A copula-based competing risks model with application to cancer risk estimation in family studies
Abstract
Cancer risk estimation tools are used by clinicians to evaluate the risk of individuals who carry high-risk pathogenic variants. In this article, we propose a new competing risks model designed to provide personalized estimates of the risk of developing breast or ovarian cancer as the first event among women carrying pathogenic variants in the BRCA1 gene. Our approach incorporates both the personal and complete family history of cancer of these high-risk women and introduces some flexibly in the modeling of the dependence among members of the same family. We use a Gaussian copula with a correlation matrix expressed in terms of the kinship coefficients of pairs of members. Furthermore, we develop an iterative estimation algorithm to estimate the parameters of the underlying model in the presence of a selection bias inherent to the family recruitment process. The performance of the proposed method is evaluated through a simulation study. An application to the Breast Cancer Family Registry data highlights the ability of the model to provide personalized estimation of the risk of developing breast cancer or ovarian cancer as the first event within the competing risks framework.
Related
- Bivariate Frank Copula: Some More Results on Point Estimation of the Association Parameter from a Bayesian Perspective and Revisiting the Goodness of Fit Tests with an Application to Model Groundwater Data from Dong Thap, Vietnam
- Copula Active Subspaces II: Error Decomposition, A Posteriori Estimation, and Sharpness of the Bounds
- Copula Active Subspaces I: A Score-Covariance Method for Reduced-Order Non-Gaussian Density Estimation
- Nonparametric Efficient Estimation of Dynamic Treatment Regimes with Competing Risks
- Doubly Robust Estimation under Covariate Dependent Censoring in Semi-Competing Risks Data
BibTeX
@misc{seboka2026copulabased,
title = {{A copula-based competing risks model with application to cancer risk estimation in family studies}},
author = {Siriac Seboka and Laurent Briollais and Yun-Hee Choi and Lajmi Lakal-Chaieb},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27388},
eprint = {2610.27388},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27388},
note = {CC0},
}
RIS
TY - UNPB
TI - A copula-based competing risks model with application to cancer risk estimation in family studies
AU - Siriac Seboka
AU - Laurent Briollais
AU - Yun-Hee Choi
AU - Lajmi Lakal-Chaieb
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.27388
UR - https://arxiv.org/abs/2610.27388
AB - Cancer risk estimation tools are used by clinicians to evaluate the risk of individuals who carry high-risk pathogenic variants. In this article, we propose a new competing risks model designed to provide personalized estimates of the risk of developing breast or ovarian cancer as the first event among women carrying pathogenic variants in the BRCA1 gene. Our approach incorporates both the personal and complete family history of cancer of these high-risk women and introduces some flexibly in the modeling of the dependence among members of the same family. We use a Gaussian copula with a correlation matrix expressed in terms of the kinship coefficients of pairs of members. Furthermore, we develop an iterative estimation algorithm to estimate the parameters of the underlying model in the presence of a selection bias inherent to the family recruitment process. The performance of the proposed method is evaluated through a simulation study. An application to the Breast Cancer Family Registry data highlights the ability of the model to provide personalized estimation of the risk of developing breast cancer or ovarian cancer as the first event within the competing risks framework.
ER -