JMIR Publications

ABSTRACT

Background:

Referred to as the "silent killer," elevated blood pressure often goes unnoticed due to the absence of apparent symptoms, resulting in cumulative harm over time. While various health conditions contribute to hypertension, they collectively account for a minority of cases. Chronic stress has been identified as a significant factor in increased blood pressure, and the heterogeneous nature of stress responses makes it challenging to identify specific deleterious behaviors through traditional clinical interviews.

Objective:

We aim to leverage machine learning algorithms for real-time predictions of stress-induced blood pressure spikes using consumer wearable devices such as FitBit, providing actionable insights to both patients and clinicians to improve diagnostics and enable proactive health monitoring.

Methods:

The study proposes the development of machine learning algorithms to analyze biosignals obtained from these wearable devices, aiming to make real-time predictions about blood pressure spikes.

Results:

We have developed the core study application, named CardioMate. CardioMate will be used to remind participants to initiate blood pressure readings using an Omron HeartGuide wearable monitor. The project described is supported as a pilot project from the Robert C. Perry Fund of the Hawai‘i Community Foundation. This protocol was approved by the University of Hawai‘i Institutional Review Board (IRB) under protocol #2023-00130.

Conclusions:

Personalized machine learning when applied to biosignals is a promising approach to providing the mobile sensing backend support for real-time digital health interventions for chronic stress and its corresponding symptoms.