Conformal Survival Bands for Risk Screening under Right-Censoring

Matteo Sesia, Vladimir Svetnik
Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 266:464-514, 2025.

Abstract

We introduce a method for quantifying uncertainty around individual survival curves produced by any survival model under general right-censoring, with formal guarantees of predictive calibration. Unlike classical confidence intervals, which focus on population-level quantities such as conditional survival probabilities, our approach constructs survival bands tailored for personalized risk screening. These bands support arbitrary selection rules aimed at identifying high- or low-risk individuals, while approximately controlling the false discovery rate. For instance, in a high-risk screening scenario, practitioners can flag patients whose entire survival band at 12 months falls below $50%$, while being confident that, on average, no more than $50%$ of flagged individuals will survive past that point. Our method builds on recent advances in conformal inference and incorporates ideas from inverse probability of censoring weighting and multiple testing. We provide asymptotic guarantees and demonstrate strong finite-sample performance using both synthetic and real-world data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v266-sesia25a, title = {Conformal Survival Bands for Risk Screening under Right-Censoring}, author = {Sesia, Matteo and Svetnik, Vladimir}, booktitle = {Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {464--514}, year = {2025}, editor = {Nguyen, Khuong An and Luo, Zhiyuan and Papadopoulos, Harris and Löfström, Tuwe and Carlsson, Lars and Boström, Henrik}, volume = {266}, series = {Proceedings of Machine Learning Research}, month = {10--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v266/main/assets/sesia25a/sesia25a.pdf}, url = {https://proceedings.mlr.press/v266/sesia25a.html}, abstract = {We introduce a method for quantifying uncertainty around individual survival curves produced by any survival model under general right-censoring, with formal guarantees of predictive calibration. Unlike classical confidence intervals, which focus on population-level quantities such as conditional survival probabilities, our approach constructs survival bands tailored for personalized risk screening. These bands support arbitrary selection rules aimed at identifying high- or low-risk individuals, while approximately controlling the false discovery rate. For instance, in a high-risk screening scenario, practitioners can flag patients whose entire survival band at 12 months falls below $50%$, while being confident that, on average, no more than $50%$ of flagged individuals will survive past that point. Our method builds on recent advances in conformal inference and incorporates ideas from inverse probability of censoring weighting and multiple testing. We provide asymptotic guarantees and demonstrate strong finite-sample performance using both synthetic and real-world data.} }
Endnote
%0 Conference Paper %T Conformal Survival Bands for Risk Screening under Right-Censoring %A Matteo Sesia %A Vladimir Svetnik %B Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2025 %E Khuong An Nguyen %E Zhiyuan Luo %E Harris Papadopoulos %E Tuwe Löfström %E Lars Carlsson %E Henrik Boström %F pmlr-v266-sesia25a %I PMLR %P 464--514 %U https://proceedings.mlr.press/v266/sesia25a.html %V 266 %X We introduce a method for quantifying uncertainty around individual survival curves produced by any survival model under general right-censoring, with formal guarantees of predictive calibration. Unlike classical confidence intervals, which focus on population-level quantities such as conditional survival probabilities, our approach constructs survival bands tailored for personalized risk screening. These bands support arbitrary selection rules aimed at identifying high- or low-risk individuals, while approximately controlling the false discovery rate. For instance, in a high-risk screening scenario, practitioners can flag patients whose entire survival band at 12 months falls below $50%$, while being confident that, on average, no more than $50%$ of flagged individuals will survive past that point. Our method builds on recent advances in conformal inference and incorporates ideas from inverse probability of censoring weighting and multiple testing. We provide asymptotic guarantees and demonstrate strong finite-sample performance using both synthetic and real-world data.
APA
Sesia, M. & Svetnik, V.. (2025). Conformal Survival Bands for Risk Screening under Right-Censoring. Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 266:464-514 Available from https://proceedings.mlr.press/v266/sesia25a.html.

Related Material