Using artificial intelligence to analyze patterns from a portable cuff-based blood pressure monitor and a wrist-worn fitness tracker may help identify adults with stage 2 high blood pressure who are at increased risk of a hypertensive crisis up to three days before it occurs, according to preliminary research presented at the American Heart Association’s Scientific Sessions 2026.
A hypertensive crisis is a medical emergency characterized by blood pressure readings higher than 180/120 mm Hg accompanied by acute end-organ damage, which can lead to stroke, heart attack, kidney damage, aortic dissection or pulmonary edema. The study, which followed 4,190 adults with stage 2 hypertension, found that an AI tool could distinguish patients at higher versus lower risk of a crisis up to 72 hours in advance. Among participants who received a positive alert, about 32% experienced a hypertensive crisis, while 97.4% of those without an alert remained crisis-free.
The findings carry significant implications for hypertension management, which has traditionally relied on single-point-in-time measurements during office visits. According to the 2025 High Blood Pressure Guideline, nearly half of U.S. adults have high blood pressure, and it is the number one modifiable risk factor for heart attack, stroke and heart failure. Continuous monitoring combined with AI could provide clinicians with actionable early warnings, allowing for timely medication adjustments and potentially preventing emergencies.
“If we are able to recognize an increased risk of a hypertensive crisis days before it occurs, we have an opportunity to provide earlier care to help reduce the risk of the serious complications,” said lead author Waleed Razzaq Chaudhry, M.D., an internal medicine resident at the University of Maryland Capital Region Medical Center. The study showed that when physicians received an alert and adjusted medications within 24 hours, hypertensive crises were about 61% lower and emergency department visits were about 45% lower compared to people who did not receive timely alert-triggered intervention.
Specifically, abnormal blood pressure patterns during sleep—where blood pressure did not decrease as it normally should—were associated with nearly five times the odds of an upcoming crisis. A sharp rise in blood pressure after waking (an increase of more than 35 mm Hg compared to nighttime levels) was linked to nearly four times the odds. These patterns, captured by the portable monitor and analyzed alongside heart rate and heart rate variability from the wrist-worn device, formed the basis of the AI predictions.
However, the research is preliminary and has limitations. All participants were adults receiving care at a single hospital in Sindh, Pakistan, and the findings need to be tested in more diverse groups and healthcare settings. Moreover, a 2025 American Heart Association scientific statement on cuffless devices emphasized that more research and standardized testing are needed before such technologies can guide patient care. The Association recommends an automatic, cuff-style, upper arm monitor, and a list of validated blood pressure devices is available at validatebp.org.
“These findings suggest that continuous blood pressure monitoring can help detect these blood pressure changes earlier, which may give patients and healthcare professionals more time to act before it turns into an emergency,” Chaudhry said. The study underscores the growing potential for digital health technologies to complement, not replace, clinical decision-making in hypertension care.
