.

Conclusions:

• The sEMG-ANFIS method provides a highly accurate and convenient approach for assessing muscle spasticity in stroke patients.
• This technique can aid in developing personalized rehabilitation programs and offer therapeutic feedback for interventions like shockwave therapy and repetitive transcranial magnetic stimulation.