Health professionals without prior ultrasound training successfully performed echocardiograms in mobile units serving rural communities when assisted by artificial intelligence and off-site expert review, according to preliminary research presented at the American Heart Association’s Scientific Sessions 2026. The findings suggest a scalable model for delivering cardiac imaging to underserved regions and for including rural populations in cardiovascular research.
The study, part of the larger RURAL (Risk Underlying Rural Areas Longitudinal) study, involved 4,597 volunteers who were scanned in mobile units across 10 rural counties in Alabama, Kentucky, Louisiana, and Mississippi between November 2021 and June 2026. Fourteen non-sonographers—nurses, nursing assistants, and CT technologists—completed a two-hour training curriculum on AI-guided ultrasound. The AI software provided real-time guidance during scans, and images were remotely reviewed by experts at the Duke Clinical Research Institute Imaging Core Laboratory.
Results showed that 98% of scans included all six standard echocardiography views required by the study protocol, and core laboratory experts rated more than 99% of studies as adequate for measurements. Diagnostic-quality images for individual views ranged from 77% to 94%. Scans were completed within the 15-minute target window 81% of the time, with a median time of 9.5 minutes. Critical findings, such as an ejection fraction below 50%, were identified in 133 scans, and 99% of these results were returned to participants within three days.
“We were surprised at how quickly and well the nurses and CT technologists who had never done a heart ultrasound were able to adapt to this technology and produce quality images for review by experts,” said study author Sanjana Ravi, M.D., an internal medicine and pediatrics resident at Duke University School of Medicine. “With real-time AI guidance and a rigorous quality-control system behind it, a nurse or CT technologist in a mobile unit can produce heart images good enough for research and good enough to flag serious heart problems that need follow-up, bringing the imaging to the community rather than asking the community to travel to it.”
Lee H. Schwamm, M.D., FAHA, a member of the American Heart Association’s volunteer committee on AI and Technology Innovation, noted that “1 in 5 Americans lives in a rural area, which limits their access to critical diagnostic testing and specialty care. In this hybrid model, community-based non-experts were able to create a human-AI partnership with the acquisition software to enable the capture of echocardiogram images that could be read by off-site experts. This novel approach brings heart imaging to local communities and truly meets people where they are. If confirmed in further studies, this approach could serve as a model for other specialties and diagnostic modalities.”
The American Heart Association provides resources on Echocardiography and offers a downloadable guide on what the test involves. The association has also issued New guidance offered for responsible AI use in health care and previously reported that Artificial intelligence-enhanced ECGs may speed heart failure diagnosis and treatment. The study’s abstract is available as abstract poster MDP2290, and additional details can be found in the release link.
Limitations include the absence of a direct comparison between sonographer-acquired and AI-guided non-sonographer images, the use of a single software brand and core laboratory, and the lack of assessment on whether returning results influenced care. The findings are considered preliminary until published in a peer-reviewed journal.


