Joint analysis of clinical risk factors and 4D cardiac motion for survival prediction using a hybrid deep learning network

TL;DR

This paper introduces a hybrid deep learning approach that combines 4D cardiac motion features from MRI with clinical risk factors to enhance survival prediction in heart failure patients.

Contribution

It presents a novel method for integrating high-dimensional cardiac motion data with clinical covariates in deep networks, including correlation analysis of their interactions.

Findings

Optimal covariate integration methods identified

Correlation between autoencoder codes and clinical factors analyzed

Potential for incorporating genetic data into survival prediction

Abstract

In this work, a novel approach is proposed for joint analysis of high dimensional time-resolved cardiac motion features obtained from segmented cardiac MRI and low dimensional clinical risk factors to improve survival prediction in heart failure. Different methods are evaluated to find the optimal way to insert conventional covariates into deep prediction networks. Correlation analysis between autoencoder latent codes and covariate features is used to examine how these predictors interact. We believe that similar approaches could also be used to introduce knowledge of genetic variants to such survival networks to improve outcome prediction by jointly analysing cardiac motion traits with inheritable risk factors.