# Artificial intelligence assessment of valvular disease and ventricular function by a single echocardiography view

## TL;DR

This study shows that AI can accurately detect heart valve and ventricular issues using a single ultrasound image, even when taken by non-cardiologists.

## Contribution

A deep learning model achieves high accuracy in diagnosing cardiac conditions from a single echocardiography view.

## Key findings

- The model achieved AUCs of 0.883 for mitral regurgitation and 0.982 for reduced ejection fraction in retrospective testing.
- Prospective testing showed AUCs of 0.97 for reduced ejection fraction using handheld devices by non-cardiologists.
- The model works well with both standard and handheld ultrasound images for cardiac screening.

## Abstract

Valvular heart disease and heart failure are major global health burdens, yet access to comprehensive echocardiography is often limited, particularly in resource-constrained settings. Artificial intelligence (AI) may enable rapid, point-of-care cardiac assessment using simplified imaging protocols.

To evaluate whether a deep learning model can accurately detect significant valvular and ventricular dysfunction using only a single two-dimensional apical four-chamber echocardiographic view, including images acquired by non-cardiologists with handheld ultrasound devices.

We retrospectively analyzed 120,127 echocardiographic studies from a tertiary medical center to train and validate a deep learning model for identifying moderate-or-greater mitral or tricuspid regurgitation, right ventricular dysfunction, and reduced left ventricular ejection fraction (≤40%). A prospective cohort of 209 patients underwent handheld point-of-care cardiac ultrasound performed by non-cardiologist physicians, with same-hospitalization comprehensive echocardiography as the reference standard.

In retrospective testing, model areas under the curve (AUCs) were 0.883 for mitral regurgitation, 0.913 for tricuspid regurgitation, 0.940 for right ventricular dysfunction, and 0.982 for reduced ejection fraction. In the prospective cohort, AUCs were 0.72, 0.87, 0.95, and 0.97 for the same respective targets.

A single-view deep learning model demonstrated strong diagnostic accuracy for detecting significant valvular and ventricular dysfunction across both standard and handheld ultrasound acquisitions. This approach may facilitate rapid, scalable cardiac function screening by non-cardiologists in diverse clinical environments.

identifier NCT05455541.