Using machine learning to predict vector-borne diseases in a changing climate

Vector-borne diseases are responsible for over 700,000 deaths annually and are expected to spread to new regions and become more frequent due to climate change. This is primarily because vectors (such as insects and ticks) are ectothermic ("cold-blooded") and highly influenced by environmental conditions.

We are broadly interested in better understanding how climate change, in combination with land use changes, will affect the spread and frequency of vector-borne diseases. This will be achieved by using machine learning models, such as random forest and deep learning algorithms, to predict disease spread and frequency. By adopting a One Health approach, where we consider human health as interconnected with animal and environmental health, we will integrate multiple data sources (e.g., climate, land use, socio-economic factors, human health, and animal health) to improve our predictions.

As an example, in the EU project Planet4Health, we will employ various machine learning models to predict outbreaks of vector-borne diseases (leishmania and mosquito-borne diseases) in the Iberian Peninsula. The project aims to identify the model that gives the most accurate and meaningful predictions, and later incorporate it as part of an early warning systems for predicting such outbreaks.