survdnn: Deep Neural Networks for Survival Analysis Using 'torch'

Provides deep learning models for right-censored survival data using the 'torch' backend. Supports multiple loss functions, including Cox partial likelihood, L2-penalized Cox, time-dependent Cox, and accelerated failure time (AFT) loss. Offers a formula-based interface, built-in support for cross-validation, hyperparameter tuning, survival curve plotting, and evaluation metrics such as the C-index, Brier score, and integrated Brier score. For methodological details, see Kvamme et al. (2019) <https://www.jmlr.org/papers/v20/18-424.html>.

Version:	0.6.0
Depends:	R (≥ 4.1.0)
Imports:	torch, survival, stats, utils, tibble, dplyr, purrr, tidyr, ggplot2, methods, rsample, cli, glue
Suggests:	testthat (≥ 3.0.0), knitr, rmarkdown
Published:	2025-07-22
DOI:	10.32614/CRAN.package.survdnn
Author:	Imad EL BADISY [aut, cre]
Maintainer:	Imad EL BADISY <elbadisyimad at gmail.com>
BugReports:	https://github.com/ielbadisy/survdnn/issues
License:	MIT + file LICENSE
URL:	https://github.com/ielbadisy/survdnn
NeedsCompilation:	no
Materials:	README, NEWS
CRAN checks:	survdnn results

Documentation:

Reference manual:

survdnn.html , survdnn.pdf

Downloads:

Package source:	survdnn_0.6.0.tar.gz
Windows binaries:	r-devel: not available, r-release: survdnn_0.6.0.zip, r-oldrel: survdnn_0.6.0.zip
macOS binaries:	r-release (arm64): survdnn_0.6.0.tgz, r-oldrel (arm64): survdnn_0.6.0.tgz, r-release (x86_64): survdnn_0.6.0.tgz, r-oldrel (x86_64): survdnn_0.6.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=survdnn to link to this page.