AI can be “powerful” tool to detect heart problems
A new research study from Mayo Clinic, published yesterday, has found a new way of identifying atrial fibrillation (AF) – a heart condition that causes the heart to beat irregularly – through the use of AI.
Atrial fibrillation affects one million people in the UK and increases the risk of stroke and long term heart problems. Whilst it is a common condition, the periods of irregular heart beats that identify atrial fibrillation are often fleeting. Therefore, it is challenging to diagnose. People are often unaware of its presence so expensive and prolonged monitoring methods are required to detect AF.
Currently, an electrocardiogram (referred to as an ECC or EKG) is used to detect atrial fibrillation. They are noninvasive tests that measure the electrical activity of the heart to detect underlying conditions.
The latest Mayo study shows that an AI-enabled EKG has the potential to detect a recent or impending occurrence of atrial fibrillation. This increases capacity to diagnose the condition and has the potential to drastically improve treatment options.
“When people come in with a stroke, we really want to know if they had AF in the days before the stroke, because it guides the treatment,” says Dr. Paul Friedman, Chair of the Department of Cardiovascular Medicine at Mayo Clinic.
He continued: “Blood thinners are very effective for preventing another stroke in people with AF. But for those without AF, using blood thinners increases the risk of bleeding without substantial benefit. That’s important knowledge. We want to know if a patient has AF.”
The digital data vault at Mayo Clinic has records of over seven million EKGs and researchers used over 450,000 in their research. They were able to train AI to identify subtle differences in a normal EKG that would indicate changes in heart structure caused by atrial fibrillation. These changes are not detectable without the use of AI.
Using 36,280 patients, of whom 3051 had atrial fibrillation, the AI-enabled EKG correctly identified the subtle patterns of atrial fibrillation with 90 per cent 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 Dr. Friedman. “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.”