Artificial intelligence can better predict future risk for heart attack patients

A landmark study led by University experts has shown that artificial intelligence can better predict how doctors should treat patients following a heart attack.

The study, conducted by an international team of researchers, led by the University of Leicester’s Honorary fellow, Doctor Florian Wenzl working closely with Professor David Adlam, both from the Department of Cardiovascular Sciences, has been published in The Lancet Digital Health.

Doctors caring for patients with the most common form of heart attack caused by a partial blockage, known as non-ST-elevation acute coronary syndrome (NSTE-ACS)—typically rely on the GRACE score to estimate a patient’s risk of dying or having another cardiovascular event. It is used to guide treatment decisions but has long been recognized as being unable to capture the full complexity of each patient.

However, the newly created GRACE 3.0 score is an advanced, AI-based risk assessment tool for patients with acute coronary syndromes. It is able to predict the probability of in-hospital and 1-year mortality by looking at nine widely available variables: age, sex, heart rate, systolic blood pressure, troponin level, ST-deviation, creatinine level, cardiac arrest, and heart failure symptoms.

Dr. Wenzl said, “GRACE 3.0 represents the next evolution of the GRACE score, bringing AI methods into one of the most widely used risk tools in cardiology. It was trained and externally validated on data from hundreds of thousands of patients from multiple countries, which gives it a very strong evidence base. Unlike traditional risk scores, GRACE 3.0 captures complex and non-linear relationships that conventional approaches often miss.”

“Another key improvement is that GRACE 3.0 is sex-specific and tailored precisely for patients with a partial blockage in their coronary artery, rather than being applied more broadly across those with other types of heart attacks caused by complete blockage in their coronary artery.

“In addition, the GRACE 3.0 score enables physicians to better predict whether or not patients will benefit from early invasive treatment such as angioplasty (to open the artery with a balloon and typically place a stent).”

Professor Adlam, an interventional cardiologist at the University, working within the Leicester NIHR Biomedical Research Center, added, “This newly developed score, using artificial intelligence, helps tailor treatment for patients by better detecting future risk and therefore guiding which health interventions they would benefit from.

“The GRACE 3.0 score is now increasingly being incorporated into international guidelines and may inform the design of future clinical trials.”