AI analyzes world’s largest heart attack data sets—and reveals new treatment methods

A landmark international study led by the University of Zurich has shown that artificial intelligence can assess patient risk for the most common type of heart attack more accurately than existing methods. This could enable doctors to guide more personalized treatment decisions for patients.

Doctors caring for patients with the most common form of heart attack—the so-called non-ST-elevation acute coronary syndrome (NSTE-ACS)—have so far relied on a standardized scoring system. Using the GRACE score, they can estimate risk and determine the optimal timing for catheter-based treatment. This score is widely used and increasingly integrated into international clinical guidelines. However, it has long been recognized that existing tools cannot always capture the full complexity of these patients.

Data from over 600,000 patients

A new study published in The Lancet Digital Health now suggests that many patients may need to be re-classified, with important implications for how heart attacks are treated worldwide. In the largest study on risk modeling in NSTE-ACS to date, an international research team led by the University of Zurich (UZH) analyzed health data from more than 600,000 patients across 10 countries.

Sign up for Blog Updates