This paper has been accepted and is currently in production.
It will appear shortly on 10.2196/77896
The final accepted version (not copyedited yet) is in this tab.
Patient Engagement With Artificial Intelligence–Enabled Tailored Text Messaging for Cardiovascular Health Among Adults With Cardiovascular Risk Factors: Secondary Analysis of a Pilot Randomized Controlled Trial
ABSTRACT
Background:
Cardiovascular (CV) disease risk factors disproportionately affect underserved populations, emphasizing the need for innovative self-management support. This pilot randomized trial evaluated AI-enabled text messaging interventions based on the American Heart Association's Life’s Essential 8 (LE8) framework across three Federally Qualified Health Systems.
Objective:
To assess participant engagement with AI-enabled text messaging based on a variety of factors including language, timing of messages, and message topic.
Methods:
Participants were randomized into three groups: generic messages, AI chatbot-tailored messages with behavioral nudges, and AI chatbot messages supplemented by pharmacist engagement.
Results:
Preliminary findings showed higher engagement with lifestyle topics (diet, physical activity, weight management) compared to health-related content (blood pressure, blood glucose, cholesterol and medicine), with no significant differences between English- and Spanish-speaking participants or across patients with different CV diseases. A significant difference in the interaction, measured as the number of incoming text message patient responses was observed between weekdays and weekends (U = 243, p < 0.01). The AI chatbot (without a pharmacist) arm demonstrated significantly higher response rates than the generic message group (p=0.0102), highlighting the potential of conversational AI to enhance patient interaction.
Conclusions:
These results underscore the promise of AI-driven messaging systems in addressing CV disease risk factors in underserved populations and suggest that future research should focus on personalization, and optimizing message delivery timing. Clinical Trial: ClinicalTrials.gov ID: NCT06324981
Citation
The author of this paper has made a PDF available, but requires the user to login, or create an account.
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.