Statistical analysis of exacerbation rates in COPD: TRISTAN and ISOLDE revisited

Abstract

Various statistical methods have been used to measure the impact of treatment on chronic obstructive pulmonary disease (COPD) exacerbations. Poisson regression has recently been recommended as the appropriate method but the model does not satisfactorily account for variability between patients. In contrast, use of a negative binomial model, which corresponds to assuming a separate Poisson parameter for each patient, offers a more appealing approach. The present paper reviews analysis methods, with particular focus on the negative binomial model. To illustrate the differences that arise from using different analysis methods, we have reanalysed data from two large studies which, among other objectives, investigated the effectiveness of inhaled corticosteroids in reducing COPD exacerbation rates. Using the negative binomial model to reanalyse data from the TRISTAN and ISOLDE studies, the overall estimates of exacerbation rates on each treatment arm are higher and the confidence intervals for comparisons between treatments are wider, but the overall conclusions of TRISTAN and ISOLDE regarding reduction of exacerbations remain unchanged. The negative binomial approach appears to provide a better fit to the distribution of the data than earlier methods and is currently the method of choice. Research needs to continue on further methods to improve the analysis of exacerbation data.