First-of-its-kind tech accurately predicts if – and when – someone will suffer cardiac arrest

YouTube video

Scientists say the deep-learning system, called SSCAR, is ‘significantly’ more accurate than doctors’ predictions.

BALTIMORE — Groundbreaking technology can now predict if — and when — someone will suffer a potentially fatal cardiac arrest. The first-of-its-kind survival predictor can detect patterns in a patient’s heart invisible to the naked eye.

Scientists at Johns Hopkins University say that the new artificial intelligence-based approach can predict “significantly more accurately” than a doctor if and when a patient could die of cardiac arrest. The technology, built on raw images of patient’s hearts and patient backgrounds, stands to revolutionize clinical decision making and increase survival from sudden and lethal cardiac arrhythmias, one of medicine’s deadliest and most puzzling conditions.

The deep learning technology is called Survival Study of Cardiac Arrhythmia Risk (SSCAR). The name alludes to cardiac scarring caused by heart disease that often results in lethal arrhythmias, and the key to the algorithm’s predictions.

“Sudden cardiac death caused by arrhythmia accounts for as many as 20 percent of all deaths worldwide and we know little about why it’s happening or how to tell who’s at risk,” says study senior author Natalia Trayanova, a professor of biomedical engineering and medicine, in a statement. “There are patients who may be at low risk of sudden cardiac death getting defibrillators that they might not need and then there are high-risk patients that aren’t getting the treatment they need and could die in the prime of their life. What our algorithm can do is determine who is at risk for cardiac death and when it will occur, allowing doctors to decide exactly what needs to be done.”

The team is the first to use neural networks to build a personalized survival assessment for each patient with heart disease. Trayanova says the risk measures provide with high accuracy the chance for a sudden cardiac death over 10 years, and when it’s most likely to happen.

MRI images - heart arrhythmia
A first-of-its-kind algorithm, using raw MRI images, can predict if and when a patient will have a lethal episode of heart arrhythmia. It detected high risk in the heart circled in red. (Credit: JHU)

The team used contrast-enhanced cardiac images that visualize scar distribution from hundreds of real patients at Johns Hopkins Hospital with cardiac scarring. This trained an algorithm to detect patterns and relationships not visible to the naked eye.

Current clinical cardiac image analysis extracts only simple scar features such as volume and mass, severely underutilizing what’s demonstrated in the work to be critical data. The images carry critical information that doctors haven’t been able to access.

“This scarring can be distributed in different ways and it says something about a patient’s chance for survival. There is information hidden in it,” says first author Dan Popescu, a former Johns Hopkins doctoral student.

The team trained a second neural network to learn from 10 years of standard clinical patient data. It analyzed 22 factors, such as patients’ age, weight, race and prescription drug use.

The algorithms’ predictions were not only significantly more accurate on every measure than doctors, they were validated in tests with an independent patient group from 60 health centers around the United States, with different cardiac histories and different imaging data. This suggests the platform could be adopted anywhere.

“This has the potential to significantly shape clinical decision-making regarding arrhythmia risk and represents an essential step towards bringing patient trajectory prognostication into the age of artificial intelligence,” says Trayanova.. “It epitomizes the trend of merging artificial intelligence, engineering, and medicine as the future of healthcare.”

She says the team is now working to build algorithms to detect other cardiac diseases. They believe the deep-learning concept could be developed for other fields of medicine that rely on visual diagnosis.

The findings are published in the journal Nature Cardiovascular Research.

South West News Service writer Stephen Beech contributed to this report.