JHVS: A Deep Learning Approach for Patient-Specific Aortic Wall Mechanical Stress Prediction in Transcatheter Aortic Valve Implantation Procedure Using Graph Neural Networks

In this study, the authors developed a deep learning model for prediction of patient-specific article on mechanical stress prediction following TAVR.

And so they implemented graph neural network models for predicting patient-specific stress outcomes, specifically contact pressure and what we call von Mises stresses following TAVR.

So this article is accompanied by a very interesting editorial from Dr. Roy Shah, Veneziani and Daci from the Georgia Institute of Technologies and Emory University in Atlanta, USA.

In this editorial, the authors state that the conversions of high fidelity computational biomechanics, physics driven model reduction, geometric deep learning, and large scale clinical imaging data set is creating the condition of a transformation in how clinical teams can plan for and evaluate structural heart intervention.

So this article by Osen and colleagues serves, I think, as a great demonstration of this evolution driven by AI and computational modeling.