Improving the analysis of composite endpoints in rare disease trials
- PDF / 757,642 Bytes
- 9 Pages / 595 x 791 pts Page_size
- 55 Downloads / 206 Views
RESEARCH
Open Access
Improving the analysis of composite endpoints in rare disease trials Martina McMenamin1*
, Anna Berglind2 and James M. S. Wason1,3
Abstract Background: Composite 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. Methods: We 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. Results: For 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. Conclusions: The 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. Keywords: Responder analysis, Composite endpoints, Improving efficiency
Background For stakeholders in rare disease communities, it is imperative to keep in mind that rare diseases are far from ‘rare’ for those whose lives they consume. The last few decades have seen a societal shift which recognises this and has resulted in a much greater focus on rare disease research. This is characterised by a surge in patient advocacy groups, a shift in regulation and incentives, increased government funding of rare disease research and advances in technologies to improve international communication
between rare disease experts and patients [1]. Despite this, for most rare diseases if
Data Loading...
