Health professionals without prior ultrasound training successfully captured quality heart scans in rural communities using artificial intelligence (AI) guidance and off-site expert review, according to preliminary research presented at the American Heart Association’s Scientific Sessions 2026. The findings, part of the RURAL (Risk Underlying Rural Areas Longitudinal) study, suggest a potential model for extending cardiac imaging to areas where specialists are scarce.
Echocardiography, which uses ultrasound to produce live images of the heart’s structure and function, is a key tool in cardiovascular research and diagnosis. However, as study author Sanjana Ravi, M.D., noted, delivering this technology in rural settings has historically been difficult due to a reliance on expert sonographers and imaging specialists who are often concentrated in hospitals or urban centers.
In the study, 14 non-sonographers—including nurses, nursing assistants, and CT technologists—completed a two-hour training program on AI-guided ultrasound. They then performed heart scans on 4,597 volunteer participants using a mobile health unit that visited 10 rural counties across Alabama, Kentucky, Louisiana, and Mississippi. The AI software provided real-time guidance during the scans, and images were later reviewed by experts at the Duke Clinical Research Institute Imaging Core Laboratory.
Results showed that 98% of the 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,” Ravi said. “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, who was not involved in the study, emphasized the broader implications. “One in five Americans lives in a rural area, which limits their access to critical diagnostic testing and specialty care,” he said. “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 authors noted several limitations, including the lack of a direct comparison between sonographer-acquired and AI-guided images, the use of a single software brand and core laboratory, and the fact that the study did not assess whether returning results influenced participants’ care. The research abstract is considered preliminary until published in a peer-reviewed journal.
The findings add to ongoing efforts to integrate AI into cardiovascular care, as reflected in recent American Heart Association initiatives such as New guidance offered for responsible AI use in health care and earlier research showing that Artificial intelligence-enhanced ECGs may speed heart failure diagnosis and treatment. For more information on the meeting, visit the Scientific Sessions 2026 page.
