Introducing the Treatment Hierarchy Question in Network Meta-Analysis

Abstract

Comparative effectiveness research using network meta-analysis can present a hierarchy of competing treatments, from the most to the least preferable option. However, in published reviews, the research question associated with the hierarchy of multiple interventions is typically not clearly defined. Here we introduce the novel notion of a treatment hierarchy question that describes the criterion for choosing a specific treatment over one or more competing alternatives. For example, stakeholders might ask which treatment is most likely to improve mean survival by at least 2 years, or which treatment is associated with the longest mean survival. We discuss the most commonly used ranking metrics (quantities that compare the estimated treatment-specific effects), how the ranking metrics produce a treatment hierarchy, and the type of treatment hierarchy question that each ranking metric can answer. We show that the ranking metrics encompass the uncertainty in the estimation of the treatment effects in different ways, which results in different treatment hierarchies. When using network meta-analyses that aim to rank treatments, investigators should state the treatment hierarchy question they aim to address and employ the appropriate ranking metric to answer it. Following this new proposal will avoid some controversies that have arisen in comparative effectiveness research.

Keywords: multiple treatments; network meta-analysis; probability; ranking; surface under the cumulative ranking curve; treatment hierarchy.

Figure 1

Hypothetical example of 3 interventions (A, B, and C) aiming to reduce low-density lipoprotein cholesterol (LDL-C) levels. The distributions refer to the true population mean for posttreatment LDL-C levels and is the result of the synthesis of randomized trials that compare pairs of treatments.

Figure 2

Distributions of the absolute estimands () of 3 active treatments (A, B, and C) and a placebo (P) with means and standard deviations SD_i in a hypothetical example. A) Scenario 1; B) scenario 2.

Figure 3

Differences in treatment hierarchy obtained from the surface under the cumulative ranking curve (SUCRA) (panel A) and from the probability of a treatment’s having the best mean outcome value (panel B) when the standard deviation (SD) for the absolute estimand of treatment C, , increases from 1 to 10. The other effects are = 2, = 1, = 1, = 1.5, = 1, = 2, and = 1. BV, best value.