AI tool for heart failure screening demonstrates long-term cost savings

Earlier research showed that primary care clinicians using AI-ECG tools identified more unknown cases of a weak heart pump, also called low ejection fraction, than without AI. New study findings published in Mayo Clinic Proceedings: Digital Health suggest that this type of screening is also cost-effective in the long term, especially in outpatient settings.

Incremental drops in heart function are treatable with medication but can be hard to spot. Patients may or may not have symptoms when their heart is not pumping effectively, and doctors may not order an echocardiogram or other diagnostic test to check ejection fraction unless there are symptoms. Peter Noseworthy, M.D., a Mayo Clinic cardiologist and co-author of the study, notes that using AI to catch the hidden signals of heart failure during a routine visit can mean earlier treatment for patients, delaying or stopping disease progression, and fewer related medical costs over time.

According to the study, the cost-effectiveness ratio of using AI-ECG was $27,858 per quality-adjusted life year -; a measure of the quality of life and years lived. The program was especially cost-effective in outpatient settings, with a much lower cost-effectiveness ratio of $1,651 per quality-adjusted life year.

The researchers studied the economic impact of using the AI-ECG tool by using real-world information from 22,000 participants in the established EAGLE trial and following which patients had weak heart pumps and which did not. They simulated the progression of disease in the longer term, assigning values for the health burden on patients and the resulting effect on economic value.

We categorized patients as either AI-ECG positive, meaning we would recommend further testing for low ejection fraction, or AI-ECG negative with no further tests needed. Then we followed the normal path of care and looked at what that would cost. Did they have an echocardiogram? Did they stay healthy or develop heart failure later and need hospitalization? We considered different scenarios, costs and patient outcomes.”

Xiaoxi Yao, Ph.D., Professor of Health Services Research at Mayo Clinic

Dr. Yao, who is the senior author of the study, notes that cost-effectiveness is an important aspect of the evaluation of AI technologies when considering what to implement in clinical practice.

“We know that earlier diagnosis can lead to better and more cost-effective treatment options. To get there, we have been establishing a framework for AI evaluation and implementation. The next step is finding ways to streamline this process so we can reduce the time and resources required for such rigorous evaluation,” says Dr. Yao.

This study was funded by Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery. Mayo Clinic and some of the researchers have a financial interest in the technology referenced in this news release. Mayo Clinic will use any revenue it receives to support its not-for-profit mission in patient care, education and research.