By Diagnostics World News
October 8, 2024 | Recent studies from researchers at Imperial College London have demonstrated how AI can identify patients with significantly higher risk of experiencing major adverse cardiac events (MACE), including heart attacks and heart failure, and how such a tool can be incorporated into the clinic. In all three studies, researchers used Eko Health's FDA-cleared and UKCA-marked Low Ejection Fraction AI. The work was presented at the European Society of Cardiology (ESC) Congress 2024 in London, Aug. 30 to Sept. 2.
Studying more than 1,000 patients, researchers used Eko's AI to predict MACE—including heart attacks, heart failure, and hospitalization—as well as all-cause mortality. They found that patients flagged by the AI for low ejection fraction were twice as likely to experience MACE compared to those without a positive AI result and also faced a 65% higher mortality rate, even after adjusting for traditional risk factors.
“An AI-ECG algorithm designed to identify impaired LVEF can identify patients at risk of MACE and all-cause mortality from single-lead ECG screening, regardless of their LVEF,” the researchers wrote in their study summary. “Such results may enable further risk stratification for cardiovascular investigations through the simple addition of single-lead ECG recording.”
The Imperial team also tested the technology’s use in empowering remote patient monitoring, particularly for individuals with heart failure. “Easy home-based tracking of cardiac function would be transformative,” the authors wrote. They found that Eko's AI could accurately predict changes in left ventricular ejection fraction (LVEF) from home so that patients could benefit from earlier interventions and personalized adjustments to their treatment plans. “Such results can place AI-ECG as a remote monitoring tool to track improvement or deterioration in patients’ LVEF%, which facilitate a proactive management and prevention strategies,” they concluded.
Practical Clinical Integration
Finally in the third study, the Imperial team successfully integrated Eko's AI across 32 primary care sites in the UK over a 12-week period at the end of 2023 for a total of 1,555 unique patient examinations (3,253 total recordings), over a median of 90 days. The Imperial team compared how usage changed at 4, 8, and 12 weeks. They found that using an AI-stethoscope in primary care is feasible and consistent. The proportion of abnormal AI findings was consistent with expected findings and would not, consequentially, overwhelm downstream health services.