Deep Learning-Based Survival Analysis with Copula-Based Activation Functions for Multivariate Response Prediction
This work addresses survival prediction in domains like healthcare, specifically for breast cancer data, but appears incremental as it combines existing techniques with novel activation functions.
The research tackled predicting multivariate survival data with high correlation and right-censoring by integrating deep learning, copula functions, and survival analysis, resulting in enhanced prediction accuracy as evaluated using Shewhart control charts and average run length metrics.
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).