Background: New technologies to improve post-stroke rehabilitation outcomes are of great interest and have a positive impact on functional, motor, and cognitive recovery. Identifying the most effective rehabilitation intervention is a recognized priority for stroke research and provides an opportunity to achieve a more desirable effect. Objective: The objective is to verify the effect of new technologies on motor outcomes of the upper limbs, functional state, and cognitive functions in post-stroke rehabilitation. Methods: Forty two post-stroke patients (8.69 ± 4.27 weeks after stroke onset) were involved in the experimental study during inpatient rehabilitation. Patients were randomly divided into two groups: conventional programs were combined with the Armeo Spring robot-assisted trainer (Armeo group; n = 17) and the Kinect-based system (Kinect group; n = 25). The duration of sessions with the new technological devices was 45 min/day (10 sessions in total). Functional recovery was compared among groups using the Functional Independence Measure (FIM), and upper limbs’ motor function recovery was compared using the Fugl–Meyer Assessment Upper Extremity (FMA-UE), Modified Ashworth Scale (MAS), Hand grip strength (dynamometry), Hand Tapping test (HTT), Box and Block Test (BBT), and kinematic measures (active Range Of Motion (ROM)), while cognitive functions were assessed by the MMSE (Mini-Mental State Examination), ACE-R (Addenbrooke’s Cognitive Examination-Revised), and HAD (Hospital Anxiety and Depression Scale) scores. Results: Functional independence did not show meaningful differences in scores between technologies (p > 0.05), though abilities of self-care were significantly higher after Kinect-based training (p < 0.05). The upper limbs’ kinematics demonstrated higher functional recovery after robot training: decreased muscle tone, improved shoulder and elbow ROMs, hand dexterity, and grip strength (p < 0.05). Besides, virtual reality games involve more arm rotation and performing wider movements. Both new technologies caused an increase in overall global cognitive changes, but visual constructive abilities (attention, memory, visuospatial abilities, and complex commands) were statistically higher after robotic therapy. Furthermore, decreased anxiety level was observed after virtual reality therapy (p < 0.05). Conclusions: Our study displays that even a short-term, two-week training program with new technologies had a positive effect and significantly recovered post-strokes functional level in self-care, upper limb motor ability (dexterity and movements, grip strength, kinematic data), visual constructive abilities (attention, memory, visuospatial abilities, and complex commands) and decreased anxiety level.

The findings show the benefits of robot therapy in two areas of functional recovery. Task-oriented robotic training in rehabilitation setting facilitates recovery not only of the motor function of the paretic arm but also of the cognitive abilities in stroke patients.

In early rehabilitation, Erigo training was safe and effective at improving orthostatic tolerance, posture and positive emotional reactions in both the ST and SCI patients (P< 0.05). In addition, advanced technologies were more effective at boosting the orthostatic tolerance in SCI patients, while they were more effective at increasing the dynamic balance and walking ability in ST patients (P< 0.05).

Remote patient monitoring is one of the most reliable choices for the availability of health care services for the elderly and/or chronically ill. Rehabilitation requires the exact and medically correct completion of physiotherapy activities. This paper presents BiomacVR, a virtual reality (VR)-based rehabilitation system that combines a VR physical training monitoring environment with upper limb rehabilitation technology for accurate interaction and increasing patients’ engagement in rehabilitation training. The system utilises a deep learning motion identification model called Convolutional Pose Machine (CPM) that uses a stacked hourglass network. The model is trained to precisely locate critical places in the human body using image sequences collected by depth sensors to identify correct and wrong human motions and to assess the effectiveness of physical training based on the scenarios presented. This paper presents the findings of the eight most-frequently used physical training exercise situations from post-stroke rehabilitation methodology. Depth sensors were able to accurately identify key parameters of the posture of a person performing different rehabilitation exercises. The average response time was 23 ms, which allows the system to be used in real-time applications. Furthermore, the skeleton features obtained by the system are useful for discriminating between healthy (normal) subjects and subjects suffering from lower back pain. Our results confirm that the proposed system with motion recognition methodology can be used to evaluate the quality of the physiotherapy exercises of the patient and monitor the progress of rehabilitation and assess its effectiveness.

No abstract