The results of the indirect comparison support the hypothesis that budesonide/formoterol is associated with fewer pneumonia events than salmeterol/fluticasone in chronic obstructive pulmonary disease. The limitations of the analysis are that the results from a single study, TORCH, have a large bearing on the overall findings of the analysis, and that there is heterogeneity in the length and the dosing of the included studies, although it does not appear that heterogeneity affected the reported results. Another important limitation is the lack of predefined diagnostic standards for pneumonia in these studies.