The impact of stopping and starting indoor residual spraying on malaria burden in Uganda

Abstract

The scale-up of malaria control efforts has led to marked reductions in malaria burden over the past twenty years, but progress has slowed. Implementation of indoor residual spraying (IRS) of insecticide, a proven vector control intervention, has been limited and difficult to sustain partly because questions remain on its added impact over widely accepted interventions such as bed nets. Using data from 14 enhanced surveillance health facilities in Uganda, a country with high bed net coverage yet high malaria burden, we estimate the impact of starting and stopping IRS on changes in malaria incidence. We show that stopping IRS was associated with a 5-fold increase in malaria incidence within 10 months, but reinstating IRS was associated with an over 5-fold decrease within 8 months. In areas where IRS was initiated and sustained, malaria incidence dropped by 85% after year 4. IRS could play a critical role in achieving global malaria targets, particularly in areas where progress has stalled.

Fig. 1. Map of Uganda showing study sites (Malaria Reference Centers) and indoor residual spraying (IRS) districts.

Districts not included in the analysis did not have an active Malaria Reference Center during the study period. Objective 1 is to assess the impact of withdrawing IRS after 5 years of sustained use; Objective 2 is to assess the impact of restarting IRS with a single round; and Objective 3 is to assess the impact of initiating and sustaining IRS.

Fig. 2. Timeline summarizing the dates of indoor residual spraying (IRS) campaigns, baseline, and evaluation periods.

Objective 1 is to assess the impact of withdrawing IRS after 5 years of sustained use; Objective 2 is to assess the impact of restarting IRS with a single round; and Objective 3 is to assess the impact of initiating and sustaining IRS. Exact dates of interventions are general; details on intervention dates by site are shown in Supplementary Fig. 1.

Fig. 3. Predicted case counts and adjusted incidence rate ratios (IRR) from multilevel negative binomial model assessing the impact of withdrawing indoor residual spraying (IRS) after 5 years of sustained use.

The blue shaded region on the left represents the 95% confidence interval around the mean predicted case counts across sites from the adjusted regression model. Gray lines represent observed monthly case counts from individual sites. On the right, vertical bars represent the 95% confidence interval around the adjusted IRR (the measure of center for the error bars).

Fig. 4. Predicted case counts and adjusted incidence rate ratios (IRR) from multilevel negative binomial model assessing the impact of restarting indoor residual spraying (IRS) with a single round.

The blue shaded region on the left represents the 95% confidence interval around the mean predicted case counts across sites from the adjusted regression model. Gray lines represent observed monthly case counts from individual sites. On the right, vertical bars represent the 95% confidence interval around the adjusted IRR (the measure of center for the error bars).

Fig. 5. Predicted case counts and adjusted incidence rate ratios (IRR) from multilevel negative binomial model assessing the impact of initiating and sustaining indoor residual spraying (IRS).

The blue shaded region on the left represents the 95% confidence interval around the mean predicted case counts across sites from the adjusted regression model. Gray lines represent observed monthly case counts from individual sites. On the right, vertical bars represent the 95% confidence interval around the adjusted IRR (the measure of center for the error bars).