Novartis/torchsurv
Deep survival analysis made easy
This tool helps researchers and clinicians analyze time-to-event data, common in medical studies or reliability engineering. You provide patient data, including whether an event occurred and the time until it happened (or censoring time), along with relevant covariates. The tool outputs predictions about survival likelihoods or event risks over time. It's designed for quantitative researchers, biostatisticians, and data scientists working on deep learning models.
188 stars. Available on PyPI.
Use this if you need to build custom deep learning models for survival analysis without being limited by specific statistical assumptions.
Not ideal if you prefer traditional, pre-defined parametric survival models or don't work with PyTorch.
Stars
188
Forks
16
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Novartis/torchsurv"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
sebp/scikit-survival
Survival analysis built on top of scikit-learn
havakv/pycox
Survival analysis with PyTorch
soda-inria/hazardous
Competing Risks and Survival Analysis
square/pysurvival
Open source package for Survival Analysis modeling
autonlab/auton-survival
Auton Survival - an open source package for Regression, Counterfactual Estimation, Evaluation...