Search

Targeted environmental and ecosystem management remain crucial in control of dengue. However, providing detailed environmental information on a large scale to effectively target dengue control efforts remains a challenge. An important piece of such information is the extent of the presence of potential dengue vector breeding sites, which consist primarily of open containers such as ceramic jars, buckets, old tires, and flowerpots. In this paper we present the design and implementation of a pipeline to detect outdoor open containers which constitute potential dengue vector breeding sites from geotagged images and to create highly detailed container density maps at unprecedented scale. We implement the approach using Google Street View images which have the advantage of broad coverage and of often being two to three years old which allows correlation analyses of container counts against historical data from manual surveys. Containers comprising eight of the most common breeding sites are detected in the images using convolutional neural network transfer learning. Over a test set of images the object recognition algorithm has an accuracy of 0.91 in terms of F-score. Container density counts are generated and displayed on a decision support dashboard. Analyses of the approach are carried out over three provinces in Thailand. The container counts obtained agree well with container counts from available manual surveys. Multi-variate linear regression relating densities of the eight container types to larval survey data shows good prediction of larval index values with an R-squared of 0.674. To delineate conditions under which the container density counts are indicative of larval counts, a number of factors affecting correlation with larval survey data are analyzed. We conclude that creation of container density maps from geotagged images is a promising approach to providing detailed risk maps at large scale. [ABSTRACT FROM AUTHOR]

Background: Although trachoma causes more cases of preventable blindness than any other infectious disease, a combination of strategies is reducing its global prevalence. As a district moves toward eliminating trachoma as a public health problem, national programs conduct trachoma impact surveys (TIS) to assess whether to stop preventative interventions and trachoma surveillance surveys (TSS) to determine whether the prevalence of active trachoma has rebounded after interventions have halted. In some contexts, programs also conduct trachomatous trichiasis (TT)-only surveys. A few costing studies of trachoma prevalence surveys exist, but none examine TIS, TSS, or TT-only surveys. Methodology/Principal findings: We assessed the incremental financial cost to the national program of TIS, TSS, and TT-only surveys, which are standardized cluster-sampled prevalence surveys. We conducted a retrospective review of expenditures and grant disbursements for TIS and TSS in 322 evaluation units in 11 countries between 2011 and 2018. We also assessed the costs of three pilot and five standard TT-only surveys in four countries between 2017 and 2018. The median cost of TIS and TSS was $8,298 per evaluation unit [interquartile range (IQR): $6,532–$10,111, 2017 USD]. Based on a linear regression with bootstrapped confidence intervals, after controlling for country, costs per survey did not change significantly over time but did decline by $83 per survey implemented in a single round (95% CI: -$108 –-$63). Of total costs, 80% went to survey fieldwork; of that, 58% went towards per diems and 38% towards travel. TT-only surveys cost a median of $9,707 (IQR: $8,537–$11,635); within a given country, they cost slightly more (106% [IQR: 94%–136%]) than TIS and TSS. Conclusions/Significance: The World Health Organization requires trachoma prevalence estimates for validating the elimination of trachoma as a public health problem. This study will help programs improve their planning as they assemble resources for that effort. [ABSTRACT FROM AUTHOR]