The questionable accuracy of wearables and other digital tools screening for complex conditions such as heart disease has prevented these devices from being particularly helpful to date.

However, a group of computer scientists at Yale University is examining a potential solution: training artificial intelligence tools on “noisy” electrocardiograms that simulate the kind of messy data readings a wearable would generate. 

Their research suggests that by mimicking the challenges of wearable-derived data right away, such as poor contact with the skin, AI can better detect heart problems. In fact, the team’s “noise-adapted” AI model designed to detect heart failure performed much better than a standard version, according to research published in Nature in July.

The team is now putting together a follow-up study with actual patients. Future goals are to clarify how the AI accounts for different demographics and whether the noise-tested AI can be “device agnostic” or only works with specific wearables.

The main disease the study tested for, left ventricular systolic dysfunction, is a common concern among older adults. Although the condition is underdiagnosed, LVSD could be detected early in roughly 90% of patients, previous studies have shown. Heart disease overall is the leading cause of death among older adults.

Wearable heart monitors are increasingly popular, with tools such as portable EKGs, smartwatches and patches in development or on the market. The ability for wearables such as an Apple Watch or FitBit to accurately detect heart disease would particularly benefit patients within long-term care settings, the researchers noted. 

“The noise-adapted approach defines a novel paradigm on how to build robust, wearable-ready, single-lead ECG cardiovascular screening models from clinical ECG repositories, with significant potential to expand the screening of LV structural cardiac disorders to low-resource settings with limited access to hospital-grade equipment,” the researchers wrote.

From the September 2023 Issue of McKnight's Long-Term Care News