dee
DeepHit
pypi i DeepHit
dee

DeepHit

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

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

0.0.1 (see all)License:MIT
pypi i DeepHit
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

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.

GitHub Stars

70

LAST COMMIT

2yrs ago

MAINTAINERS

1

CONTRIBUTORS

3

OPEN ISSUES

1

OPEN PRs

0
VersionTagPublished
0.0.1
1yr ago
No alternatives found
No tutorials found
Add a tutorial