search

sebp / scikit-survival

Survival analysis built on top of scikit-learn
GNU General Public License v3.0
1.12k stars 214 forks source link

Conditional Survival Forest model #341

Open realonbebeto opened 1 year ago

realonbebeto commented 1 year ago

In a runtime comparison, the Conditional Survival Forest model proves to be computationally faster than the existing alternatives with a reduced split variable selection bias

Implementation of the Conditional Survival Forest Model with the foundation of the scikit-learn API

pySurvival was last updated in 2019 and is not supported by MLFlow

References and existing implementations https://square.github.io/pysurvival/models/conditional_survival_forest.html https://arxiv.org/pdf/1605.03391.pdf

sebp commented 1 year ago

I agree that the split criterion of Conditional Survival Forests would be nice to have. However, I currently have no plan to work in this myself, but contributions are always welcome.