-
Cardiovascular
ROCHESTER, Minn. — Mayo Clinic researchers tested an approach that uses artificial intelligence (AI) to help people without previous ultrasound experience capture heart images and identify patients who may have a common and serious heart valve condition. In a study published in JAMA Cardiology and presented at the 2026 ESC Congress, after four hours of training, novice users were able to collect focused heart ultrasound images while using AI models to guide their image collection and help to analyze the images for signs of moderate or greater aortic stenosis.
Aortic stenosis happens when the heart’s aortic valve narrows, making it harder for the heart to pump blood to the rest of the body. It affects approximately 7% of people age 75 and older and is the most common reason for heart valve intervention worldwide. People with aortic stenosis may not experience symptoms until the condition is more advanced. Finding the disease earlier can help ensure patients receive appropriate monitoring and care.
“A comprehensive echocardiogram is the standard diagnostic test for aortic stenosis. However, its use is resource-intensive, requiring specialized equipment as well as trained personnel with expertise in both image acquisition and interpretation. These requirements can limit access, particularly in resource-constrained settings, and make comprehensive echocardiography neither feasible nor cost-effective as a broad screening tool,” says Gal Tsaban, M.D., Ph.D., a cardiologist at Mayo Clinic and senior author of the study.
“We wanted to see whether combining AI guidance with focused cardiac ultrasound could help people with no previous ultrasound experience capture usable heart images and identify patients who may need further evaluation,” adds Jared Bird, M.D., a Mayo Clinic cardiologist who co-led the study.
First, the researchers developed and validated the deep learning algorithm using echocardiograms from patients at Mayo Clinic sites in Arizona, Florida, the Mayo Clinic Health System and Rochester. They evaluated the model’s performance on hand-held ultrasound images collected by experienced sonographers.
In the prospective study, nine research staff members with no previous clinical or ultrasound experience used AI guidance to perform focused heart ultrasounds after four hours of training. The staff members were able to use the AI model to analyze nearly 97% of the exams. It helped the researchers correctly identify 93% of patients with moderate or more severe aortic stenosis and correctly rule out 96% of patients who did not have the condition.
About 10% of exams were flagged for review by a heart imaging specialist. The combined approach of AI plus human review reduced false-positive results, but it also meant that some patients with aortic stenosis were not identified.
Dr. Tsaban and Dr. Bird note that the approach is intended to help people screen for aortic stenosis and determine who may benefit from additional testing. It is not intended to replace a comprehensive echocardiogram or a physician’s evaluation. Patients identified as potentially having moderate or more severe aortic stenosis still need comprehensive echocardiography to confirm the diagnosis and determine the severity of the condition.
The findings suggest that putting AI tools in the hands of people with limited ultrasound experience could help more patients access screening for aortic stenosis, particularly in communities where comprehensive echocardiography and trained imaging professionals are less readily available.
A full list of authors, appropriate disclosures and funding sources for this research can be found within the paper: “Artificial Intelligence-Enabled Acquisition and Interpretation for Screening Aortic Stenosis.” Mayo Clinic has a financial interest in the technology referenced in this news release and will use any revenue it receives to support its nonprofit mission in patient care, education and research.
###
About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.
Media contact:
