Infections caused by extended-spectrum beta-lactamases producing Enterobacteriaceae: clinical and economic impact in patients hospitalized in 2 teaching hospitals in Dakar, Senegal

Abstract

Background: Infections caused by extended-spectrum beta-lactamases producing Enterobacteriaceae (ESBL-E) are of major concern in clinical practice because of limited therapeutic options effective to treat them. Published studies showed that ESBL-E, widely spread in Europe, United States or Asia; are also frequent in Africa. However, the impact of ESBL-E infections is yet to be adequately determined in Sub-Saharan African countries, particularly in Senegal. The aim of our study was to estimate the incidence rate of ESBL-E infections and to assess their clinical and economic impact in Senegal.

Methods: Two retrospective cohort studies were conducted in patients hospitalized from April to October 2012. A classic retrospective cohort study comparing patients infected by an Enterobacteriaceae producer of ESBL (ESBL+) and patients infected by an Enterobacteriaceae non-producer of ESBL (ESBL-) was carried out for fatal outcomes. Besides, a retrospective parallel cohort study comparing infected patients by an ESBL+ and ESBL- versus uninfected patients was carried out for the excess LOS analyses. Multivariable regression analysis was performed to identify risk factors for fatal outcomes. A multistate model and a cost-of-illness analysis were used to estimate respectively the excess length of stay (LOS) attributable to ESBL production and costs associated. Cox proportional hazards models were used to assess the independent effect of ESBL+ and ESBL- infections on LOS.

Results: The incidence rate of ESBL-E infections was 3 cases/1000 patient-days (95 % CI: 2.4-3.5 cases/1000 patient-days). Case fatality rate was higher in ESBL+ than in ESBL- infections (47.3 % versus 22.4 %, p = 0.0006). Multivariable analysis indicated that risk factors for fatal outcomes were the production of ESBL (OR = 5.7, 95 % CI: 3.2-29.6, p = 0.015) or being under mechanical ventilation (OR = 5.6, 95 % CI: 2.9-57.5, p = 0.030). Newborns and patients suffering from meningitidis or cancer were patients at-risk for fatal outcomes. ESBL production increased hospital LOS (+4 days) and reduced significantly the hazard of discharge after controlling for confounders (HR = 0.3, 95 % CI:0.2-0.4). The additional cost associated with ESBL-production of €100 is substantial given the lower-middle-income status of Senegal.

Conclusion: Our findings show an important clinical and economic impact of ESBL-E infections in Senegal and emphasize the need to implement adequate infection control measures to reduce their incidence rate. An antibiotic stewardship program is also crucial to preserve the effectiveness of our last-resort antibiotic drugs.

Keywords: Africa; Antibiotic resistance; Cost-of-illness; ESBL; Economic; Enterobacteriaceae; Impact; Multistate model.

Fig. 1

Multistate model used for the excess length of stay analysis. Every patient enters the model in state 1 on the day of admission, make a transition into state 2 at the time of infection (ESBL+ or ESBL-) then move to the 3 at the time of discharge or death. Uninfected patients enter in state 1 and move to state 3 without transition through state 2