Community-based digitally enabled blood pressure monitoring and AI support resulted in approximately 25% of consistently monitored adult participants achieving controlled blood pressure at one year.
Observational (n=2,000)
Does a community-based, digitally enabled blood pressure monitoring model with AI support improve blood pressure control in adults with hypertension?
A community-based digital health platform combining self-monitoring, health coaches, and AI support showed encouraging trends in improving blood pressure control among adults with hypertension.
Objective: To describe the use and effectiveness of a community-based, digitally enabled blood pressure monitoring model and follow-up. Design and method: This was a retrospective study of adult members with hypertension enrolled on the mDoc digital health platform. Data were extracted from community hubs, health coach records, and the complete health dashboard, including the health passport and AI–member conversation logs. Self-reported blood pressure measurements and conversational data were analyzed to identify abnormal readings and longitudinal trends. Descriptive analyses were conducted to assess observed trends and blood pressure control patterns in the months following the detection of elevated blood pressure. Results: At the beginning of 2025, over 2,000 community members were identified with elevated blood pressure, either during their first visit to the community hub or through self-monitoring. Following this initial finding, participants received ongoing support from health coaches, with some also engaging in conversations with our AI model, Kem. By the end of the year, we observed that about one-quarter of those who were consistently monitored and followed up achieved controlled blood pressure readings. While this data is not intended to be presented as statistically significant, it highlights an encouraging trend. The improvement seen among a meaningful portion of participants suggests that consistent follow-up, personalized guidance, and accessible digital support may play an important role in blood pressure management. These early observations point to strong future potentials. They highlight the importance of further discussion, deeper review, and continued investment in community-based monitoring and supportive technologies as potential tools for improving long-term cardiovascular health outcomes. Conclusions: Combining self-monitoring, community-based blood pressure monitoring, and AI has the potential to improve global blood pressure management beyond traditional clinic-based care. This integrated approach may enhance access and long-term control, but it requires extensive comparative studies with traditional clinical care to assess its efficiency and sustainability.
Anasiudu et al. (Fri,) conducted a observational in Hypertension (n=2,000). Community-based digitally enabled blood pressure monitoring and AI-enabled care was evaluated on Controlled blood pressure readings. Community-based digitally enabled blood pressure monitoring and AI support resulted in approximately 25% of consistently monitored adult participants achieving controlled blood pressure at one year.