About 10% of people with hypertension have normal blood pressure readings at the doctor’s office. Now researchers at the University of Arkansas have developed an artificial-intelligence diagnostic tool to detect this condition, known as masked hypertension. The work, led by associate professor of chemical engineering William J. Richardson, could help more people get treatment for hypertension, a condition that kills 10 million people around the world each year.

Today, masked hypertension is detected with ambulatory blood pressure monitors, which take readings as a patient goes about their normal day. The equipment, however, can be cumbersome and expensive, and it may not be available in low-income countries. Doctors may also not even consider an ambulatory monitor for patients with masked hypertension who have normal blood pressure readings during an exam.