Global antibiotic consumption and usage in humans, 2000-18: a spatial modelling study

Abstract

Background: Antimicrobial resistance (AMR) is a serious threat to global public health. WHO emphasises the need for countries to monitor antibiotic consumption to combat AMR. Many low-income and middle-income countries (LMICs) lack surveillance capacity; we aimed to use multiple data sources and statistical models to estimate global antibiotic consumption.

Methods: In this spatial modelling study, we used individual-level data from household surveys to inform a Bayesian geostatistical model of antibiotic usage in children (aged <5 years) with lower respiratory tract infections in LMICs. Antibiotic consumption data were obtained from multiple sources, including IQVIA, WHO, and the European Surveillance of Antimicrobial Consumption Network (ESAC-Net). The estimates of the antibiotic usage model were used alongside sociodemographic and health covariates to inform a model of total antibiotic consumption in LMICs. This was combined with a single model of antibiotic consumption in high-income countries to produce estimates of antibiotic consumption covering 204 countries and 19 years.

Findings: We analysed 209 surveys done between 2000 and 2018, covering 284 045 children with lower respiratory tract infections. We identified large national and subnational variations of antibiotic usage in LMICs, with the lowest levels estimated in sub-Saharan Africa and the highest in eastern Europe and central Asia. We estimated a global antibiotic consumption rate of 14·3 (95% uncertainty interval 13·2-15·6) defined daily doses (DDD) per 1000 population per day in 2018 (40·2 [37·2-43·7] billion DDD), an increase of 46% from 9·8 (9·2-10·5) DDD per 1000 per day in 2000. We identified large spatial disparities, with antibiotic consumption rates varying from 5·0 (4·8-5·3) DDD per 1000 per day in the Philippines to 45·9 DDD per 1000 per day in Greece in 2018. Additionally, we present trends in consumption of different classes of antibiotics for selected Global Burden of Disease study regions using the IQVIA, WHO, and ESAC-net input data. We identified large increases in the consumption of fluoroquinolones and third-generation cephalosporins in North Africa and Middle East, and south Asia.

Interpretation: To our knowledge, this is the first study that incorporates antibiotic usage and consumption data and uses geostatistical modelling techniques to estimate antibiotic consumption for 204 countries from 2000 to 2018. Our analysis identifies both high rates of antibiotic consumption and a lack of access to antibiotics, providing a benchmark for future interventions.

Funding: Fleming Fund, UK Department of Health and Social Care; Wellcome Trust; and Bill & Melinda Gates Foundation.

Figure 1

The percentage of children (aged <5 years) with symptoms of lower respiratory tract infections with caregiver-reported antibiotic usage in low-income and middle-income countries, 2018 Modelled estimates are shown by level two administrative divisions. High-income countries and pixels (1×1 km) with populations of less than ten people are shown in grey.

Figure 2

5 yearly estimates of the percentage of children (aged <5 years) with lower respiratory tract infections with caregiver-reported antibiotic usage in low-income and middle-income countries Modelled estimates are shown by level two administrative divisions. High-income countries and pixels (1×1 km) with populations of less than ten people are shown in grey.

Figure 3

Within-country variation in antibiotic usage in 2000 and 2018 (A) Bars show the range in antibiotic usage for districts within each country; coloured bars represent estimates from 2018 and grey bars represent estimates from 2000. Points represents the mean percentage of antibiotic usage for each country, with diamonds representing 2018 and triangles representing 2000. (B) Bars show the range in the relative deviation from the mean for antibiotic usage in each country; coloured bars represent estimates from 2018 and the grey bars represent estimates from 2000. The 2018 colours are based on the GBD super-regions to which the country belongs, and countries are ordered (on the x-axis) based on the mean antibiotic usage in 2018 (ascending). Countries are labelled using the International Organisation for Standardisation codes. GBD=Global Burden of Disease.

Figure 4

Total antibiotic consumption rates for 2018, with uncertainty intervals Estimates of antibiotic consumption rates in DDD per 1000 population per day. The mean map combines the modelled estimates for LMICs, and the imputed dataset for HICs. The upper and lower maps represent the upper and lower 95% uncertainty intervals for the LMIC model, with HICs shaded. The time-series of total antibiotic consumption rates in DDD per 1000 population per day from 2000 to 20015 is shown in the appendix (p 45). DDD=defined daily doses. HIC=high-income country. LMIC=low-income and middle-income country.

Figure 5

Temporal trends in the total antibiotic consumption rates for GBD super-regions and World Bank income groups Modelled estimates of antibiotic consumption rates in DDD per 1000 population per day from 2000 to 2018. Estimates are plotted as the total for each GBD super-region (solid lines) and each World Bank income group (dashed lines), with the 95% uncertainty intervals represented by the coloured ribbons (not available for high-income countries). DDD=defined daily doses. GBD=Global Burden of Disease.