In this study, we assessed the potential severity of MAEs identified by direct observation in a Brazilian university hospital. The frequency of errors classified as potentially moderate and severe in our study was higher than that in international studies [3, 6, 10, 13,14,15]. The average severity score for MAEs was also higher (5.2) than those reported by Dean and Barber [10] (2.7) and Taxis and Barber [13] (3.1). We do not know the reasons why both the frequency of severe errors and the average severity score were high in our study. However, we do know that some related factors may have contributed to these findings, such as the intravenous route of administration and use of potentially dangerous medications, which are already known to cause the greatest harm to patients when an error occurs [5, 16, 17].

A study conducted in a Brazilian university hospital found a greater association between the intravenous administration route and the occurrence of errors, especially in the medication preparation phase [18]. The relationship between the severity of potential errors and the intravenous administration route is well established. A similar study involving a sample of 10 wards from two hospitals in England showed that errors in intravenous administration occurred in half of the doses administered and caused potential harm in one-third of the cases [19]. Another similar study was conducted in Germany, in which the same author found that 3% of 65 MAEs associated with the intravenous route of administration were severe. Several international studies have demonstrated the high degree of severity of errors associated with intravenous administration [15, 17, 19, 20]. However, there is no information on the severity of MAEs in Latin America, especially Brazil. Thus, it is necessary to better investigate the potential for harms caused by medication errors to patients, especially in low- and middle-income countries [3, 5, 15, 21].

Another important finding was that almost half of the errors assessed as potentially severe were technical errors, which differs from the results found in national and international literature [5, 14, 15]. Furthermore, the potentially severe errors involved categories A, J, and B medications, with insulin being the main medication. The literature indicates that medication errors related to insulin are common, and approximately one-third of these cases involve fatal errors. Nguyen et al. [22]. examined insulin administration and found that most errors were potentially moderate and severe, emphasizing the need for interventions focused on clinically important errors because insulin requires timely dosing, administration, and careful monitoring (Additional file 5).

When studying the incidence or prevalence of medication errors, it is important to determine their clinical significance. However, it is often difficult to do so, because in many studies, the actual clinical outcomes are unknown due to the lack of longitudinal follow-up of patients or researchers intervening to prevent errors from causing harm to patients. There are several methods for assessing error severity. The two most common are the National Coordinating Council for Medication Error Reporting and Prevention severity index and the Dean and Barber method [10]. This was the first study using a validated scale to assess the severity of errors in Brazil [12]. The scale developed by Dean and Barber10 seems to be more suitable for use in research [23]. Assessment of potential error severity is complex and can be influenced by many factors. The use of this scale in future research may help determine the clinical significance of medication errors more clearly in the Brazilian context, contributing to the development of interventions aimed at reducing the associated harm. To the best of our knowledge, this is the first study on MAE assessment that has been conducted using a validated, reliable scale for potential error severity in Brazil.