An AI model accurately detects cardiac structural issues using point-of-care ultrasound (POCUS) images, even by non-cardiologists.
Key Details
- 1The AI model was developed through a collaboration between AISAP and Sheba Medical Center.
- 2Training involved over 120,000 annotated transthoracic echocardiograms.
- 3AISAP Cardio, the POCUS platform, is FDA-cleared for automated cardiac measurements.
- 4Retrospective AUCs for key findings: mitral regurgitation (0.883), tricuspid regurgitation (0.913), ventricular dysfunction (0.940), reduced ejection fraction (0.982).
- 5Prospective real-world AUCs: 0.72, 0.87, 0.95, and 0.97 for the same metrics, using data from 200+ patients scanned by non-cardiologists.
Why It Matters
This AI-driven advancement opens opportunities for broader access to accurate cardiac screening at the point of care, enabling non-experts to detect significant heart issues and potentially improving patient outcomes, especially in resource-limited settings.
Source
Cardiovascular Business
Related News
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•AuntMinnie
Multimodal LLMs Achieve High Accuracy Detecting Scoliosis on X-rays
Multimodal LLMs achieved up to 94% accuracy for scoliosis detection on spine x-rays, but struggled with lumbar stenosis on MRI.