Investigating the compounding effects of socio-economic factors on infectious disease dynamics of vector-borne diseases

Background:

The spread of diseases, especially those transmitted by mosquito vectors, such as malaria, dengue, and Zika, is significantly influenced by a myriad of factors, among which socio-economic conditions play not the last role. These conditions, including factors such as income levels, urbanization, access to healthcare, and education, directly affect the vulnerability of populations to these diseases. For instance, poorer communities often experience higher exposure risks due to inadequate housing, limited access to preventive measures, and the proximity of mosquito breeding sites. Despite the acknowledged impact of socio-economic factors on disease spread, their explicit integration into predictive modelling of vector-borne diseases has been limited. To date, investigations into the extent of their influence mechanism have not been pursued with the depth required for comprehensive understanding and effective intervention planning. Compounding this challenge is the ongoing global climate change, which not only alters the distribution and lifecycle of vectors like mosquitoes but also exacerbates the socio-economic vulnerabilities of populations.

Aim/s:

Given these intertwined challenges, there is a critical need to integrate socio-economic and demographic factors into the modelling of future pandemic preparedness. This integration aims not only to enhance the accuracy of predictive models but also to deepen the understanding of the interplay between socio-economic conditions, demographic and climate changes, and their impact on spread of infections. By doing so, more effective strategies for disease prevention and control can be developed that are responsive to the realities of climate change and socio-economic disparities.

AI methods:

This work will integrate machine learning methods (including space and time aware neural networks, transformers, and other attention-based architectures) to co-analyse relevant environmental, population and socio-economic data streams. Further, trained ML models will be integrated into existing infectious disease models to improve their process simulation and prediction capabilities.

Keywords:

Climate change, socio-economic determinants, infectious dieseases modelling, machine learning, data extraction

to the top