# Artificial intelligence in the diagnosis and management planning of bicuspid aortic valvular disease: a case series

## TL;DR

This paper explores how artificial intelligence improves the diagnosis and treatment planning for bicuspid aortic valve disease using echocardiography.

## Contribution

The paper demonstrates AI's role in enhancing diagnostic accuracy and surgical planning for bicuspid aortic valve disease through echocardiography.

## Key findings

- AI tools helped assess valvular disease by estimating transvalvular gradients and velocity-time integrals.
- AI reconstructed 3D valve anatomy and calculated left ventricular volumes and ejection fraction.
- AI integration improved diagnostic efficiency and patient-specific treatment planning.

## Abstract

Bicuspid aortic valve (BAV) is the most common congenital heart anomaly, often leading to significant aortic stenosis (AS) or aortic regurgitation (AR), which may require surgical intervention. Echocardiography is typically used for the diagnosis of BAV, and the integration of artificial intelligence (AI) can enhance diagnostic accuracy and guide surgical decisions.

We present two patients with BAV: a 17-year-old male football player with isolated AR due to prolapse undergoing aortic valve repair and a 68-year-old male with combined AS and AR, candidate for aortic valve replacement. Artificial intelligence-based tools assisted in characterizing the valvular disease and assessing its haemodynamic impact by estimating and averaging transvalvular gradients and velocity-time integrals, reconstructing three-dimensional valve anatomy, and automatically calculating left ventricular volumes, ejection fraction, and global longitudinal strain. This comprehensive assessment improved prognostic evaluation and helped tailor the treatment plan.

Artificial intelligence in echocardiography holds great potential for diagnosis and planning the treatment of BAV disease. By enhancing image analysis and automating key diagnostic steps, AI can reduce diagnostic times and optimize patient outcomes. As AI-based tools continue to evolve and gain clinical validation, their integration into everyday practice will likely lead to a more efficient and accurate care for patients with valvular heart disease.