JMIR Publications

ABSTRACT

Background:

Hypertension remains a major global health challenge, significantly increasing cardiovascular and all-cause mortality risks. While exercise therapy is effective, conventional approaches face limitations in accessibility and personalization, compromising adherence. Artificial intelligence (AI)-assisted remote rehabilitation enables real-time monitoring and personalized guidance, offering a promising alternative. Nevertheless, its clinical benefits and applicability require further systematic validation.

Objective:

This study aimed to evaluate the effects of artificial intelligence-assisted tele-rehabilitation training on exercise capacity and related health outcomes in patients with hypertension by a randomized controlled trial.

Methods:

This study was a prospective, dual-arm, open-label, randomized clinical controlled trial. 62 patients with hypertension were randomly assigned to the intervention group or the control group (1:1). The intervention group received AI remote rehabilitation intervention on the basis of routine health education, while the control group received hypertension health education and offline routine exercise guidance. The exercise program consisted of warm-up, cardiorespiratory endurance, strength resistance, balance, flexibility training, and cool-down. Each session lasted 30 to 50 minutes and was conducted at least three times per week over an eight-week period. At baseline and after 8 weeks of intervention, the 6 Minute Walk Test（6MWT）, Cardiopulmonary Exercise Test（CPET）, International Physical Activity Questionnaire（IPAQ）, Short-Form Health Survey 12（SF-12）, Patient Health Questionnaire-9（PHQ-9）, Generalized Anxiety Disorder-7（GAD-7）, exercise self-efficacy scale, blood pressure, body weight, handgrip strength and other health-related indicators were evaluated in the two groups.

Results:

After 8 weeks of intervention, the 6MWD (95%CI: -146.086,-11.057, P=.024), systolic blood pressure reduction (95%CI: 0.107,8.467, P=.045), IPAQ (95%CI: -1521.244,-357.589, P=.002) and exercise self-efficacy scores (95%CI: -29.456,-13.287, P<.001) of the intervention group were significantly better than those of the control group. There were significant differences in the total exercise time (95%CI: -168.950，-44.371, P=.003) and Peak oxygen uptake (Peak VO2) (95%CI: -8.429，-0.055, P=.047) between the two groups. The exercise capacity of the intervention group were better than those of the control group.

Conclusions:

Compared with conventional exercise rehabilitation, AI-assisted remote rehabilitation training was found to yield superior therapeutic outcomes in patients with hypertension. It significantly improves exercise capacity, promotes the development of regular physical activity habits, and supports positive lifestyle changes. This approach provides practical guidance for the development of effective real-time home-based exercise interventions for hypertensive individuals. Clinical Trial: The study was registered with the Chinese Clinical Trial Registry (registration number：ChiCTR2300076451).