CONFERENCE UPDATE: AAN 2025

SmartRehab transforms stroke recovery through AI-powered telerehabilitation

09 Jun 2025

Stroke is one of the leading causes of long-term disability worldwide, and effective post-stroke rehabilitation plays a critical role in improving functional outcomes and quality of life for survivors.1 Yet, conventional in-person rehabilitation faces numerous challenges, including therapist shortages, access barriers, and increasing healthcare system burdens.1 In response to these issues, researchers have turned to digital innovations, with telerehabilitation emerging as a promising solution to bridge these gaps and provide more accessible care.1 At the AAN Annual Meeting 2025, Dr. Faddi Saleh Velez from the University of Oklahoma in the United States, presented a recent study that examined the efficacy, usability, and feasibility of the SmartRehab application, an automated telerehabilitation platform that utilizes artificial intelligence (AI) and computer vision to support remote stroke recovery.1

In this international multicenter study, participants received a four-week automated rehabilitation program prescribed by their therapists using the SmartRehab application.1 SmartRehab provides personalized, therapist-guided sessions that patients can access at home.1 The system uses a computer vision-based movement tracking algorithm to analyze patient movements in real time, offering precise feedback, assessments, and dynamic session adjustments.1 Motor improvements were measured using the Fugl-Meyer Assessment (FMA) for the upper and lower extremities, while user satisfaction was evaluated with the Telehealth Usability Questionnaire (TUQ).1

The study assessed SmartRehab’s feasibility and efficacy in post-stroke patients with motor disabilities.1 Early results from 30 subjects across seven countries and eight hospitals were promising.1 Among them, 15 stroke survivors completed the full four-week telerehabilitation program (mean age 57.6 ± 16.97; 75% male).1 Preliminary analysis of 11 participants with complete FMA revealed a statistically significant improvement in upper extremity motor function, with a mean change of -10.8 ± 6.8 points from baseline to follow-up (p<0.001), reinforcing its potential as a viable rehabilitation tool.1 Additionally, there was a notable trend toward improvement in lower extremity function (mean change: -4.571 ± 4.9), which approached statistical significance (p=0.052).1

Stroke survivors rated the program highly on the TUQ, with an average score of 5.87 ± 1.1 on a 7-point scale, indicating strong user acceptance.1 Therapists also reported high satisfaction, emphasizing the system’s ease of use and the value the platform provided to patients.1 However, adherence rates varied considerably across participating countries, ranging from 19% to 95% with an average of 48%, with lower compliance attributed to technological barriers and varying levels of digital literacy among patients​.1 Despite these encouraging findings, the study also revealed barriers related to technology access and digital literacy, which may affect program adherence.1 The researchers emphasized the importance of addressing these issues to ensure equitable access and optimize the benefits of telerehabilitation.1

In conclusion, the SmartRehab application demonstrates both feasibility and efficacy as an AI-powered telerehabilitation platform for post-stroke recovery, leading to significant improvements in upper extremity motor function.1 Stroke survivors reported high satisfaction, as reflected in favorable TUQ scores, while therapists noted its ease of use and clinical value.1 With continued efforts to address technological and digital literacy barriers, SmartRehab holds strong potential as an accessible and effective solution for stroke rehabilitation.1


References
  1. Velez FS, et al. SmartRehab: enhancing stroke recovery through automated telerehabilitation. Presented at American Academy of Neurology (AAN) Annual Meeting 2025; April 5-9, 2025.
TELEREHABILITATION
POST-STROKE RECOVERY
ARTIFICIAL INTELLIGENCE
REMOTE
MOTOR DISABILITY


Related Articles

AI-created digital twins of vertebra predict the vertebral fracture risk IN SM patients

It is projected that there will be 1.9 million new cancer diagnoses and over 600,000 cancer deaths in 2022 in the United States alone.1 Spine is the most common site for bone metastasis; up to 70% of cancer patients could experience spinal metastasis (SM) and about 20% of them become symptomatic, causing considerable pain and morbidity.2 Most common regions for SM are dorsal (45%), lumbar (17%), cervical (14%), and dorsolumbar (10%).3 Vertebral fractures (VFs) are the common complications of SM, with an estimation of 30% of patients developing VFs that mostly require surgery.4 Tumor lesions and some treatments for cancer can lead to loss of bone tissue, thus increasing the risk of VFs.5 Hence, it is imperative to predict the VF risk in SM patients, so that well-informed interventions can be designed.5 Factors influencing VFs include both the macro- and micro-structure of the vertebra, especially of the trabecula.5 In-vitro methods are used to study the biomechanical forces that alter the vertebral shape, but they cannot accurately measure in-vivo stresses that damage its microstructure.5 The development of computational modeling has made it a compelling tool for measuring these in-vivo stressors.5 A recent study by Ahmadian et al was to assess the feasibility of the artificial intelligence (AI)-assisted framework to create ‘digital twins’ of the human vertebra, termed ReconGAN, to predict the VF risk in both osteolytic and osteoblastic metastatic tumors.5

08 Jul 2022