Key Food Hygiene Behaviors to Reduce Microbial Contamination of Complementary Foods in Rural Bangladesh

Abstract

Microbial contamination of complementary foods puts young children at risk of developing intestinal infections and could be reduced by improved handwashing and food hygiene practices. We aimed to identify which promoted food hygiene practices are associated with reduced complementary food contamination in a rural population in Bangladesh. We collected cross-sectional data on reported and observed maternal food hygiene behaviors and measured Escherichia coli counts as an indicator of microbial contamination in complementary food samples from 342 children of women enrolled in the Food and Agricultural Approaches to Reducing Malnutrition trial in Sylhet, Bangladesh. We used multivariable logistic regression to examine associations of food hygiene behaviors with food contamination. Approximately 46% of complementary food samples had detectable levels of E. coli. Handwashing with soap at critical times and fresh preparation of food before feeding were strongly associated with reduced odds of food sample contamination (odds ratio [OR]: 0.8, 95% confidence interval [CI]: 0.6-0.9 and OR: 0.3, 95% CI: 0.1-0.7, respectively); in contrast, there was no or only weak evidence that reheating of stored food, safe food storage, and cleanliness of feeding utensils reduced contamination. Reduction in food contamination could be more than halved only when several food hygiene behaviors were practiced in combination. In conclusion, single food hygiene practices showed limited potential and a combined practice of multiple food hygiene behaviors may be needed to achieve a substantial reduction of complementary food contamination.

Figure 1.

Association of reported maternal food hygiene behaviors and complementary food contamination in Sylhet, Bangladesh. Odds ratios (OR) of Escherichia coli contamination in complementary food samples (N = 342), with 95% confidence intervals from multilevel multivariable regression model with reported maternal food hygiene behaviors, adjusted for temperature and humidity of the food storage area, food type, food storage time, household wealth, maternal literacy, and intervention allocation, with settlement random effects.

Figure 2.

Association of observed food hygiene behaviors and spot‐checks and complementary food contamination in Sylhet, Bangladesh. Odds ratios (OR) of Escherichia coli contamination in complementary food samples (N = 342), with 95% confidence intervals, from multilevel multivariable regression model with observed food hygiene behaviors and spot‐checks, adjusted for temperature and humidity of the food storage area, food type, food storage time, household wealth, maternal literacy, and intervention allocation, with settlement random effects.

Figure 3.

Predicted probabilities of Escherichia coli complementary food contamination in Sylhet, Bangladesh. Marginal probabilities of E. coli contamination and (A) reported handwashing at critical times by safe storage, (B) observed utensils and food reheating status by storage temperature. Results are from multilevel multivariable regression models, adjusted for temperature and humidity of the food storage area, food type, food storage time, household wealth, maternal literacy, and intervention allocation, with settlement random effects. Dotted lines: Clean utensils. N = 342. This figure appears in color at www.ajtmh.org.

Figure 4.

Population attributable fractions of food hygiene behaviors in Sylhet, Bangladesh. Population attributable fractions (PAF) were calculated following multivariable logistic regression with robust standard errors for A) reported food hygiene behaviors and B) observed food hygiene behaviors and spot‐checks in households (N = 342). PAFs are shown in % with 95% confidence intervals.