Development of a convolutional neural network (CNN) based assessment exercise recommendation system for individuals with chronic stroke: a feasibility study.

BACKGROUND: The use of artificial intelligence (AI) is revolutionizing nearly every aspect of healthcare, but the application of AI in rehabilitation is lagging behind. Clinically, gait parameters and patterns are used to evaluate stroke-specific impairment. We hypothesized that gait kinematics of individuals with stroke provide rich information for the deep-learning to predict the clinical decisions made by physiotherapist. OBJECTIVE: To investigate whether the results of clinical assessments and exercise recommendations by physiotherapists can be accurately predicted using a deep-learning algorithm with gait kinematics data. METHOD: In this cross-sectional study, 40 individuals with stroke were assessed by a physiotherapist using the lower-extremity subscale of the Fugl-Meyer Assessment (FMA-LE) and Berg Balance Scale (BBS). The physiotherapist also decided whether or not the single-leg-stance was an appropriate balance training for each participant. The participants were classified as having good mobility and a low fall risk based on the cutoff scores of the two clinical scales. A convolutional neural network (CNN) was trained using gait kinematics to predict the assessment results and exercise recommendations. RESULTS: The trained model accurately predicted the results of the clinical assessments and decisions with an average prediction accuracy of 0.84 for the FMA-LE, 0.66 for the BBS, and 0.78 for the recommendation of the single-leg-stance exercise. CONCLUSIONS: This CNN deep-learning model provided time-effective and accurate prediction of clinical assessment results and exercise recommendations. This study provides preliminary evidence to support the use of biomechanical data and AI to assist treatment planning and shorten the decision-making process in rehabilitation.

Immediate effects of transcutaneous electrical nerve stimulation on gait patterns in chronic stroke survivors: A single group, pretest-posttest clinical trial.

BACKGROUND: Transcutaneous electrical nerve stimulation (TENS) has been used to reduce muscle spasticity and improve locomotion in stroke survivors. We speculate that acute changes in gait performance after TENS mediate functional improvement in the long-term. However, no previous study has investigated the effect of TENS on ankle kinetics and kinematics during walking in stroke survivors. PURPOSE: We aimed to investigate whether TENS applied over the paretic leg could rapidly improve the plantar flexion moment and ankle kinematics in chronic stroke survivors with lower limb paresis. METHODS: Twenty chronic stroke survivors were recruited. They underwent 30 min of TENS over the area innervated by the common peroneal nerve on the paretic leg. Three-dimensional (3D) motion capture was performed and ankle plantar flexor spasticity was assessed before and immediately after stimulation. Ankle kinematics and kinetic and spatiotemporal data were collected using 3D motion capture. Ankle plantar flexor spasticity was assessed using the Modified Tardieu Scale. PRINCIPAL RESULTS: A significant increase in the ankle plantar flexion moment of the paretic side during the pre-swing phase was observed immediately after stimulation (p = 0.009, maximal mean difference = 0.035, 95%CI = 0.0125 to 0.0575). The step length of the paretic limb also increased significantly after stimulation (p = 0.023, mean difference = -0.02, 95%CI = -0.04 to -0.004). TENS had no immediate effect on paretic ankle spasticity, as measured by the Modified Tardieu Scale, or on other temporo-spatial parameters. CONCLUSION: The findings support the use of TENS to improve the motor function and gait pattern in chronic stroke survivors. The study indicated that the application of TENS to the paretic leg before gait training might improve rehabilitation outcomes. Future studies investigating the effects of TENS on functional outcomes, the optimal stimulation duration, and assessing spasticity using more sensitive measures are warranted.