Early warning systems for natural disasters have undoubtedly saved countless lives. Detectors that monitor signs of impending earthquakes, hurricanes, and tornadoes, among others, provide crucial hours — sometimes days — for us to take evasive action.
What if we could do the same thing for heart attacks? A group of French researchers working with some U.S. colleagues, have designed an Artificial Intelligence (AI) tool that could help do just that, they report in the European Heart Journal.
Early Detection for Heart Attacks
Cardiac events contribute to over 5 million deaths a year. They often strike like a bolt from the blue — sometimes killing people without warning signs and no known history of heart disease.
To look for hidden patterns that might provide potential heart attack victims a heads up, the researchers first investigated electrocardiograms data from over 240,000 patients. They essentially looked at several million hours of heartbeats.
“By analyzing their electrical signal for 24 hours, we realized that we could identify the subjects susceptible of developing a serious heart arrhythmia within the next two weeks,” Laurent Fiorina, an author of the study and researcher at the Paris Cardiovascular Research Centre (PARCC), said in a press release. “If left untreated, this type of arrhythmia can progress towards a fatal cardiac arrest.”
They probed the data with AI tools and identified weak signals that could precede arrhythmia. Based on that information, the research team developed an AI algorithm that could identify people at risk of any arrhythmia serious enough to trigger cardiac arrest. They based their tool on an artificial neural network that simulates how the brain talks to the heart.
Read More: Repairing the Damage After a Heart Attack
Potentially Life-Saving Predictions
The tool could predict such events within two weeks in over 70 percent of cases. The monitoring method could potentially change how heart disease is detected and treated.
“Until now we’d been trying to identify patients at risk over the medium and long term, but were incapable of predicting what could happen in the minutes, hours or days that precede a cardiac arrest,” Eloi Marijon, research director at PARCC and an author of the study, said in a press release. “Now, thanks to artificial intelligence, we can predict these events in the very short term and potentially take action before it’s too late.”
The team will continue to refine the tool, then test it in clinical trials to ensure its accuracy. If it pasts those tests, we’ll have the equivalent of a warning siren that tells us to seek help to prevent a heart attack.
Read More: Why Are Heart Attacks More Frequent In December And January?
Article Sources
Our writers at Discovermagazine.com use peer-reviewed studies and high-quality sources for our articles, and our editors review for scientific accuracy and editorial standards. Review the sources used below for this article:
Before joining Discover Magazine, Paul Smaglik spent over 20 years as a science journalist, specializing in U.S. life science policy and global scientific career issues. He began his career in newspapers, but switched to scientific magazines. His work has appeared in publications including Science News, Science, Nature, and Scientific American.
