TorchSurv: A Lightweight Package for Deep Survival Analysis

Mélodie Monod, Peter Krusche, Qian Cao, Berkman Sahiner, Nicholas Petrick +2 more
4/16/2024
cs.LG

No official code found. Best implementation: Novartis/torchsurv (210 stars, MIT, PyTorch, last commit 2026-04-28).

Abstract

TorchSurv is a Python package that serves as a companion tool to perform deep survival modeling within the PyTorch environment. Unlike existing libraries that impose specific parametric forms, TorchSurv enables the use of custom PyTorch-based deep survival models. With its lightweight design, minimal input requirements, full PyTorch backend, and freedom from restrictive survival model parameterizations, TorchSurv facilitates efficient deep survival model implementation and is particularly beneficial for high-dimensional and complex input data scenarios.

View on arXivView PDF

Code Implementations(1)

Novartis/torchsurvCommunity100%
PyTorchMIT

Deep survival analysis made easy

21015R, TeXFeb 29, 20245 months agoMIT
deep-learningpytorchsurvival-analysis

Similar Papers

Torchbearer: A Model Fitting Library for PyTorch

79% match1 repo6412018

SurvLIMEpy: A Python package implementing SurvLIME

76% match1 repo252023

TorchSISSO: A PyTorch-Based Implementation of the Sure Independence Screening and Sparsifying Operator for Efficient and Interpretable Model Discovery

74% match1 repo422024

Torch-Choice: A PyTorch Package for Large-Scale Choice Modeling with Python

73% match1 repo602023

SurvReLU: Inherently Interpretable Survival Analysis via Deep ReLU Networks

71% match1 repo92024

TorchAO: PyTorch-Native Training-to-Serving Model Optimization

71% match1 repo2.9k2025

Cite this paper

@article{monod2024torchsurv,
  title  = {TorchSurv: A Lightweight Package for Deep Survival Analysis},
  author = {Mélodie Monod and Peter Krusche and Qian Cao and Berkman Sahiner and Nicholas Petrick and David Ohlssen and Thibaud Coroller},
  year   = {2024},
  eprint = {2404.10761},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.10761v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.10761.svg)](https://codeofpaper.com/paper/2404.10761)

Discussion