Geographical variability in the likelihood of bloodstream infections due to gram-negative bacteria: correlation with proximity to the equator and health care expenditure

Abstract

Objective: Infections due to Gram-negative bacteria exhibit seasonal trends, with peak infection rates during warmer months. We hypothesized that the likelihood of a bloodstream infection due to Gram-negative bacteria increases with proximity to the equator. We tested this hypothesis and identified geographical, climatic and social factors associated with this variability.

Design: We established a network of 23 international centers in 22 cities.

Setting: De-identified results of positive blood cultures from 2007-2011 and data sources for geographic, climatic and socioeconomic factors were assembled for each center.

Participants: Patients at the 23 centers with positive blood cultures.

Main outcome: Due to variability in the availability of total culture volumes across sites, our primary outcome measure was the fraction of positive blood cultures that yielded Gram-negative bacteria; sources of variability in this outcome measure were explored using meta-regression techniques.

Results: The mean fraction of bacteremia associated with Gram-negative bacteria was 48.4% (range 26.4% to 61.8%). Although not all sites displayed significant seasonality, the overall P-value for seasonal oscillation was significant (P<0.001). In univariate meta-regression models, temperature, latitude, latitude squared, longitude, per capita gross domestic product and percent of gross domestic product spent on healthcare were all associated with the fraction of bacteremia due to Gram-negative bacteria. In multivariable models, only percent of gross domestic product spent on healthcare and distance from the equator (ie. latitude squared) were significantly associated with the fraction of bacteremia due to Gram-negative bacteria.

Conclusions: The likelihood of bacteremia due to Gram-negative bacteria varies markedly between cities, in a manner that appears to have both geographic (latitude) and socioeconomic (proportion gross domestic product devoted to health spending) determinants. Thus, the optimal approach to initial management of suspected bacteremia may be geographically specific. The rapid emergence of highly antibiotic-resistant Gram-negative pathogens may have geographically specific impacts.

Figure 1. Locations of participating sites.

Figure 2. Fraction of bloodstream infections due to Gram-negative bacteria by site (lowest to highest).

Note that X-axis is presented on a natural log scale. The area of rectangles is inverse to the variance of log(odds) of bloodstream infection due to Gram-negative bacteria; horizontal lines represent 95% confidence intervals.

Figure 3. Fitted waveforms for bloodstream infections due to Gram-negative bacteria from Poisson models adjusted for culture frequency for data available at 13 sites.

Arithmetic means for northern hemisphere (solid curve) and southern hemisphere (dashed curve) are represented by black curves. Curves for individual sites from northern hemisphere (solid curves) and southern hemisphere (dashed curves) are presented in gray.

Figure 4. Relationship between peak month of occurrence of bloodstream infection due to Gram-negative bacteria (Y-axis) and latitude (X-axis) (circles).

It can be seen that while there is a strong linear overall relationship between month of peak occurrence and latitude, this largely reflects the inversion of summer and winter months in the northern and southern hemispheres (fitted solid black line). Within the northern hemisphere (fitted dashed line) and the southern hemisphere (fitted gray line) there is no relationship between distance from the equator and month of peak incidence.

Figure 5. Mean monthly fraction of bloodstream infections due to Gram-negative bacteria (Y-axis) plotted against latitude by study site (black circles).

Predicted mean monthly fractions of bloodstream infections due to Gram-negative bacteria, based on a meta-regression model that incorporated latitude-squared, percent of GDP spent on healthcare, and mean annual temperature, are plotted as gray circles. It can be seen that the 3-coefficient model resulted in excellent prediction of Gram-negative bacterial bloodstream infection fraction, and in some cases predictions are sufficiently precise that labels are superimposed.

Figure 6. Non-linear effects of latitude on risk of bloodstream infection due to Gram-negative bacteria, among bacteremic individuals, according to distance in degrees from equator.

The figure is based on a coefficient for latitude-squared of -0.0003, as presented in Table 4. The log-odds of bloodstream infections due to Gram-negative bacteria (logit, blue curve) is calculated as −0.0003 x latitude², while the odds ratio for GNB (relative to the odds at the equator) is this quantity exponentiated (red curve). The change in odds ratio per 10 degree increment is non-constant by latitude, and is presented as the green curve.