Researchers from Mayo Clinic and AliveCor Inc. have been using artificial intelligence (AI) to develop a mobile device that can identify certain patients at risk of sudden cardiac death. This research has yielded a breakthrough in determining the health of the electrical recharging system in a patient’s heart. The researchers determined that a smartphone-enabled mobile EKG device can rapidly and accurately determine a patient’s QTc, thereby identifying patients at risk of sudden cardiac death from congenital long QT syndrome (LQTS) or drug-induced QT prolongation.
Clinicians evaluate the heart’s rate-corrected QT interval, or QTc, as a vital health barometer of the heart’s electrical recharging system. A potentially dangerous prolonged QTc, which is equal to or longer than 50 milliseconds. Such a prolonged QTc can predispose people to dangerously fast and chaotic heartbeats, and even sudden cardiac death. For over 100 years, QTc assessment and monitoring has relied heavily on the 12-lead electrocardiogram (EKG). But that could be about to change, according to this research.
The AI algorithm’s ability to recognize clinically meaningful QTc prolongation on a mobile EKG device was similar to the EKG assessments made by a trained QT expert and a commercial laboratory specializing in QTc measurements for drug studies. The mobile device effectively detected a QTc value of greater than or equal to 500 milliseconds, performing with 80% sensitivity, This means that fewer cases of QTc prolongation were missed, and 94.4% specificity, meaning that if a case was detected it was real.
Also, at the Mayo clinic, Using simplified ECG data taken from an Apple Watch, researchers were able to use an artificial intelligence algorithm to spot people whose hearts may be having trouble pumping blood out to the rest of the body. Low ejection fraction is often a prelude to or part of heart failure and needs to be addressed to avoid continued deterioration. Researchers at the clinic previously demonstrated that they could use AI to detect cases of low ejection fraction using a hospital-based ECG with 12 leads and multiple electrodes wired to the chest. Now, they’ve shown they can tune the system to get the number of leads down to one. Participants from 11 countries signed up for the study over email. More than 125,000 ECGs were logged over a period of six months. According to the researchers, the test demonstrated an area under the curve of 0.88, a measure of prediction accuracy about equivalent to a treadmill-based cardiac stress test
