Rains, Piper, Little, Christine, Golchin, Maryam, and Hickson, Roslyn (2022) Machine learning-based risk prediction of pathogen richness. In: [Presented at ANZIAM 2022]. From: ANZIAM 2022, 6-11 February 2022, Perth, WA, Australia and Online.

PDF (Accepted Version) - Presentation Restricted to Repository staff only

Abstract

Infectious disease emergence from spillover (transmission of diseases across species) events is of global concern, and has the potential to cause significant harm to society as shown by the ongoing COVID-19 pandemic. More than 70% of the +400 infectious diseases that emerged in the past five decades have a zoonotic origin, including all recent pandemics. There are many known drivers and factors leading to increased spillover risk, based on the interfaces and connectedness of the health of humans, animals, and shared environments (I.e. One Health). In this study, we built a spatiotemporal predictive model at the country level for pathogen richness. It is a Multilayer Layer Percepteron (MLP) Neural Networks model based on data including urban population, land use proportion, road length, flight passenger, and biodiversity (species richness). Our model will be used to understand the drivers of the pathogen richness as a step towards predicting spillover risk.

Item ID:	77022
Item Type:	Conference Item (Presentation)
Related URLs:	https://anziam2022.com.au/
Additional Information:	ANZIAM (Australia and New Zealand Industrial and Applied Mathematics) is a division of The Australian Mathematical Society (AustMS).
Date Deposited:	14 Dec 2022 02:51
FoR Codes:	49 MATHEMATICAL SCIENCES > 4901 Applied mathematics > 490199 Applied mathematics not elsewhere classified @ 100%
SEO Codes:	20 HEALTH > 2004 Public health (excl. specific population health) > 200499 Public health (excl. specific population health) not elsewhere classified @ 100%
Downloads:	Total: 1
	More Statistics