Mayo initiative shows AI can detect irregular heart rhythms
Atrial fibrillation is difficult to diagnose, especially if the heart is in normal rhythm during a test. But artificial intelligence is able to detect recent AF that occurred without symptoms or that is impending.
Atrial fibrillation is difficult to diagnose, especially if the heart is in normal rhythm during a test. But artificial intelligence is able to detect recent AF that occurred without symptoms or that is impending.
Leveraging a convolutional neural network, Mayo Clinic researchers have developed an AI-enabled electrocardiogram to detect the electrocardiographic signature of AF present during normal sinus rhythm using standard 10-second, 12-lead EKGs.
A study, published in The Lancet, found that the AI-enabled EKG correctly identified the subtle patterns of AF—undetectable without the use of the technology—with 90 percent accuracy.
“An EKG will always show the heart’s electrical activity at the time of the test, but this is like looking at the ocean now and being able to tell that there were big waves yesterday,” says senior author Paul Friedman, MD, chair of the Department of Cardiovascular Medicine at Mayo Clinic. “AI can provide powerful information about the invisible electrical signals that our bodies give off with each heartbeat—signals that have been hidden in plain sight."
Also See: Tech proves accurate in identifying patients with irregular heartbeat
Researchers trained the AI using about 450,000 EKGs from the Mayo Clinic digital data, and then tested it on normal-rhythm EKGs from 36,280 patients—of whom 3,051 were known to have AF.
According to Friedman, who is a cardiac electrophysiologist, the technology can be processed using a smartphone or watch, which could make the AI-enabled EKG widely accessible.
A commentary accompanying the study in The Lancet, notes that silent or undetected AF is common, and the few screening methods available are demanding in terms of time and resources.
“Rather than finding the needle in the haystack by prolonged monitoring, authors basically suggest that AI will be able to judge by looking at the haystack if it has a needle hidden in it,” wrote Jeroen Hendriks, of the University of Adelaide in Australia, and Larissa Fabritz, MD, of the University of Birmingham in the UK.
Leveraging a convolutional neural network, Mayo Clinic researchers have developed an AI-enabled electrocardiogram to detect the electrocardiographic signature of AF present during normal sinus rhythm using standard 10-second, 12-lead EKGs.
A study, published in The Lancet, found that the AI-enabled EKG correctly identified the subtle patterns of AF—undetectable without the use of the technology—with 90 percent accuracy.
“An EKG will always show the heart’s electrical activity at the time of the test, but this is like looking at the ocean now and being able to tell that there were big waves yesterday,” says senior author Paul Friedman, MD, chair of the Department of Cardiovascular Medicine at Mayo Clinic. “AI can provide powerful information about the invisible electrical signals that our bodies give off with each heartbeat—signals that have been hidden in plain sight."
Also See: Tech proves accurate in identifying patients with irregular heartbeat
Researchers trained the AI using about 450,000 EKGs from the Mayo Clinic digital data, and then tested it on normal-rhythm EKGs from 36,280 patients—of whom 3,051 were known to have AF.
According to Friedman, who is a cardiac electrophysiologist, the technology can be processed using a smartphone or watch, which could make the AI-enabled EKG widely accessible.
A commentary accompanying the study in The Lancet, notes that silent or undetected AF is common, and the few screening methods available are demanding in terms of time and resources.
“Rather than finding the needle in the haystack by prolonged monitoring, authors basically suggest that AI will be able to judge by looking at the haystack if it has a needle hidden in it,” wrote Jeroen Hendriks, of the University of Adelaide in Australia, and Larissa Fabritz, MD, of the University of Birmingham in the UK.
More for you
Loading data for hdm_tax_topic #better-outcomes...