AI can help create inexpensive detectors for heart diseases

That artificial intelligence (AI) is beneficial is the reason why it has managed to encroach in our lives this much. However, every once in a while, a study warns us about its negative effects and all of us take a backseat. But today’s not that day. Today, applying artificial intelligence to a widely available test – the electrocardiogram (EKG) results in a test that is simpler, affordable and an early indicator of a precursor to heart failure, according to scientists.

When tested, the accuracy of the AI/EKG system did better than the other common screening tests like the mammography for breast cancer, according to the research published in the journal Nature Medicine.

Characterised by the pressure of a weak heart pump with a risk of over heart failure, asymptomatic left ventricular dysfunction is associated with reduced quality of life and longevity. But when identified, the disease can be treated.

As of now there is not an inexpensive, noninvasive and painless screening tool for asymptomatic left ventricular dysfunction available for its diagnosis. The test that seems to work requires the patient to draw blood and also doesn’t have the most reliable results.

Left ventricular dysfunction typically is diagnosed with expensive and less accessible imaging tests, such as echocardiograms, or CT or MRI scans.

"Congestive heart failure afflicts more than 5 million people and consumes more than USD 30 billion in health care expenditures in the US alone," said Paul Friedman from Mayo Clinic.

"The ability to acquire a ubiquitous, easily accessible, inexpensive recording in 10 seconds -- the EKG -- and to digitally process it with AI to extract new information about previously hidden heart disease holds great promise for saving lives and improving health," he said.

To test the hypothesis of asymptomatic left ventricular dysfunction that can be detected by EKG by a properly trained neural network, the researchers created and trained a neutral system.

The accuracy of the AI/EKG test compared favourably than other common screening tests, such as a prostate-specific antigen for prostate cancer, mammography for breast cancer and cervical cytology for cervical cancer.

"In other words, the test not only identified asymptomatic disease but also predicted the risk of future disease, presumably by identifying very early, subtle EKG changes that occur before heart muscle weakness," said Friedman.