JMIR Publications

ABSTRACT

Background:

Home blood pressure (BP) monitoring is recommended for people with hypertension; however, meta-analyses have demonstrated that BP improvements are related to additional coaching support in combination with self-monitoring, with little or no effect of self-monitoring alone. High-contact coaching requires substantial resources and may be difficult to deliver via human coaching models.

Objective:

This observational study assessed changes in BP and body weight following participation in a fully digital program called Lark Hypertension Care with coaching powered by artificial intelligence (AI).

Methods:

Participants (N=1,140) had a baseline systolic (SBP) ≥120 mm Hg and had reached at least their third month in the program. The primary outcome was the change in SBP at three and six months, with secondary outcomes of change in body weight and associations of changes in SBP and body weight with participant demographics, characteristics, and program engagement.

Results:

By month three, there was a significant drop of 5.3 mm Hg (95% CI 4.2-6.3; p≤.0001) in mean SBP. BP did not change significantly (i.e., SBP drop maintained) from three to six months for participants who provided readings at both time points (p=.36). Half of the participants achieved a clinically meaningful drop of ≥5 mm Hg by month three (51.1%) and month six (50.2%). The magnitude of the drop depended on starting SBP, with participants classified as elevated lowering by M=1.2 mm Hg (SE=.7) by month three and M=-.6 mm Hg (SE=1.1) by month six, hypertension stage 1 by M=4.7 mm Hg (SE=.7) by month three and M=6.7 mm Hg (SE=1.1) by month six, and hypertension stage 2 by M=12.6 mm Hg (SE=1.2) by month three and M=13.8 mm Hg (SE=1.5) by month six. Starting SBP (β=1.11, p≤.0001), percent weight change (β=.36, p=.015), and initial BMI (β=-.56, p≤.001) were significantly associated with the likelihood of lowering SBP ≥5 mm Hg by month three. Percent weight change acted as a mediator of the relationship between program engagement and drop in SBP. The bootstrapped unstandardized indirect effect was .0023, 95% CI .0005-.00, p=.006.

Conclusions:

A hypertension care program with coaching powered by AI was associated with a clinically meaningful reduction in SBP following three and six months of program participation. Percent weight change was significantly associated with the likelihood of achieving a ≥5 mm Hg drop in SBP. An AI-powered solution offers a scalable, long-term approach to helping individuals with hypertension achieve clinically meaningful reductions in their BP and associated risk of cardiovascular disease and other serious adverse outcomes.