cmclean5 / PublicHealthModels

R implementation of popular ML models for health care data
0 stars 0 forks source link

DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks #1

Open cmclean5 opened 1 year ago

cmclean5 commented 1 year ago

TL;DR

This paper proposes a deep neural network approach to survival analysis.

Paper Link

http://medianetlab.ee.ucla.edu/papers/AAAI_2018_DeepHit

Author/Institution

Changhee Lee (University of California), William R. Zame (University of California),
Jinsung Yoon (University of California), Mihaela van der Schaar (University of California, University of Oxford, Alan Turing Institute)

Overview

This paper proposes a deep neural network approach to survival analysis, to learn the distribution of survival times directly. The DeepHit model makes no assumptions about the underlying stochastic process and allows for the possibility that the relationship between covariates and risk(s) changes over time. The DeepHit model can handle competing risks; i.e. settings in which there is more than one possible event of interest.

Contributions and Distinctions from Previous Works

Methods

Survival analysis, neural networks.

Results

Cite

Changhee Lee, et, al. DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 2020.

Comments

Python code available: https://github.com/chl8856/DeepHit