Using Google Trends and ambient temperature to predict seasonal influenza outbreaks

Yuzhou Zhang; Hilary Bambrick; Kerrie Mengersen; Shilu Tong; Wenbiao Hu

doi:10.1016/j.envint.2018.05.016

Using Google Trends and ambient temperature to predict seasonal influenza outbreaks

Environ Int. 2018 Aug:117:284-291. doi: 10.1016/j.envint.2018.05.016. Epub 2018 May 16.

Authors

Yuzhou Zhang¹, Hilary Bambrick², Kerrie Mengersen³, Shilu Tong⁴, Wenbiao Hu⁵

Affiliations

¹ School of Public Health and Social Work, Institute of Health and Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: yuzhou.zhang@hdr.qut.edu.au.
² School of Public Health and Social Work, Institute of Health and Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: h.bambrick@qut.edu.au.
³ Science and Engineering Faculty, Mathematical and Statistical Science, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: k.mengersen@qut.edu.au.
⁴ School of Public Health and Social Work, Institute of Health and Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia; School of Public Health and Institute of Environment and Human Health, Anhui Medical University, Hefei, Anhui, China; Shanghai Children's Medical Centre, Shanghai Jiao-Tong University, Shanghai, China. Electronic address: s.tong@qut.edu.au.
⁵ School of Public Health and Social Work, Institute of Health and Biomedical Innovation, Queensland University of Technology, Brisbane, Queensland, Australia. Electronic address: w2.hu@qut.edu.au.

PMID: 29778013
DOI: 10.1016/j.envint.2018.05.016

Abstract

Background: The discovery of the dynamics of seasonal and non-seasonal influenza outbreaks remains a great challenge. Previous internet-based surveillance studies built purely on internet or climate data do have potential error.

Methods: We collected influenza notifications, temperature and Google Trends (GT) data between January 1st, 2011 and December 31st, 2016. We performed time-series cross correlation analysis and temporal risk analysis to discover the characteristics of influenza epidemics in the period. Then, the seasonal autoregressive integrated moving average (SARIMA) model and regression tree model were developed to track influenza epidemics using GT and climate data.

Results: Influenza infection was significantly corrected with GT at lag of 1-7 weeks in Brisbane and Gold Coast, and temperature at lag of 1-10 weeks for the two study settings. SARIMA models with GT and temperature data had better predictive performance. We identified autoregression (AR) for influenza was the most important determinant for influenza occurrence in both Brisbane and Gold Coast.

Conclusions: Our results suggested internet search metrics in conjunction with temperature can be used to predict influenza outbreaks, which can be considered as a pre-requisite for constructing early warning systems using search and temperature data.

Keywords: Early warning; Prediction; Search terms; Seasonal influenza; Temperature.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Climate*
Humans
Influenza, Human / epidemiology*
Internet
Models, Statistical*
Seasons
Temperature