discoveries magazine

A Better Model of Heart Disease Prediction

A flat 2-dimensional illustration of a heart.

Predicting and diagnosing heart conditions can be greatly improved by applying artificial intelligence tools, according to rigorous Cedars-Sinai studies.

In the first blinded randomized clinical trial of artificial intelligence in cardiology, Smidt Heart Institute and Artificial Intelligence in Medicine researchers led by cardiologist David Ouyang, MD, found that AI is more successful in assessing cardiac function than echocardiogram assessments made by sonographers

Investigators led by Damini Dey, PhD, professor of Biomedical Sciences, developed an AI-based tool that measures plaque buildup in the coronary arteries from a standard CT test. They also matched results with images taken by two invasive tests considered to be highly accurate in assessing coronary artery plaque and narrowing: intravascular ultrasound and catheter-based coronary angiography. The investigators discovered that measurements made by the AI algorithm from CTA images accurately predicted heart attack risk within five years.

Read more about the promise of integrating AI into medicine in our special report: 

The Human Factor of Artificial Intelligence

Sumeet Chugh, MD, has spent much of his career studying the most lethal of heart disease problems: sudden cardiac arrest. Dr. Chugh—director of the Center for Cardiac Arrest Prevention, the Pauline and Harold Price Chair in Cardiac Electrophysiology Research, and director of Artificial Intelligence in Medicine—and his team working in the community for more than two decades discovered a novel scoring system that sums up a person’s risk of ventricular fibrillation. They have now embarked on the Observational Study of Cardiac Arrest Risk, or OSCAR, that will study nearly 400,000 Los Angeles County residents. These large collections of clinical data are being analyzed with AI tools to validate and improve the ability to predict who is at risk of a fatal cardiac arrest. 

"By the time someone collapses from cardiac arrest and 911 has been dialed, it is too late for 90% of people," Dr. Chugh says. "The way we predict and prevent cardiac arrest now is not sustainable. AI can help us build a better prediction model that will quickly get interventions to the people who really need them and save lives."