Deep Learning for Survival Analysis: A Review

TL;DR

This paper provides a comprehensive review of deep learning methods applied to survival analysis, highlighting current capabilities, limitations, and the need for more complex task handling.

Contribution

It systematically characterizes DL-based survival analysis methods and introduces an open-source, interactive database for tracking progress in the field.

Findings

Most methods focus on simple, single-risk, right-censored data

Current methods often neglect complex, real-world survival scenarios

The paper offers a community-updated resource for ongoing research

Abstract

The influx of deep learning (DL) techniques into the field of survival analysis in recent years has led to substantial methodological progress; for instance, learning from unstructured or high-dimensional data such as images, text or omics data. In this work, we conduct a comprehensive systematic review of DL-based methods for time-to-event analysis, characterizing them according to both survival- and DL-related attributes. In summary, the reviewed methods often address only a small subset of tasks relevant to time-to-event data - e.g., single-risk right-censored data - and neglect to incorporate more complex settings. Our findings are summarized in an editable, open-source, interactive table: https://survival-org.github.io/DL4Survival. As this research area is advancing rapidly, we encourage community contribution in order to keep this database up to date.