Dataset Information

Data-driven and interpretable machine-learning modeling to explore the fine-scale environmental determinants of malaria vectors biting rates in rural Burkina Faso.

ABSTRACT:

Background

Improving the knowledge and understanding of the environmental determinants of malaria vector abundance at fine spatiotemporal scales is essential to design locally tailored vector control intervention. This work is aimed at exploring the environmental tenets of human-biting activity in the main malaria vectors (Anopheles gambiae s.s., Anopheles coluzzii and Anopheles funestus) in the health district of Diébougou, rural Burkina Faso.

Methods

Anopheles human-biting activity was monitored in 27 villages during 15 months (in 2017-2018), and environmental variables (meteorological and landscape) were extracted from high-resolution satellite imagery. A two-step data-driven modeling study was then carried out. Correlation coefficients between the biting rates of each vector species and the environmental variables taken at various temporal lags and spatial distances from the biting events were first calculated. Then, multivariate machine-learning models were generated and interpreted to (i) pinpoint primary and secondary environmental drivers of variation in the biting rates of each species and (ii) identify complex associations between the environmental conditions and the biting rates.

Results

Meteorological and landscape variables were often significantly correlated with the vectors' biting rates. Many nonlinear associations and thresholds were unveiled by the multivariate models, for both meteorological and landscape variables. From these results, several aspects of the bio-ecology of the main malaria vectors were identified or hypothesized for the Diébougou area, including breeding site typologies, development and survival rates in relation to weather, flight ranges from breeding sites and dispersal related to landscape openness.

Conclusions

Using high-resolution data in an interpretable machine-learning modeling framework proved to be an efficient way to enhance the knowledge of the complex links between the environment and the malaria vectors at a local scale. More broadly, the emerging field of interpretable machine learning has significant potential to help improve our understanding of the complex processes leading to malaria transmission, and to aid in developing operational tools to support the fight against the disease (e.g. vector control intervention plans, seasonal maps of predicted biting rates, early warning systems).

SUBMITTER: Taconet P

PROVIDER: S-EPMC8243492 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundBurkina Faso's immunization program has benefited regularly from national and international support. However, national immunization coverage has been irregular, decreasing from 34.7% in 1993 to 29.3% in 1998, and then increasing to 43.9% in 2003. Undoubtedly, a variety of factors contributed to this pattern. This study aims to identify both individual and systemic factors associated with complete vaccination in 1998 and 2003 and relate them to variations in national and international policies and strategies on vaccination of rural Burkinabé children aged 12-23 months.MethodsData from the 1998 and 2003 Demographic and Health Surveys and the Ministry of Health's 1997 and 2002 Statistical Yearbooks, as well as individual interviews with central and regional decision-makers and with field workers in Burkina's healthcare system, were used to carry out a multilevel study that included 805 children in 1998 and 1,360 children in 2003, aged 12-23 months, spread over 44 and 48 rural health districts respectively.ResultsIn rural areas, complete vaccination coverage went from 25.9% in 1998 to 41.2% in 2003. District resources had no significant effect on coverage and the impact of education declined over time. The factors that continued to have the greatest impact on coverage rates were poverty, with its various dimensions, and the utilization of other healthcare services. However, these factors do not explain the persistent differences in complete vaccination between districts. In 2003, despite a trend toward district homogenization, differences between health districts still accounted for a 7.4% variance in complete vaccination.ConclusionComplete vaccination coverage of children is improving in a context of worsening poverty. Education no longer represents an advantage in relation to vaccination. Continuity from prenatal care to institutional delivery creates a loyalty to healthcare services and is the most significant and stable explanatory factor associated with complete vaccination of children. Healthcare service utilization is the result of a dynamic process of interaction between communities and the healthcare system; understanding this process is the key to understanding better the factors underlying the complete vaccination of children.