aiqbench analysis
This paper presents a methodological investigation into using copulas to model the dependence structure between clinical and genomic machine learning risk scores for breast cancer stratification. The study finds that while this approach offers an interpretable description of joint distributions, it does not outperform standard linear fusion methods in terms of ROC-AUC discrimination on independent datasets. Consequently, the primary contribution is a novel statistical framework rather than a breakthrough in predictive performance or generalizable AI capabilities.
Copula Based Fusion of Clinical and Genomic Machine Learning Risk Scores for Breast Cancer Risk Stratification
arXiv:2511.17605v2 Announce Type: replace Abstract: Clinical and gene-expression models predict breast cancer outcomes, but simple linear fusion ignores dependence between their risk scores. Using METABRIC, we tested whether modeling the joint distribution of clinical and gene-expression scores improved stratification of 5-year cancer-specific mortality. We defined clinical and mRNA-expression predictor views, trained classifiers, and obtained out-of-fold probabilities through 5-fold cross-validation. The scores were transformed into pseudo-observations on (0,1)^2 and used to fit Gaussian, Clayton, Gumbel, and Frank copulas. The clinical model discriminated better than the gene-expression model (AUC 0.783 vs 0.721). Frank had the smallest goodness-of-fit statistic, with Gaussian performing similarly. Copula fusion did not improve ROC-AUC over the clinical model. However, joint score groups showed clear survival differences, with patients scoring high on both views having the poorest outcomes. Competing-risks analysis showed the same pattern for cancer-death incidence. We also conducted an external evaluation in independent TCGA data using shared predictors and a harmonized 5-year overall-mortality endpoint. Copula-fused, individual, and simple-fusion scores showed comparable discrimination with overlapping confidence intervals. All received the same METABRIC-based recalibration. No gene met the prespecified stability criterion under repeated cross-validated permutation importance, so gene-level findings were treated as exploratory. Copulas provide an explicit, interpretable description of dependence between clinical and gene-expression risk scores and support descriptive joint-group analyses. This methodological study does not establish superior prediction, validated clinical risk categories, or clinical utility.
Abstract:Clinical and gene-expression models predict breast cancer outcomes, but simple linear fusion ignores dependence between their risk scores. Using METABRIC, we tested whether modeling the joint distribution of clinical and gene-expression scores improved stratification of 5-year cancer-specific mortality. We defined clinical and mRNA-expression predictor views, trained classifiers, and obtained out-of-fold probabilities through 5-fold cross-validation. The scores were transformed into pseudo-observations on (0,1)^2 and used to fit Gaussian, Clayton, Gumbel, and Frank copulas. The clinical model discriminated better than the gene-expression model (AUC 0.783 vs 0.721). Frank had the smallest goodness-of-fit statistic, with Gaussian performing similarly. Copula fusion did not improve ROC-AUC over the clinical model. However, joint score groups showed clear survival differences, with patients scoring high on both views having the poorest outcomes. Competing-risks analysis showed the same pattern for cancer-death incidence. We also conducted an external evaluation in independent TCGA data using shared predictors and a harmonized 5-year overall-mortality endpoint. Copula-fused, individual, and simple-fusion scores showed comparable discrimination with overlapping confidence intervals. All received the same METABRIC-based recalibration. No gene met the prespecified stability criterion under repeated cross-validated permutation importance, so gene-level findings were treated as exploratory. Copulas provide an explicit, interpretable description of dependence between clinical and gene-expression risk scores and support descriptive joint-group analyses. This methodological study does not establish superior prediction, validated clinical risk categories, or clinical utility.
Machine Learning (cs.LG); Methodology (stat.ME); Machine Learning (stat.ML)
arXiv:2511.17605 [cs.LG]
(or arXiv:2511.17605v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2511.17605 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 320 words
