Evidence Hub

Advancing methods for fair outcome comparisons in clinical trials: Application to empagliflozin in heart failure using the win ratio

John Gregson

Vivli, 2025

Abstract

Heart failure is a long-term condition where the heart cannot pump blood as well as it should. This affects millions of people worldwide, causing symptoms such as breathlessness, fatigue, and frequent hospital stays. Many new treatments are tested in clinical trials, and it is important that these trials use the best possible methods to assess whether treatments work. In clinical trials, researchers often look at patient outcomes such as survival or whether patients need to be hospitalised. To make these comparisons fair, we usually adjust for differences in patient characteristics such as age, sex, or other health conditions. This process is called covariate adjustment. A newer approach called the win ratio is increasingly being used in heart failure studies. The win ratio compares patients across several outcomes in order of importance—for example, survival is considered more important than hospitalisation. This approach can give a fuller picture of treatment effects, but it is not yet clear how best to combine it with covariate adjustment. This analysis will explore different ways to apply covariate adjustment when using the win ratio. To do this, we will use two approaches. First, we will run computer-based simulations to test different strategies, such as stratification (grouping patients by certain characteristics), other statistical methods (mathematical models), and using risk scores that summarise patient risk factors. Second, we will apply these approaches to data…

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free