Currently submitted to: Journal of Medical Internet Research
Date Submitted: Sep 2, 2026
Open Peer Review Period: Sep 3, 2026 - Oct 29, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Effects of AI-HEALS Intervention on Medication Adherence in Young and Middle-Aged Patients with Hypertension: A Randomized Controlled Trial
ABSTRACT
Background:
Young and middle-aged patients with hypertension often exhibit low rates of disease awareness, treatment, and blood pressure control, with poor medication adherence further increasing their risk of cardiovascular events. Digital intelligent interventions grounded in behavioral change theories may offer a promising approach to improving medication-taking behaviors and enhancing treatment adherence.
Objective:
This study aimed to develop an Artificial Intelligence-based Healthcare, Education, Assistance, and Life-management System (AI-HEALS) intervention guided by the Behavior Change Wheel (BCW) theory and to evaluate its effects on medication adherence among young and middle-aged patients with hypertension.
Methods:
A single-center, randomized controlled trial was conducted. A total of 82 eligible patients aged 18–59 years were randomly assigned in a 1:1 ratio to the intervention group (AI-HEALS intervention) and control group (routine management). Medication adherence, medication literacy, medication adherence self-efficacy, medication beliefs, social support, health-related quality of life, and blood pressure were assessed at baseline and at week 12. All analyses were conducted according to the intention-to-treat principle, with multiple imputation used to address missing data. Statistical analyses were performed using SPSS version 26.0.
Results:
Baseline characteristics were comparable between the two groups (all P > 0.05). At week 12, the intervention group demonstrated significantly higher total medication adherence scores (t = −2.376, P = 0.020), as well as higher scores in the medication cooperation (t = −2.945, P = 0.004) and intention (t = −2.189, P = 0.032) dimensions, compared with the control group. The intervention group also had significantly higher critical medication literacy (t = −2.224, P = 0.029) and medication adherence self-efficacy (t = −2.165, P = 0.033). Systolic blood pressure decreased significantly within the intervention group (t = 2.865, P = 0.007), whereas no significant between-group differences were observed in diastolic blood pressure, medication beliefs, social support, or health-related quality of life (all P > 0.05). In the control group, only the regular medication dimension and family support showed modest improvements.
Conclusions:
The BCW theory-guided AI-HEALS intervention effectively improved medication adherence, critical medication literacy, and medication adherence self-efficacy among young and middle-aged patients with hypertension, and was associated with a significant within-group reduction in systolic blood pressure. These findings suggest that AI-HEALS may serve as a feasible digital self-management tool for improving medication-related behaviors in this population.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.