A fully likelihood-based approach to model survival data with crossing survival curves

TL;DR

This paper introduces a fully likelihood-based method using piecewise exponential modeling to analyze survival data with crossing curves, extending the Yang and Prentice model for more general regression scenarios.

Contribution

It develops a new likelihood-based approach for the YP model, enabling flexible and tractable analysis of crossing survival curves in regression settings.

Findings

Model performs well with moderate sample sizes

Outperforms the original YP model in simulations

Demonstrated usefulness in cancer clinical trial data

Abstract

Proportional hazards (PH), proportional odds (PO) and accelerated failure time (AFT) models have been widely used to deal with survival data in different fields of knowledge. Despite their popularity, such models are not suitable to handle survival data with crossing survival curves. Yang and Prentice (2005) proposed a semiparametric two-sample approach, denoted here as the YP model, allowing the analysis of crossing survival curves and including the PH and PO configurations as particular cases. In a general regression setting, the present work proposes a fully likelihood-based approach to fit the YP model. The main idea is to model the baseline hazard via the piecewise exponential (PE) distribution. The approach shares the flexibility of the semiparametric models and the tractability of the parametric representations. An extensive simulation study is developed to evaluate the performance of the proposed model. In addition, we demonstrate how useful is the new method through the analysis of survival times related to patients enrolled in a cancer clinical trial. The simulation results indicate that our model performs well for moderate sample sizes in the general regression setting. A superior performance is also observed with respect to the original YP model designed for the two-sample scenario.