Deep Neural Networks for Survival Analysis Based on a Multi-Task Framework

TL;DR

This paper introduces a deep learning-based multi-task logistic regression model for survival analysis, outperforming traditional models like MTLR and CoxPH in nonlinear scenarios by leveraging a neural network architecture.

Contribution

It presents a novel deep neural network framework for survival analysis based on MTLR, improving predictive accuracy over existing models.

Findings

Outperforms MTLR in all experiments

Outperforms CoxPH when nonlinear dependencies are present

Achieves higher Concordance index and Brier score

Abstract

Survival analysis/time-to-event models are extremely useful as they can help companies predict when a customer will buy a product, churn or default on a loan, and therefore help them improve their ROI. In this paper, we introduce a new method to calculate survival functions using the Multi-Task Logistic Regression (MTLR) model as its base and a deep learning architecture as its core. Based on the Concordance index (C-index) and Brier score, this method outperforms the MTLR in all the experiments disclosed in this paper as well as the Cox Proportional Hazard (CoxPH) model when nonlinear dependencies are found.