Integrating genomic signatures for treatment selection with Bayesian predictive failure time models

Abstract

Over the past decade, a tremendous amount of resources have been dedicated to the pursuit of developing genomic signatures that effectively match patients with targeted therapies. Although dozens of therapies that target DNA mutations have been developed, the practice of studying single candidate genes has limited our understanding of cancer. Moreover, many studies of multiple-gene signatures have been conducted for the purpose of identifying prognostic risk cohorts, and thus are limited for selecting personalized treatments. Existing statistical methods for treatment selection often model treatment-by-covariate interactions that are difficult to specify, and require prohibitively large patient cohorts. In this article, we describe a Bayesian predictive failure time (BPFT) model for treatment selection that integrates multiple-gene signatures. Our approach relies on a heuristic measure of similarity that determines the extent to which historically treated patients contribute to the outcome prediction of new patients. The similarity measure, which can be obtained from existing clustering methods, imparts robustness to the underlying stochastic data structure, which enhances feasibility in the presence of small samples. Performance of the proposed method is evaluated in simulation studies, and its application is demonstrated through a study of lung squamous cell carcinoma. Our BPFT approach is shown to effectively leverage genomic signatures to match patients to the therapies that are most beneficial for prolonging their survival.

Bayesian personalized treatment selection strategies that integrate predictive with prognostic determinants

“…Alternatively, we may investigate signatures that have been reported in the literature from different studies. For example, Ma et al (2017) investigated several literature-reported genomic signatures for patients with lung squamous cell carcinoma, and they found that a 13-gene signature developed by (Kaufman et al, 2014) performed well for treatment selection. Thus, the approach is encouraging given that results obtained from these signatures are generally robust due to the external cross validation process.…”

“…We use to denote the specific pairwise similarity metric between new patient and the i th patient. Then assume that determines the degree of influence imposed by i th patient in estimating the effectiveness of the treatment received for the new patient, which can be achieved via a power prior model (Ibrahim, Chen, & Sinha, ; Ma et al., , ). Let represent the number of previous treated patients receiving treatment j .…”

“…Conventional approaches should be considered limited, however, as they often rely of assumptions of statistical exchangeability among patients within biomarker defined subgroups or rely on linear models despite the presence of large numbers of potentially correlated inputs and interaction terms. Recently, Bayesian approaches that predict the personalized treatment utility for a given individual's tumor on the basis of measures of interpatient molecular similarity (Ma, Hobbs, & Stingo, ; Ma, Stingo, & Hobbs, ) have been established using predictive biomarkers stemming from multigene signatures. In both empirical and case studies, the Bayesian predictive methods were shown to effectively leverage a large set of tumor features and substantially outperformed competing methods based on penalized regression (Archer & Williams, ; Geng, Zhang, & Lu, ).…”

Estimating mean local posterior predictive benefit for biomarker-guided treatment strategies

“…4 The low success rate is likely the result of ineffective agents as well as the reliance on trial designs that are inadequate for characterizing treatment benefit 5 among predictive subpopulations, inaccurate thresholds for defining molecular subtypes, and analytical approaches that fail to characterize selection rules based on the joint effects of multiple candidate biomarkers. 6–9…”

“…4 The low success rate is likely the result of ineffective agents as well as the reliance on trial designs that are inadequate for characterizing treatment benefit 5 among predictive subpopulations, inaccurate thresholds for defining molecular subtypes, and analytical approaches that fail to characterize selection rules based on the joint effects of multiple candidate biomarkers. [6][7][8][9] With the recent focus on precision medicine, exploratory studies should be devised to test the reproducibility of candidate biomarkers as well as identify selection rules that delineate patient subpopulations most likely to benefit from biomarker-guided therapies. The effectiveness with which a treatment's utility to a given type of tumor/patient may be inferred from data inherently depends upon the effectiveness with which the design and method of analysis characterize determinants that are predictive of treatment effectiveness from those that are prognostic, or describe the disease extent.…”