Search

BACKGROUND: Although clinical machine learning (ML) algorithms offer promising potential in forecasting optimal stroke rehabilitation outcomes, their specific capacity to ascertain favorable outcomes and identify responders to robotic-assisted gait training (RAGT) in individuals with hemiparetic stroke undergoing such intervention remains unexplored. OBJECTIVE: We aimed to determine the best predictive model based on the international classification of functioning impairment domain features (Fugl– Meyer assessment (FMA), Modified Barthel index related-gait scale (MBI), Berg balance scale (BBS)) and reveal their responsiveness to robotic assisted gait training (RAGT) in patients with subacute stroke. METHODS: Data from 187 people with subacute stroke who underwent a 12-week Walkbot RAGT intervention were obtained and analyzed. Overall, 18 potential predictors encompassed demographic characteristics and the baseline score of functional and structural features. Five predictive ML models, including decision tree, random forest, eXtreme Gradient Boosting, light gradient boosting machine, and categorical boosting, were used. RESULTS: The initial and final BBS, initial BBS, final Modified Ashworth scale, and initial MBI scores were important features, predicting functional improvements. eXtreme Gradient Boosting demonstrated superior performance compared to other models in predicting functional recovery after RAGT in patients with subacute stroke. CONCLUSION: eXtreme Gradient Boosting may be an invaluable prognostic tool, providing clinicians and caregivers with a robust framework to make precise clinical decisions regarding the identification of optimal responders and effectively pinpoint those who are most likely to derive maximum benefits from RAGT interventions. [ABSTRACT FROM AUTHOR]

BACKGROUND: While the limited ankle dorsiflexion syndrome (ADS) is common in neuro-musculoskeletal conditions, the instrument-assisted mobilization focused on the shortened gastro-soleus myofascial structure (IMI) rather than the homologous structure (both gastrosoleus and tibiliais anterior muscles, HIM). OBJECTIVE: We aimed to compare the immediate therapeutic effects between IMH and IMI treatment groups on the ankle dorsiflexion angle, muscle activation and foot pressure distribution during dynamic gait in ADS. METHODS: Neuromechanical tests including kinematics (ankle mobility), kinetics (center of pressure distribution), and electromyography were used to determine the immediate therapeutic effects between HIM and IMI treatment groups in 24 participants with ADS. RESULTS: The ankle joint angle analysis demonstrated a more improved active DF angle in the group who received HIM intervention when compared to the group who received IMI intervention. (11.26% and 3.58%, respectively) EMG analysis showed more decreased mean and peak TA activation amplitudes in the group who received HIM intervention (9.1% and 9%) when compared to the group who received IMI intervention (11.48% and 1.48%). Plantar pressure distribution analysis showed difference that the forefoot/area decreased in the group who received HIM intervention (8.1%), but rather increased in the group who received IMI intervention (14.3%). CONCLUSIONS: Our neuromechanical results demonstrated promising positive effects on ankle joint mobility, muscle activation and foot pressure distribution during gait in ADS. [ABSTRACT FROM AUTHOR]

Arm-leg coordinated humanoid exoskeletal robots offer a solution to the ‘unnatural’ gait patterns seen in current leg-only exoskeletons, but their neuromechanical control mechanisms require further exploration.This study investigates the neuromechanical properties and modulation of cervical and lumbar central pattern generators (CPGs) across different gait training conditions.Eleven healthy adults (mean age: 25.27 ± 1.95 years; 5 females, 6 males) participated in gait analysis involving kinematics, kinetics, and electromyography during treadmill-based arm-leg interlimb coordination (TIT), robot-assisted arm-leg coordination (RIT), and robot-assisted leg-only coordination (RLT).Trunk counterrotation and shoulder, hip, and knee kinematics in RIT closely resembled those in TIT (5–10% variance) but significantly differed from RLT (30–40% variance). Electromyography revealed normalized reciprocal activation between the anterior and posterior deltoids (r = -0.48), tibialis anterior, and gastrocnemius (r = -0.68) during RIT, while RLT showed altered agonist-antagonist co-activation (r = 0.84).These findings highlight the importance of cervical and lumbar CPG interaction in natural locomotion, suggesting that arm-leg coordinated exoskeletons could improve neurorehabilitation for individuals recovering from stroke or spinal cord injury. [ABSTRACT FROM AUTHOR]

Proprioceptive neuromuscular facilitation (PNF) alone has limited effectiveness in restoring gait, while robotic-assisted gait training (RAGT) improves motor relearning through repetitive, task-specific movements. Combining PNF with robotic gait training (PRGT) may enhance locomotor recovery by promoting proprioceptive awareness and muscle activation alongside repetitive gait retraining in stroke patients.This study compares the immediate effects of PRGT and RAGT on ankle dorsiflexion and muscle activity in chronic hemiparetic stroke patients and healthy controls.Thirty participants, including 15 stroke patients and 15 healthy controls, were randomly assigned to PRGT or RAGT for a single 30-min session. Muscle activity (pectoralis major, external oblique, internal oblique/transverse abdominis, rectus femoris, tibialis anterior) was measured using electromyography, while ankle dorsiflexion angle was assessed using a dual-axis inclinometer.PRGT significantly increased muscle activations compared to RAGT in stroke patients (p < 0.05). Additionally, there was a significant difference in ankle dorsiflexion between RAGT and PRGT in both groups (p < 0.05).PRGT demonstrated superior immediate effects on muscle activation and ankle movement, suggesting that combining PNF with robotic-assisted gait training is beneficial for chronic stroke rehabilitation. [ABSTRACT FROM AUTHOR]

Optimal candidates and interventions for advanced robot-assisted stroke gait rehabilitation remain unknown.We aimed to determine the optimal therapeutic efficacy for balance, sensorimotor and locomotor functions, daily activity, and cognition between the lower-entering functional ambulation category (L-FAC) and higher-entering FAC (H-FAC) groups.190 stroke patients received conventional physical therapy (CPT), exoskeletal robotic-assisted gait training (RAGT), or end-effector RAGT (eRAGT), each comprising 60-min/session, two times per week for 10–20 weeks. Standardized clinical tests included the Fugl–Meyer assessment of the lower extremities, Berg balance scale, FAC, modified Barthel index, and mini-mental state examination. A two-way analysis of variance was performed, with significance set at P < 0.05.Both groups demonstrated significant improvements. Compared with the H-FAC group, L-FAC group achieved the most notable improvements in sensorimotor function, balance, gait, daily activity, and cognition after RAGT, followed by CPT and eRAGT (P < 0.05).RAGT was more effective than CPT and eRAGT on sensorimotor function, balance, and gait function in patients with stroke with L-FAC. We identified the optimal candidates and interventions for balance, gait, and cognition patients with stroke. [ABSTRACT FROM AUTHOR]