Key Takeaways
An AI voice agent helped older adults accurately self-report their blood pressure readings
Using the AI agent to contact patients slashed costs and improved blood pressure management
This technology could help improve remote patient care and outcomes
MONDAY, Sept. 8, 2025 (HealthDay News) — Older adults managing high blood pressure might just have one more tool in the toolbox.
A new study suggests that artificial intelligence (AI)-powered voice agents can help older adults manage their high blood pressure, potentially transforming how remote patient care is delivered.
These preliminary findings were presented Sunday during an American Heart Association meeting in Baltimore.
During the study, an AI voice agent prompted patients who were missing blood pressure data or whose most recent BP reading was not within the normal range of less than 120/80 mm Hg to report home blood pressure readings.
The research aimed to assess how adding AI into the clinical workflow could improve patients’ management of home blood pressure checks and identify those needing follow-up medical care.
The voice agent was designed to function like a health care professional, contacting patients, talking to them and asking them to provide blood pressure readings.
"Controlling blood pressure remains a cornerstone for improving cardiovascular outcomes for patients, however, capturing timely, compliant blood pressure readings remains a challenge, particularly for patients with limited access to care," said lead author Dr. Tina-Ann Kerr Thompson, a senior vice president at Emory Healthcare in Atlanta.
"In our study, we were able to improve accuracy of blood pressure measures and patient outcomes," she added in a news release.
Home monitoring is recommended for all adults with any level of high blood pressure, according to the AHA’s 2025 guideline on high blood pressure, released last month.
The 10-week study included 2,000 adults, most of whom were 65 or older. The AI agent placed calls to patients, who were asked to provide a recent blood pressure reading or take a live measurement during the call.
The agent, which spoke multiple languages including English and Spanish, automatically escalated the call to a nurse or medical assistant if a reading was outside a pre-set threshold or if the patient reported symptoms like dizziness or chest pain.
This automated process proved to be highly effective and efficient. By reducing the manual workload for clinical staff, the cost per reading was 88.7% lower than using human nurses for similar tasks.
In all, the voice agent successfully reached 85% of patients. Of those, 67% completed the call, and 60% took a compliant blood pressure reading while on the phone. This led to a notable improvement in blood pressure control, while reaching more patients and closing gaps in care.
Patient satisfaction with the AI agent was also remarkably high. At the end of each call, patients were asked to rate their experience on a scale of 1 to 10. The average score was over 9, indicating a very positive experience, results showed.
“We were surprised by the high patient satisfaction scores after interacting with artificial intelligence-based voice agents,” Thompson said. “We are excited for what that means for the future, since patient engagement and satisfaction are so critical to health care outcomes.”
An American Heart Association volunteer expert, Dr. Eugene Yang, a clinical professor in the cardiology division at the University of Washington School of Medicine in Seattle, called the findings “game-changing,” noting the potential for new technologies to address barriers to care.
“Accurate blood pressure readings are essential to improving control, and new approaches can help make that possible,” he said in a news release. “Breakthrough AI technologies like this could transform how we manage blood pressure by reaching patients wherever they are and addressing critical barriers, such as limited access to care and gaps in patient support.”
The study had some limitations. The AI calls were not directly compared to human-only calls, as it was not feasible to make enough human calls to complete the study, researchers said.
Findings presented at medical meetings should be considered preliminary until published in a peer-reviewed journal.
More information
Tulane University has more on strategies for effective communication in health care.
SOURCE: American Heart Association, news release, Sept. 7, 2025
What This Means For You
If you or a loved one are managing high blood pressure, new AI-powered tools might soon become a valuable part of your care team, making it easier to monitor your health from home.
Commented