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]

Introduction: Schistosomiasis is a chronic parasitic trematode disease that affects over 240 million people worldwide. The Schistosoma lifecycle is complex, involving transmission via specific intermediate-host freshwater snails. Predictive mathematical models of Schistosoma transmission have often chosen to simplify or ignore the details of environmental human-snail interaction in their analyses. Schistosome transmission models now aim to provide better precision for policy planning of elimination of transmission. This heightens the importance of including the environmental complexity of vector-pathogen interaction in order to make more accurate projections. Methodology and principal findings: We propose a nonlinear snail force of infection (FOI) that takes into account an intermediate larval stage (miracidium) and snail biology. We focused, in particular, on the effects of snail force of infection (FOI) on the impact of mass drug administration (MDA) in human communities. The proposed (modified) model was compared to a conventional model in terms of their predictions. A longitudinal dataset generated in Kenya field studies was used for model calibration and validation. For each sample community, we calibrated modified and conventional model systems, then used them to model outcomes for a range of MDA regimens. In most cases, the modified model predicted more vigorous post-MDA rebound, with faster relapse to baseline levels of infection. The effect was pronounced in higher risk communities. When compared to observed data, only the modified system was able to successfully predict persistent rebound of Schistosoma infection. Conclusion and significance: The observed impact of varying location-specific snail inputs sheds light on the diverse MDA response patterns noted in operational research on schistosomiasis control, such as the recent SCORE project. Efficiency of human-to-snail transmission is likely to be much higher than predicted by standard models, which, in practice, will make local elimination by implementation of MDA alone highly unlikely, even over a multi-decade period. [ABSTRACT FROM AUTHOR]