Decision support systems (DSSs) are recognized as important tools, capable of processing high volumes of data and increasing productivity. The usability of these tools affects their effectiveness. By evaluating the interactions between registered nurses (RNs) and the DSSs, this study explores how they impact RN decision-making. This study analyzed 24 months (2011–2012) of data collected in Brazil in two units of a large, public, urban hospital in São Paulo that uses a nurse documentation system with an embedded DSS based on NANDA-I. Using mixed effects logistic regression, this study analyzed the agreement between RNs and a DSS when selecting nursing diagnoses. Results suggest that the agreement is mediated by characteristics of the RNs (education and experience) as well as units and year of encounter. Surprisingly, disagreement between RN and DSS when selecting defining characteristics (DC) had positive effects on the odds of agreement on diagnoses. Our results suggest that DSSs support nurses' clinical decision making, but the nurse's clinical judgment is the mediating factor. More research is necessary.