About 10% of individuals with hypertension exhibit normal blood pressure readings during clinical visits, a condition known as masked hypertension. Researchers at the University of Arkansas have developed a new artificial intelligence tool designed to identify this hidden form of high blood pressure. Led by associate professor of chemical engineering William J. Richardson, the study introduces a machine learning model that analyzes patterns in patients’ blood pressure data collected outside the clinic, such as through home monitoring or wearable devices. By detecting subtle trends and anomalies that may be missed during brief office visits, the AI system can flag cases of masked hypertension earlier and more accurately. This advancement could significantly improve early diagnosis and treatment, potentially reducing the risk of heart attacks, strokes, and other complications associated with untreated hypertension. The condition contributes to approximately 10 million deaths globally each year, making early detection a critical public health priority. The team’s approach leverages real-world data to enhance diagnostic precision, offering a promising tool for clinicians and patients alike in the ongoing effort to combat cardiovascular disease.