Automatic Assessment of Upper Extremity Function and Mobile Application for Self-Administered Stroke Rehabilitation.

Rehabilitation training is essential for a successful recovery of upper extremity function after stroke. Training programs are typically conducted in hospitals or rehabilitation centers, supervised by specialized medical professionals. However, frequent visits to hospitals can be burdensome for stroke patients with limited mobility. We consider a self-administered rehabilitation system based on a mobile application in which patients can periodically upload videos of themselves performing reach-to-grasp tasks to receive recommendations for self-managed exercises or progress reports. Sensing equipment aside from cameras is typically unavailable in the home environment. A key contribution of our work is to propose a deep learning-based assessment model trained only with video data. As all patients carry out identical tasks, a fine-grained assessment of task execution is required. Our model addresses this difficulty by learning RGB and optical flow data in a complementary manner. The correlation between the RGB and optical flow data is captured by a novel module for modality fusion using cross-attention with Transformers. Experiments showed that our model achieved higher accuracy in movement assessment than existing methods for action recognition. Based on the assessment model, we developed a patient-centered, solution-based mobile application for upper extremity exercises for hemiplegia, which can recommend 57 exercises with three levels of difficulty. A prototype of our application was evaluated by potential end-users and achieved a good quality score on the Mobile Application Rating Scale (MARS).

Asymmetry and Variability Should Be Included in the Assessment of Gait Function in Poststroke Hemiplegia With Independent Ambulation During Early Rehabilitation.

OBJECTIVE: To extract independent features from spatiotemporal data of poststroke gait. DESIGN: Retrospective observational study. SETTING: Motion analysis laboratory in the rehabilitation department of a university hospital. PARTICIPANTS: Convenience sample from inpatients in subacute recovery stage post stroke. Of 98 patients post stroke who underwent gait assessment, 69 patients post stroke were included in the data analysis (N=69). They could walk more than 10 m without personal assist or assistive devices. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Spatiotemporal parameters during level walking and their asymmetry and variability were obtained by insole foot pressure measurement system. RESULTS: Of independent components extracted by principal component analysis, 3 independent components explained 81.9% of total variance of spatiotemporal poststroke gait data. The first component has associations with walking speed and proportion of double support phase, and it explains 46.6% of total variance. The second component has association with temporal asymmetry, and it explains 21.1% of total variance. The third component has association with temporal variability, and it explains 14.2% of total variance. Principal component scores did not show significant differences between stroke types and among stroke lesions. CONCLUSIONS: Temporal asymmetry and variability should be included in the assessment of poststroke gait during early rehabilitation. They are independent of each other and provide characteristics of poststroke gait that are independent to the walking speed. They are helpful for rehabilitation planning and developing treatment strategy in poststroke gait rehabilitation.

Change in Center of Pressure Progression in the Foot Provides Clues for Functional Improvement of the More Affected Lower Limb During Post-stroke Gait Rehabilitation.

OBJECTIVE: The aim of this study was to determine the clinical significance of the anterior-posterior displacement of the center of pressure in the foot (apCoP) in post-stroke gait rehabilitation. DESIGN: This observational study was conducted in a tertiary hospital. Forty-two subacute post-stroke patients were included. The apCoP was measured twice with a wearable insole foot pressure measurement system, time interval more than 7 days. The results were compared between the first and second tests. The relationship between apCoP changes and spatiotemporal parameter changes were investigated. RESULTS: The apCoP increased significantly between tests. The change in walking speed was significantly predicted by the change in the apCoP on the less affected side. The change in asymmetry of the single support phase was significantly correlated with the change in the apCoP on the more affected side. CONCLUSION: The change in apCoP provides information about the restoration of body support, body forward progression control, and propulsion in the more affected lower limb during early post-stroke rehabilitation. The apCoP can be a useful parameter for the monitoring of functional changes in the more affected lower limb during post-stroke gait rehabilitation.