Development of predictive signatures for treatment selection in precision medicine with survival outcomes

Abstract

For survival endpoints in subgroup selection, a score conversion model is often used to convert the set of biomarkers for each patient into a univariate score and using the median of the univariate scores to divide the patients into biomarker-positive and biomarker-negative subgroups. However, this may lead to bias in patient subgroup identification regarding the 2 issues: (1) treatment is equally effective for all patients and/or there is no subgroup difference; (2) the median value of the univariate scores as a cutoff may be inappropriate if the sizes of the 2 subgroups are differ substantially. We utilize a univariate composite score method to convert the set of patient's candidate biomarkers to a univariate response score. We propose applying the likelihood ratio test (LRT) to assess homogeneity of the sampled patients to address the first issue. In the context of identification of the subgroup of responders in adaptive design to demonstrate improvement of treatment efficacy (adaptive power), we suggest that subgroup selection is carried out if the LRT is significant. For the second issue, we utilize a likelihood-based change-point algorithm to find an optimal cutoff. Our simulation study shows that type I error generally is controlled, while the overall adaptive power to detect treatment effects sacrifices approximately 4.5% for the simulation designs considered by performing the LRT; furthermore, the change-point algorithm outperforms the median cutoff considerably when the subgroup sizes differ substantially.

Subgroup Identification for Time-to-event Data Based on AFT Model

“…The AFT model simply regresses the logarithm of the survival time over the covariates and has an intuitive interpretation. Thus, our work extends that of Chen's [12] in some ways. Our study will focus on the AFT model with the Benjamini-Hochberg procedure to adjust the significance level.…”

“…Cox model combined with a change-point algorithm [12]. This study has evaluated whether the strategy proposed by Chen [12] can be used to subgroup identification in the AFT model with Benjamini-Hochberg procedure to control the FDR.…”

“…Cox model combined with a change-point algorithm [12]. This study has evaluated whether the strategy proposed by Chen [12] can be used to subgroup identification in the AFT model with Benjamini-Hochberg procedure to control the FDR. These evaluations are made through simulations conducted across different sample size, censoring rate, subgroup proportion or predictive covariate size.…”

“…In our study, relatively high-sensitivity and high-specificity are found in subgroup detection and largely improved power is presented in 2-stage biomarker adaptive design across different situations for the univariate AFT model excluding the main effect (Eq_ex) combined with changepoint algorithm. Besides, its corresponding typeⅠerror is controlled well no matter whether LRT is conducted whereas that of Chen's [12] (approximately 0.14) is large without performing the LRT. This is mainly due to that the use of Benjamini-Hochberg procedure that can adjust the significant level in the predictive covariate identification, while it is not clear why the significant level of the Cox model one is directly set to be 0.001 and 0.0025 in Chen's study [12].…”

“…When interest lies in the relationship between covariates and duration time, the most popular regression model in survival analysis is Cox proportional hazards model. Chen's research [12] used Cox models to identify predictive covariates. But it only evaluates the performance of classifiers and models when the subgroup proportion is 0.2 and 0.5.…”