How AI can be applied to an EKG to measure overall health

Overall health status may soon be measurable by applying AI to electrocardiogram data, according to a journal from the American Heart Association, Circulation: Arrhythmia and Electrophysiology.

Electrocardiograms (EKG or ECG) are a test that measures the electrical heart activity and is known to be affected by a person’s characteristics such as age and sex. When applied, AI may be able to better determine a patient’s gender and provide an estimate of their physiologic age, which is a measure of overall body function and health status that is different from chronological age.

“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, MD, assistant professor of medicine and director for Augmented and Virtual Reality Innovation at Mayo Clinic, said in a statement.

Researchers from Mayo Clinic trained convolutional neural networks using 10-second samples of 12-lead ECG signals from nearly 500,000 patients to predict sex and age. The CNN was tested against data from another 275,000 patients for accuracy.

The AI network was able to estimate a patient’s chronological age as higher when the patient had experienced adverse health situations (heart attack, low ejection fraction and coronary heart disease) and a lower age for those without adverse events. The estimations could help doctors make better interventions for patients at risk.

“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,” Kapa said.

The network also predicted gender with 90% accuracy and chronological age group 72% of the time. With these predictions––and further validation in more research––AI’s applications to ECGs could serve to measure overall health.

“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.