Artificial Intelligence Could Use EKG Data to Measure Our Health

Researchers applied AI to electrocardiogram data to measure the health of patients.
Chris Young
Medical technology and instruments iStock/metamorworks

In the not-too-distant future, medical professionals might be able to apply AI to electrocardiogram data in order to measure a patient's overall health status.

This is according to new research published in Circulation: Arrhythmia and Electrophysiology, a journal of the American Heart Association.


AI health scans

An electrocardiogram - also called an EKG or ECG - is a test used to measure the electrical activity of the heart. A patient's sex and age can have an effect on how an EKG turns out.

That's why the team of researchers built an AI that could determine a patient's gender and estimate their 'physiologic age' - an indicator of overall health that is different from chronological age.

Using the EKG data of roughly 500,000 patients, the AI was trained to estimate the physiologic age of patients based largely on whether they had suffered various diseases.

"While physicians already consider whether a patient 'appears [their] stated age' as part of their baseline physical examination, the ability to more objectively and consistently assess this may impact healthcare on multiple levels," study author Suraj Kapa, M.D., director for Augmented and Virtual Reality Innovation at Mayo Clinic in Rochester, said in a press release.

"Being able to more accurately assess overall health status may help doctors determine which patients they should examine further to determine if there are asymptomatic or currently silent diseases that could benefit from early diagnosis and intervention."

Most Popular

"For people at large, an AI-enhanced electrocardiogram could better show there may be something going on such as a new health issue or comorbid condition that they were otherwise unaware of," Kapa explained.

High accuracy in determining age

The researchers discovered that their AI was able to determine the chronological age group of any patient with 72% accuracy.

"This evidence—that we might be gleaning some sort of 'physiologic age'—was certainly both surprising and exciting for its potential role in future outcomes research, and may foster a new area of science where we seek to better understand the biologic underpinnings of such a finding," Kapa said.

In the future, the researchers would like to focus their studies on the wider population, so as to determine how accurately it reads people who are also in very good health.

message circleSHOW COMMENT (1)chevron