Vector-AI: Knowledge-Driven AI Supports for Vector-Borne Disease Analyses Under Climate Change
Background: Vector-borne diseases are severe diseases caused by pathogens like parasites, viruses or bacteria that are transmitted to human and animals from infected hematophagous arthropods li ke mosquitos, ticks and fleas. These diseases, including Malaria, Dengue, Chagas disease, Yellow fever, or Japanese encephalitis, are responsible for 17% of all infectious diseases, leading to more than 700,000 annual deaths worldwide, more than any other causes combined. While others such as chikungunya, leishmaniasis and lymphatic filariasis cause chronic suffering, life-long morbidity, disability and occasional stigmatization. Traditionally, these diseases are known to be widely spread in tropical and sub-tropical areas, severely affecting poorest populations disproportionately. However, their geographical distributions and active seasons are gradually and quickly expanded to much wider latitude and altitude ranges and periods due to different demographic, environmental and social factors like global travel and trade, unplanned urbanization, vector adaptation, and especially global climate change. E.g., for the first time in 20 years in UK, there were more than 2,000 confirmed cases of Malaria in England, Wales and Northern Ireland in 2023. Many areas in UK are highly vulnerable to these diseases such as North Kent marshes and other the coastal marshes of Southeast England and woodland sites. Or from the first outbreak in Croatia in 2010, dengue fever outbreaks have been rapidly emerged in many other EU countries like Italy, Spain and especially France. Aedes aegypti, the main carrier of dengue, has also invaded and been found in 13 different EU countries.
Objectives: Due to their emerging global threats, having effective and explainable early warning systems for vector borne disease outbreaks and deeply understanding their relationships to demographic, environmental and social factors are crucial for disease controls and managements following the strategic guidance from The Global Vector Control Response (GVCR) 2017-2030 approved by World Health Organization (WHO) in 2017. However, they are non-trivial tasks due to many existing challenges, e.g., complicated relationships among relevant risk factors, rapid changes in disease and climate patterns, lack of quantified and qualified data (especially socio-economy one), and (more interestingly) lack of interdisciplinary knowledge among relevant fields like Data Science, Public Health, Geography, Climate, Socio-Economy and Biology.
Methods: In this project, we aim to target those objectives from unified perspectives of Diseases, Healthcare, Climate, Socio-Economy and Biology guided by Artificial Intelligence (Data Science, Machine Learning) for Knowledge Discovery.
Training: This project is highly interdisciplinary, especially in AI, Public Health, Socio-Economy and Bioscience. Hence, they will be trained to obtain necessary knowledge in these relevant fields.
Click here to access the application form