JMIR Publications

ABSTRACT

Background:

Home blood pressure (BP) monitoring in conjunction with lifestyle coaching is effective in managing hypertension (HTN) and reducing cardiovascular risk. However, traditional manual lifestyle coaching models significantly limit availability due to high operating costs and personnel requirements. Furthermore, the lack of patient lifestyle monitoring and time constraints experienced by clinicians can prevent personalized counsel on lifestyle modifications for patients.

Objective:

This study aims to assess the effectiveness of a fully digital, autonomous, and artificial intelligence (AI)-based lifestyle coaching program on achieving BP control among adults with HTN.

Methods:

Participants were enrolled in a single-arm nonrandomized trial in which they were provided with a BP monitor and wearable activity tracker. Data was collected from these devices and a questionnaire mobile application and used to train personalized machine learning (ML) models that enabled precision lifestyle coaching delivered to participants via SMS and a mobile application. The primary outcomes included: 1.) The change in systolic and diastolic BP from baseline to 12 and 24 weeks. 2.) The percent change of participants in the controlled, Stage 1, and Stage 2 HTN categories from baseline to 12 and 24 weeks. Secondary outcomes included: 1.) The participant engagement rate as measured by the consistency of data collection. 2.) The number of manual clinician outreaches based on the escalation rules set for the study.

Results:

141 participants were monitored over 24 weeks. At 12 weeks, systolic and diastolic BP decreased by 5.6 mmHg (P<.001; 95% CI -7.1 to -4.2) and 3.8 mmHg (P<.001; 95% CI -4.7 to -2.8), respectively. Particularly, for participants starting with Stage 2 HTN, systolic and diastolic BP decreased by 9.6 mmHg (P<.001; 95% CI -12.2 to -6.9) and 5.7 mmHg (P<.001; 95% CI -7.6 to -3.9), respectively. At 24 weeks, systolic and diastolic BP decreased by 8.1 mmHg (P<.001; 95% CI -10.1 to -6.1) and 5.1 mmHg (P<.001; 95% CI -6.2 to -3.9), respectively. For participants starting with Stage 2 HTN, systolic and diastolic BP decreased by 14.2 mmHg (P<.001; 95% CI -17.7 to -10.7) and 8.1 mmHg (P<.001; 95% CI -10.4 to -5.7), respectively, at 24 weeks. The percentage of participants with controlled BP increased by 17% (P<.001) and 26% (P<.001) from baseline to 12 and 24 weeks, respectively. The percentage of participants with Stage 2 HTN decreased by 25% (P<.001) and 26% (P<.001) from baseline to 12 and 24 weeks, respectively. The average weekly participant engagement rate was 92% and only 5.9% of participants required manual outreach over 24 weeks.

Conclusions:

The study demonstrates the potential of fully digital, autonomous, and AI-based lifestyle coaching to achieve significant BP improvements and high engagement for patients with HTN, while significantly reducing the workload on clinicians and health coaches.