Mayo Clinic researchers have developed an AI model that detects heart obstructions from routine ultrasound, potentially improving early identification of at-risk patients.
Key Details
- 1The AI model identifies left ventricular outflow tract (LVOT) obstruction in hypertrophic cardiomyopathy (HCM) using non-Doppler ultrasound videos.
- 2External validation was performed with 46 patients from a South Korean hospital, showing strong model performance despite population differences.
- 3Combining three standard ultrasound views improved model accuracy for detecting elevated LVOT gradients.
- 4In some cases, the AI outperformed two expert echocardiographers using only standard images.
- 5The technology intends to complement Doppler echocardiography, aiding early detection and triage.
- 6No external funding was received for the study; results are published in Circulation: Cardiovascular Imaging.
Why It Matters
This AI advancement may enable more accessible and timely identification of significant cardiac obstructions, especially where Doppler expertise is lacking. It demonstrates how imaging AI could extend cardiac screening capabilities in varied clinical settings.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.
•EurekAlert
Scripps Researchers Develop AI Foundation Model for ECG-Based Heart Disease Prediction
A new AI foundation model, ECG-CLIP, improves detection and prediction of multiple heart diseases using large-scale ECG and clinician note data.