Prediction of Peak-to-Peak Pressure Gradient in Patients with Aortic Coarctation Using Physics-Informed Neural Networks

Even after early repair of aortic coarctation (AoCo), life expectancy is reduced due to complications such as hypertension. Invasive diagnostic catheterization is used to evaluate peak-to-peak pressure gradients (PG<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pp</inf>) across the CoAo. Clinically significant PG<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pp</inf> are those greater than 20 mmHg under resting conditions, in which case the patient is referred for a second intervention to repair the CoAo. In this study, we demonstrate the feasibility of using Physics-Informed Neural Networks (PINNs) to predict PG<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pp</inf> in patients with AoCo non-invasively, based on images obtained from cardiac magnetic resonance imaging. We analyzed a group of 3 patients with CoAo under resting and pharmacological stress conditions. We were able to obtain PG<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pp</inf> values very close to the actual values obtained by diagnostic catheterization, with an absolute error and average percentage error of 0.57 mmHg and 8.29% for the resting condition, and 4.13 mmHg and 8.63% for the pharmacological stress condition. Our method also successfully identified the only patient who presented a clinically significant PG<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">pp</inf> under resting conditions, with differences of less than 1 mmHg.