Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders
This work addresses the need for interpretable models to understand cardiac health risks in healthcare systems, though it is incremental as it builds on existing VAE methods.
The study tackled the problem of analyzing how systolic blood pressure impacts cardiac function by developing a framework that combines deep learning with variational autoencoders to estimate interpretable biomarkers from cardiac MRI data in a cohort of 3,600 subjects from the UK Biobank, resulting in insights into cardiac deterioration and adaptation patterns.
Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health. The aim of this study is to analyze the impact of systolic blood pressure (SBP) on cardiac function while preserving the interpretability of the model using known clinical biomarkers in a large cohort of the UK Biobank population. We propose a novel framework that combines deep learning based estimation of interpretable clinical biomarkers from cardiac cine MR data with a variational autoencoder (VAE). The VAE architecture integrates a regression loss in the latent space, which enables the progression of cardiac health with SBP to be learnt. Results on 3,600 subjects from the UK Biobank show that the proposed model allows us to gain important insight into the deterioration of cardiac function with increasing SBP, identify key interpretable factors involved in this process, and lastly exploit the model to understand patterns of positive and adverse adaptation of cardiac function.