https://github.com/chl8856/DeepHit

DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks
https://github.com/chl8856/DeepHit

Last synced: 3 months ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/chl8856/DeepHit
• Owner: chl8856
• Created: 2019-02-12T06:55:31.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-01-08T05:33:02.000Z (almost 3 years ago)
• Last Synced: 2024-07-21T20:51:38.069Z (4 months ago)
• Language: Python
• Size: 1.27 MB
• Stars: 167
• Watchers: 3
• Forks: 73
• Open Issues: 5
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-sciml - chl8856/DeepHit: DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks

README

        
# DeepHit

Title: "DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks"

Authors: Changhee Lee, William R. Zame, Jinsung Yoon, Mihaela van der Schaar

- Reference: C. Lee, W. R. Zame, J. Yoon, M. van der Schaar, "DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks," AAAI Conference on Artificial Intelligence (AAAI), 2018

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

- Supplementary: http://medianetlab.ee.ucla.edu/papers/AAAI_2018_DeepHit_Appendix

### Description of the code

This code shows the modified implementation of DeepHit on Metabric (single risk) and Synthetic (competing risks) datasets.

The detailed modifications are as follows:

- Hyper-parameter opimization using random search is implemented

- Residual connections are removed

- The definition of the time-dependent C-index is changed; please refer to T.A. Gerds et al, "Estimating a Time-Dependent Concordance Index for Survival Prediction Models with Covariate Dependent Censoring," Stat Med., 2013

- Set "EVAL_TIMES" to a list of evaluation times of interest for optimizating the network with respect these evaluation times.