Escherichia coli from urine samples of pregnant women as an indicator for antimicrobial resistance in the community: a field study from rural Burkina Faso

Background In low- and middle-income countries, surveillance of antimicrobial resistance (AMR) is mostly hospital-based and, in view of poor access to clinical microbiology, biased to more resistant pathogens. We aimed to assess AMR among Escherichia coli isolates obtained from urine cultures of pregnant women as an indicator for community AMR and compared the AMR results with those from E. coli isolates obtained from febrile patients in previously published clinical surveillance studies conducted within the same population in Nanoro, rural Burkina Faso. We furthermore explored feasibility of adding urine culture to standard antenatal care in a rural sub-Saharan African setting. Methods Between October 2016-September 2018, midstream urine samples collected as part of routine antenatal care in Nanoro district were cultured by a dipslide method and screened for antibiotic residues. Significant growth was defined as a pure culture of Enterobacterales at counts of >= 10(4) colony forming units/ml. Results Significant growth was observed in 202/5934 (3.4%) cultures; E. coli represented 155 (76.7%) of isolates. Among E. coli isolates, resistance rates to ampicillin, cotrimoxazole and ciprofloxacin were respectively 65.8%, 64.4% 16.2%, compared to 89.5%, 89.5% and 62.5% among E. coli from clinical isolates (n = 48 of which 45 from blood cultures). Proportions of extended spectrum beta-lactamase producers and multidrug resistance were 3.2% and 5.2% among E. coli isolates from urine in pregnant women versus 35.4%, and 60.4% respectively among clinical isolates. Conclusions The E. coli isolates obtained from healthy pregnant women had significantly lower AMR rates compared to clinical E. coli isolates, probably reflecting the lower antibiotic pressure in the pregnant women population. Adding urine culture to the routine urine analysis (dipstick) of antenatal care was feasible. The dipslide culture method was affordable and user-friendly and allowed on-site inoculation and easy transport; challenges were contamination (midstream urine sampling) and the semi-quantitative reading. Provided confirmation of the present findings in other settings, E. coli from urine samples in pregnant women may be a potential indicator for benchmarking, comparing, and monitoring community AMR rates across populations over different countries and regions.