Agreement among four drug information sources for the occurrence of warfarin drug interactions in Brazilian heart disease patients with a high prevalence of Trypanosoma cruzi infection

The aim of this study was to assess the agreement of four renowned interaction lists on potentially severe warfarin drug interactions (DI) in outpatients at a university hospital in Brazil, specifically in subgroups of Trypanosoma cruzi-infected and non-infected patients and those with previous bleeding episodes. This was a cross-sectional study in which adult outpatients with heart disease and indications for chronic warfarin use were enrolled. The occurrence of potentially severe warfarin DI was evaluated based on the lists provided by three compendia, i.e., Drug Interaction Facts (DIF), Drug Interactions: Analysis and Management (DIAM) and DRUG-REAX, and by the World Health Organization (WHO) Model Formulary. A kappa coefficient was used to calculate the agreement among the sources. A total of 280 patients were studied. Most patients were female (54.6 %) with an average age of 56.8 (standard deviation 13.1) years. The agreement among the four sources was fair (Fleiss' kappa coefficient = 0.295). T. cruzi-infected individuals were less likely to have severe warfarin DI than non-infected patients (p < 0.05 for DIAM, DRUG-REAX and the WHO Model Formulary). Potentially severe DI were more frequent in patients with previous bleeding episodes, based on the DIF compendia (p = 0.007). This evaluation of warfarin DI revealed that the disagreement between compendia is also observed in clinical practice. T. cruzi infection is associated with a lower prevalence of potentially severe warfarin DI, but with a wider variation in its detection. Our results suggest a wide spectrum of discrepancies in detecting heart disease patients at higher risk for severe warfarin DI and a possible heterogeneity in clinical guidance.