A low cost, adaptive mixed reality system for home-based stroke rehabilitation

A Hierarchical Bayesian Model for Cyber-Human Assessment of Movement in Upper Extremity Stroke Rehabilitation

The evidence-based quantification of the relation between changes in movement quality and functionality can assist clinicians in achieving more effective structuring or adapting of therapy. In this paper, clinicians rated task, segment, and composite movement feature performance for 478 videos of stroke survivors executing upper extremity therapy tasks. We used the clinician ratings to develop a Hierarchical Bayesian Model (HBM) with task, segment, and composite layers for computing the statistical relation of movement quality changes to function. The model was enhanced through a detailed correlation graph ( ∆HBM ) that links computationally extracted kinematics with clinician-rated composite features for different task-segment combinations. Utilizing the weights and correlation graphs, we finally derive reverse cascading probabilities of the proposed HBM from kinematics to composite features, segments, and tasks. In a test involving 98 cases where clinician ratings differed, the HBM resolved 95% of these discrepancies. The model effectively aligned kinematic data with specific task-segment combinations in over 90% of cases. Once the HBM is expanded and refined through additional data it can be used for the automated calculation of statistical relations between changes in kinematics and performance of functional tasks and the generation of therapy assessment recommendations for clinicians. While our work primarily focuses on the upper extremities of stroke survivors, the HBM can be adapted to many other neurorehabilitation contexts.

Safety, Feasibility, and Acceptability of a New Virtual Rehabilitation Platform: A Supervised Pilot Study

Purpose:

Stroke is the leading cause of disability in adults worldwide, with hemiparesis being the most prevalent consequence. The use of video games and movement sensors could contribute to improving patients’ chances of recovery. We performed a supervised pilot study to validate the safety, feasibility, and acceptability of a new virtual rehabilitation platform in patients with chronic post-stroke upper limb hemiparesis.

Methods:

The participants (n = 9) participated in 40 rehabilitation sessions, twice a week, for a period of 20 weeks. Their experiences with the platform were documented using a Likert-scale survey. Changes in motor function were evaluated using the Chedoke Arm and Hand Activity Inventory (CAHAI) and the Wolf Motor Function Test (WMFT).

Results and conclusions:

All participants expressed that they enjoyed the experience and felt comfortable using the platform. Preliminary results showed significant motor recovery (P = .0039) according to the WMFT scores. Patients with significant impairment showed no improvement in upper limb task-oriented motor function after therapy.

The new platform is safe and well-accepted by patients. The improvement in motor function observed in some of the participants should be attributed to the therapy since spontaneous functional recovery is not expected in chronic stroke patients.

Automated Movement Assessment in Stroke Rehabilitation

We are developing a system for long term Semi-Automated Rehabilitation At the Home (SARAH) that relies on low-cost and unobtrusive video-based sensing. We present a cyber-human methodology used by the SARAH system for automated assessment of upper extremity stroke rehabilitation at the home. We propose a hierarchical model for automatically segmenting stroke survivor's movements and generating training task performance assessment scores during rehabilitation. The hierarchical model fuses expert therapist knowledge-based approaches with data-driven techniques. The expert knowledge is more observable in the higher layers of the hierarchy (task and segment) and therefore more accessible to algorithms incorporating high level constraints relating to activity structure (i.e., type and order of segments per task). We utilize an HMM and a Decision Tree model to connect these high level priors to data driven analysis. The lower layers (RGB images and raw kinematics) need to be addressed primarily through data driven techniques. We use a transformer based architecture operating on low-level action features (tracking of individual body joints and objects) and a Multi-Stage Temporal Convolutional Network(MS-TCN) operating on raw RGB images. We develop a sequence combining these complimentary algorithms effectively, thus encoding the information from different layers of the movement hierarchy. Through this combination, we produce a robust segmentation and task assessment results on noisy, variable and limited data, which is characteristic of low cost video capture of rehabilitation at the home. Our proposed approach achieves 85% accuracy in per-frame labeling, 99% accuracy in segment classification and 93% accuracy in task completion assessment. Although the methodology proposed in this paper applies to upper extremity rehabilitation using the SARAH system, it can potentially be used, with minor alterations, to assist automation in many other movement rehabilitation contexts (i.e., lower extremity training for neurological accidents).

An Adaptive Home-Use Robotic Rehabilitation System for the Upper Body

Robotic rehabilitation systems have been developed to treat musculoskeletal conditions, but limited availability prevents most patients from using them. The objective of this paper was to create a home-use robotic rehabilitation system. Data were obtained in real time from a Microsoft \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${\rm Kinect}^{\rm TM}$ \end{document} and a wireless surface electromyograph system. Results from the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${\rm Kinect}^{\rm TM}$ \end{document} sensor were compared to a standard motion capture system. A subject completed visual follow exercise tasks in a 3-D visual environment. Data from two training exercises were used to generate a neural network, which was then used to simulate the subject's individual performance. The subjects completed both the exercise task output from the neural network (custom), and the unmodified task (standard). In addition, a wearable arm robot prototype was built. Basic system identification was completed, and a control algorithm for the robot based on pressure control was designed and tested. The subjects had greater root-mean-square error for position and velocity variables during the custom exercise tasks. These results suggest that the custom task was difficult to complete, possibly because the neural network was unconstrained. Finally, the robot prototype was able to mimic changes in a subject's elbow angle in real time, demonstrating the feasibility of the robotic rehabilitation system.

A feasibility study of an upper limb rehabilitation system using Kinect and computer games

A new low-cost system for rehabilitation of the impaired upper limb for stroke survivors is presented. A computer game was developed specifically for this purpose and the user's impaired upper extremity is tracked using a downward-pointed Kinect, an inexpensive motion capture system commercially available from Microsoft. A Kalman filter was implemented to reduce data jittering. Patients are required to move their impaired arm, sliding it on top of a transparent support, in order to play the game. The game is personalized to the patient through specific settings that adapt to the patient's range of motion and motor control at the start of the game as well as performance during the game. The final score is proportional to the arm's movement speed. A feasibility study was carried out with one stroke survivor. The game was played for ten days and usability surveys were answered before and after the study. The patient was engaged with the game, found it easy to understand and reported willingness to use it in the home environment and enjoyment of the use in the clinic.