Researchers at Johns Hopkins University have developed a groundbreaking artificial intelligence (AI) model that can predict sudden cardiac death with remarkable accuracy, offering new hope in preventing this silent killer.
The AI system, called Multimodal AI for Ventricular Arrhythmia Risk Stratification (MAARS), analyzes detailed heart images and patient health records to detect hidden signs of heart problems that doctors might miss. This means it can identify people who are at high risk of sudden cardiac death much better than current methods.
“We have patients dying in the prime of their life because they aren’t protected, and others who are putting up with defibrillators for the rest of their lives with no benefit,” said Natalia Trayanova, the senior author of the study. “We have the ability to predict with very high accuracy whether a patient is at very high risk for sudden cardiac death or not.”
Sudden cardiac death is a leading cause of death, especially among young people with heart conditions like hypertrophic cardiomyopathy—an inherited disease that affects the heart muscle. Until now, doctors have struggled to predict who is at risk, with current guidelines being accurate only about 50% of the time.
The MAARS model, however, has shown an overall accuracy of 89%, and it’s even more accurate—93%—for people aged 40 to 60, who are at the greatest risk.
“Our study demonstrates that the AI model significantly enhances our ability to predict those at highest risk compared to our current algorithms,” said cardiologist Jonathan Chrispin, one of the researchers. “It has the power to transform clinical care.”
The AI works by looking for patterns of scarring in heart MRI scans—something that is difficult for doctors to interpret on their own. By finding these hidden patterns, the AI can provide early warnings and potentially save lives.
The research team plans to test the AI model on more patients and expand its use to other heart diseases, aiming to make this life-saving technology available to more people around the world.
