AI software enabled non-sonographer health professionals to successfully perform quality echocardiograms in rural U.S. communities, with scans reviewed by off-site experts.
Key Details
- 1Study involved 4,597 adults (ages 25-65) in rural Alabama, Kentucky, Louisiana, and Mississippi.
- 214 non-sonographers (nurses, assistants, CT techs) trained via a 2-hour AI-guided curriculum performed heart ultrasounds in a mobile unit.
- 398% of scans included all six standard echocardiography views with >99% rated adequate by core lab experts.
- 4Diagnostic-quality images per view ranged from 77% to 94%; 81% of scans completed within a 15-minute target with a median time of 9.5 minutes.
- 5133 critical results (e.g., low ejection fraction) detected; 99% of results returned to participants within 3 days.
- 6Images reviewed remotely by certified echocardiographers at Duke Clinical Research Institute Imaging Core Laboratory.
Why It Matters
This study demonstrates that AI-guided tools can empower non-specialists to deliver high-quality echocardiography in underserved, rural areas, potentially improving access to cardiac imaging and research participation where specialist resources are scarce. If validated, this model could expand to other imaging modalities and specialties, addressing critical gaps in healthcare delivery.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
AI Deep Learning Model Enhances Echocardiogram RV Assessment and Prognosis
Researchers developed DROID-RV, a deep learning tool that automates right ventricular assessment from echocardiograms, showing strong prognostic links with cardiovascular outcomes.