Kernel Cox partially linear regression: building predictive models for cancer patients' survival

TL;DR

This paper introduces a novel regularized kernel Cox model with a LASSO penalty for predicting cancer patient survival, effectively handling high-dimensional molecular data and irrelevant predictors.

Contribution

It develops a semi-parametric kernel Cox model with a new regularized kernel machine method that improves prediction accuracy and feature selection in high-dimensional survival analysis.

Findings

Proposed method outperforms existing models in simulation studies.

Successfully applied to multiple myeloma data to classify patient risk.

Enhances survival prediction accuracy using gene expression data.

Abstract

Wide heterogeneity exists in cancer patients' survival, ranging from a few months to several decades. To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates patients' molecular profiles with patients' survival. With complex relationships between survival and high-dimensional molecular predictors, it is challenging to conduct non-parametric modeling and irrelevant predictors removing simultaneously. In this paper, we build a kernel Cox proportional hazards semi-parametric model and propose a novel regularized garrotized kernel machine (RegGKM) method to fit the model. We use the kernel machine method to describe the complex relationship between survival and predictors, while automatically removing irrelevant parametric and non-parametric predictors through a LASSO penalty. An efficient high-dimensional algorithm is developed for the proposed method. Comparison with other competing methods in simulation shows that the proposed method always has better predictive accuracy. We apply this method to analyze a multiple myeloma dataset and predict patients' death burden based on their gene expressions. Our results can help classify patients into groups with different death risks, facilitating treatment for better clinical outcomes.