Improving the analysis of composite endpoints in rare disease trials

Abstract

BackgroundComposite endpoints are recommended in rare diseases to increase power and/or to sufficiently capture complexity. Often, they are in the form of responder indices which contain a mixture of continuous and binary components. Analyses of these outcomes typically treat them as binary, thus only using the dichotomisations of continuous components. The augmented binary method offers a more efficient alternative and is therefore especially useful for rare diseases. Previous work has indicated the method may have poorer statistical properties when the sample size is small. Here we investigate small sample properties and implement small sample corrections.MethodsWe re-sample from a previous trial with sample sizes varying from 30 to 80. We apply the standard binary and augmented binary methods and determine the power, type I error rate, coverage and average confidence interval width for each of the estimators. We implement Firth’s adjustment for the binary component models and a small sample variance correction for the generalized estimating equations, applying the small sample adjusted methods to each sub-sample as before for comparison.ResultsFor the log-odds treatment effect the power of the augmented binary method is 20-55% compared to 12-20% for the standard binary method. Both methods have approximately nominal type I error rates. The difference in response probabilities exhibit similar power but both unadjusted methods demonstrate type I error rates of 6–8%. The small sample corrected methods have approximately nominal type I error rates. On both scales, the reduction in average confidence interval width when using the adjusted augmented binary method is 17–18%. This is equivalent to requiring a 32% smaller sample size to achieve the same statistical power.ConclusionsThe augmented binary method with small sample corrections provides a substantial improvement for rare disease trials using composite endpoints. We recommend the use of the method for the primary analysis in relevant rare disease trials. We emphasise that the method should be used alongside other efforts in improving the quality of evidence generated from rare disease trials rather than replace them.Electronic supplementary materialThe online version of this article (10.1186/s13023-018-0819-1) contains supplementary material, which is available to authorized users.

Analysis of responder-based endpoints: improving power through utilising continuous components

“…The original motivation was solid-tumour oncology (6,7), but subsequent papers have focused on developing the methodology for rheumatology (8) and rare diseases using composite endpoints (9). A detailed description of how to fit the method is provided in the supplementary material.…”

Analysis of responder-based endpoints: improving power through utilising continuous components

“…The original motivation was solid-tumour oncology (10,11), but subsequent papers have focused on developing the methodology for rheumatology (12) and rare diseases using composite endpoints (13).…”

Digital Twins and the Emerging Science of Self: Implications for Digital Health Experience Design and “Small” Data

“…Putting all the value, promise, and hype of Big Data aside, the digital twin for health has a small data requirement. It is becoming increasingly clear that RCT and group methods, although still quite valuable, are insufficient as treatments and testing move toward the precision of inherent individual differences, which are reflected in every person and every treatment response (positive or negative) (Gagne et al, 2014;Richter et al, 2015;Hilgers et al, 2016;McMenamin et al, 2018). The quantified self, with the "self " as the primary unit of analysis, was always intended for the individual to benefit from the added detail of self-observation.…”