A framework for the risk prediction of avian influenza occurrence: An Indonesian case study.

Samira Yousefinaghani,Rozita Dara,Fei Song,Shayan Sharif,Zvonimir Poljak,Alessandro Rizzo

doi:10.1371/journal.pone.0245116

Abstract

Avian influenza viruses can cause economically devastating diseases in poultry and have the potential for zoonotic transmission. To mitigate the consequences of avian influenza, disease prediction systems have become increasingly important. In this study, we have proposed a framework for the prediction of the occurrence and spread of avian influenza events in a geographical area. The application of the proposed framework was examined in an Indonesian case study. An extensive list of historical data sources containing disease predictors and target variables was used to build spatiotemporal and transactional datasets. To combine disparate sources, data rows were scaled to a temporal scale of 1-week and a spatial scale of 1-degree × 1-degree cells. Given the constructed datasets, underlying patterns in the form of rules explaining the risk of occurrence and spread of avian influenza were discovered. The created rules were combined and ordered based on their importance and then stored in a knowledge base. The results suggested that the proposed framework could act as a tool to gain a broad understanding of the drivers of avian influenza epidemics and may facilitate the prediction of future disease events.

Highlights

Avian Influenza (AI) disease is caused by influenza type A viruses, which can infect domestic poultry, wild birds and mammalian species, including humans
Underlying patterns in form of “IF-” rules along with their respective importance were identified by RuleFit and false positive (FP)-Growth models
From the most relevant rules obtained from the RuleFit and FP-Growth, we discovered that the FP-Growth and RuleFit algorithms agreed on the impact of several predictors such as chicken density, duck density, season and temperature

Summary

Introduction

Avian Influenza (AI) disease is caused by influenza type A viruses, which can infect domestic poultry, wild birds and mammalian species, including humans. Despite researchers’ efforts to eradicate and control this disease, it has continuously caused significant losses to poultry and has threatened human lives. To mitigate the impact of AI outbreaks, it is necessary to understand the extent to which different risk factors and their interactions contribute to the introduction and spread of outbreaks. An extensive array of studies have reported on spatiotemporal surveillance and control of AI using approaches, including logistic regression, boosted regression tree, cluster analysis and maximum entropy in different geographical scales. Some studies have performed spatiotemporal surveillance on a country scale such as those in Bangladesh [5], China [6], Indonesia [7], India [8], Thailand [1]

Methods

Results

Conclusion