Deep Learning-Based Survival Analysis with Copula-Based Activation Functions for Multivariate Response Prediction

TL;DR

This paper proposes a novel deep learning framework using copula-based activation functions to improve multivariate survival analysis, effectively modeling complex dependencies and handling right-censored data for better prediction accuracy.

Contribution

It introduces copula-based activation functions within deep neural networks to explicitly model dependencies in multivariate survival data, a novel approach in this domain.

Findings

Enhanced prediction accuracy demonstrated on breast cancer data

Effective modeling of nonlinear dependencies with copula-based activations

Improved handling of right-censored survival data

Abstract

This research integrates deep learning, copula functions, and survival analysis to effectively handle highly correlated and right-censored multivariate survival data. It introduces copula-based activation functions (Clayton, Gumbel, and their combinations) to model the nonlinear dependencies inherent in such data. Through simulation studies and analysis of real breast cancer data, our proposed CNN-LSTM with copula-based activation functions for multivariate multi-types of survival responses enhances prediction accuracy by explicitly addressing right-censored data and capturing complex patterns. The model's performance is evaluated using Shewhart control charts, focusing on the average run length (ARL).