Risk assessment strategies for early detection and prediction of infectious disease outbreaks associated with climate change

Can Commun Dis Rep. 2019 May 2;45(5):119-126. doi: 10.14745/ccdr.v45i05a02.

Abstract

A new generation of surveillance strategies is being developed to help detect emerging infections and to identify the increased risks of infectious disease outbreaks that are expected to occur with climate change. These surveillance strategies include event-based surveillance (EBS) systems and risk modelling. The EBS systems use open-source internet data, such as media reports, official reports, and social media (such as Twitter) to detect evidence of an emerging threat, and can be used in conjunction with conventional surveillance systems to enhance early warning of public health threats. More recently, EBS systems include artificial intelligence applications such machine learning and natural language processing to increase the speed, capacity and accuracy of filtering, classifying and analysing health-related internet data. Risk modelling uses statistical and mathematical methods to assess the severity of disease emergence and spread given factors about the host (e.g. number of reported cases), pathogen (e.g. pathogenicity) and environment (e.g. climate suitability for reservoir populations). The types of data in these models are expanding to include health-related information from open-source internet data and information on mobility patterns of humans and goods. This information is helping to identify susceptible populations and predict the pathways from which infections might spread into new areas and new countries. As a powerful addition to traditional surveillance strategies that identify what has already happened, it is anticipated that EBS systems and risk modelling will increasingly be used to inform public health actions to prevent, detect and mitigate the climate change increases in infectious diseases.

Keywords: artificial intelligence; climate change; event-based surveillance systems; machine learning; natural language processing; risk assessment; risk modelling.