Added-value of Mosquito Vector Breeding Sites from Street View Images in the Risk Mapping of Dengue Incidence in Thailand

Project Members:

• Prof. Dr. Peter Haddawy, Faculty of ICT, Mahidol University
• Dr. Dominique Bicout, Biomathematics and Epidemiology, Grenoble-Alpes University, VetAgro Sup, Laue–Langevin Institute, Theory Group.
• Grenoble, France.
• Dr. Myat Su Yin, Faculty of ICT, Mahidol University
• Dr. Yongjua Laosiritaworn, Information Technology Center, Department of Disease Control, Ministry of Public Health, Nonthaburi, Thailand
• Patiwat  Sa-angchai, Faculty of Tropical Medicine, Mahidol University

The primary dengue mosquito vectors breed in containers with sufficient water and nutrition. Outdoor containers can be detected from geotagged images using state-of-the-art deep learning methods.  Eight breeding site container types in Google street view images are detected using convolutional neural networks. We investigate the added value of including container information from geotagged images in predicting dengue risk. To explain the target variable dengue incidence, weather variables are added to complement the container variable predictors. Linear mixed-effects models are built to account for the effects of spatial and seasonal variation in weather and container variables on the dengue incidence. Evaluation is carried out over three provinces in Thailand: Bangkok, Nakhon Si Thammarat, and Krabi in comparison with classic linear models as well as the mixed effect models without container information. The proposed model with the container information outperforms both baseline models in all three provinces. We further perform sensitivity analysis to investigate the sensitivity of dengue incidence to the changes in the number of containers as well as the improvement in the model performance. This is the first work on dengue risk prediction models using container counts from image analysis.