Researchers from Mayo Clinic and AliveCor Inc. has been using artificial intelligence (AI) to develop a mobile device that identifies specific patients at risk of sudden cardiac death. This research has resulted in determining the health of the electrical transplant system in a patient’s heart.
The researchers concluded that a mobile EKG device with smartphone QTc capability can quickly and accurately detect a patient, thus identifying patients at risk of sudden cardiac death from congenital long QT syndrome (LQTS) or drug-induced QT proliferation.
The heart beats with a complex system of electrical signals that promotes constant and essential contraction. Clinicians evaluate the phase-corrected QT interval, or QTc, as an essential health barometer of the cardiac electrical transplant system. Persistent and potentially dangerous QTc, equal to or greater than 50 milliseconds, can be caused by:
- More than 100 drugs approved by the Food and Drug Administration (FDA).
- Genetics, including long congenital QT syndrome.
- Many systemic diseases, including even SARS-CoV-2-mediated COVID-19.
Such prolonged QTc can lead people to rapid and chaotic dangerous heartbeats, and even sudden heart death. For more than 100 years, QTc evaluation and monitoring has relied heavily on the 12-lead electrocardiogram (EKG). But that is likely to change, according to this research.
Led by Michael Ackerman, MD, Ph.D., genetic cardiologist at the Mayo Clinic, researchers trained and tested an AI-based deep neural network to detect QTc expansion using AliveCor’s KardiaMobile 6L EKG device. The findings, published in Circulation, compared to the mobile EKG capability with AI capability to traditional 12-lead EKG in detecting QT expansion.
“This collaborative effort with researchers from academia and industry has yielded what I call‘ pivot ’detection,” said Dr. Ackerman, director of the Mayo Smith Rice Clinic’s Sudden Sudden Heart Death Program. “So we pivot from the old way we have been getting the QTc to this new way. Since Einthoven’s first major EKG paper in 1903, 2021 will mark a fresh start for the QT interim. “
The team used more than 1.6 million 12-lead EKGs from more than half a million patients to train and test an AI-based deep neural network to accurately identify and measure the QTc. This next QTc assessment is based on AI? The “QT meter”? was pre-diagnosed in nearly 700 patients evaluated by Drs. Ackerman at Mayo’s Rice Genetics Rhythm Clinic Mayo Clinic. Half of these patients had long congenital QT syndrome.
The goal was to compare QTc values from a 12-lead EKG with those from the EKG handheld prototype device used by a smartphone. Both sets of EKG were given at the same clinical visit, usually within five minutes of each other.
The ability of the AI algorithm to identify clinically significant QTc proliferation on a mobile EKG device was similar to EKG evaluations performed by a trained QT expert and commercial lab specializing in QTc measurement for drug studies. The mobile device effectively found a QTc value greater than or equal to 500 milliseconds, achieving with:
- 80% Sensitivity This means that fewer cases of QTc expansion have been missed.
- Specificity 94.4%
This means that he was very accurate in predicting who did not have a long QTc.
“The ability to equip mobile EKG machines with accurate AI-powered approaches capable of accurately calculating the QTc represents a potential paradigm shift in terms of how and where the inter- assess QT time, ”says John Giudicessi, MD, Ph.D., Mayo. Man of clinical cartography and first author of the study.
“Currently, AliveCor’s KardiaMobile 6L EKG device has been cleared by the FDA for the detection of atrial fibrillation, bradycardia, and tachycardia. Once FDA approval is obtained for this AI-based QTc evaluation, real We have a QT meter that will enable this vital sign that features “Alarms” to be readily and accurately available, “said Dr Ackerman. “Like a glucose meter for diabetics, for example, this QT meter provides an early warning system, allowing patients with congenital or acquired LQTS and potentially life-saving changes on the medicines and their electrolytes. “
This point-of-care use of artificial intelligence is highly scalable, as it is connected to a smartphone. It can save a life by telling someone that certain medicines can be harmful before taking the first pill. This will allow a possible life situation to be identified before the symptoms become apparent. “
Paul Friedman, MD, Chair, Department of Cardiovascular Medicine, Mayo Clinic, Rochester
“Regular monitoring for LQTS using KardiaMobile 6L allows real-time data collection outside of hospital walls,” said David Albert, MD, founder and chief medical officer at AliveCor Inc. ” Because LQTS can be intermittent and achievable, the ability to detect this rhythm without 12-lead EKG – which requires the patient to be hospitalized – can improve patient outcomes and save resources hospitals, while still providing the physicians with reliable and timely data that their patients need. “