Skip to main content

DiNeMo: Disease Networks and Mobility

Posted by: jur023

August 24, 2018

Overview

The Disease Networks and Mobility (DiNeMo) Project explores how human infectious diseases found overseas might spread in Australia. The project looks at the patterns of how people move both internationally and domestically in order to forecast the risk of the spread of disease.

Using dengue virus outbreaks in Queensland as a case study, this work identifies and tracks new cases of infection to their original source in Australia, and links how the disease transfers between people. Ultimately, the project aims to help protect Australia against the increasing risk of infectious diseases.

 

Challenges

Australia has historically had low risk of importation and establishment of many infectious diseases, due to its geographic remoteness and separation from the rest of the world. Recent decades have seen significant and ongoing increases in the volumes of people and goods moving into Australia, which also increases the risk of importing infectious diseases and invasive species that into the country.

A key challenge in managing this risk has been the lack of sufficient data to pinpoint these risks and forecast them to guide proactive actions. The DiNeMo project focuses on multiple data sources describing people movement patterns to determine the risk of diseases coming into the country, and where and when outbreaks may happen. One case study within DiNeMo is focused on dengue importation.

Dengue is now endemic in more than 100 countries and many face the threat of ongoing local transmission in the near future. While dengue is not established in Australia, some areas in the country host the mosquito vector that transmits the disease. Imported cases from overseas therefore carry the risk of leading to local outbreaks, and in the extreme, to the establishment of dengue in the country. A key challenge the DiNeMo project explores is how to forecast the number of arriving cases of dengue into Australia. A related challenge is to determine how the disease could spread domestically.

Impact

We have developed a model (in the Figure below), recently published at Proceedings of the National Academy of Sciences,  for understanding the hidden links between reported dengue cases. Using reported dengue cases over a period of 15 years provided by Queensland Health, this study maps the reported cases to their respective regions in Queensland and then infers the infection pathways among the regions. The inference of these pathways is underpinned by human mobility traces from multiple data sources, including tourist surveys, geo-tagged social media, and airline travel. 

The resulting infection pathways from the model are shown below for the three years in the dataset that had the most outbreaks. Individual circles represent reported cases that are colour-coded by their region, while the links between them indicate the most likely pathways of infection over time. As the figure shows, the spread pattern in 2003 has fewer larger outbreaks, while in 2013, there are more outbreaks that are smaller in scale.

We have also developed a model for predicting dengue importation globally and into Australia. The model’s predictions, shown below for international airports in 2015, estimate the number of dengue infected people arriving at any airport based on international travel patterns, as well as the incidence rate and seasonality of dengue at the origin of travel. The dark shaded countries, including Australia, are the countries most at risk of dengue importation, where the vector that is capable of spreading dengue is present yet the virus is not. Light shaded countries are countries where dengue is already established.

People

Media Coverage

Using tweets and tourist travel data to predict the next dengue outbreak, Computer World, February, 2019.

Australian researchers reveal tool to track spread of dengue and other infectious diseases, Straits Times, February, 2019.

Data61 builds new disease tracker, InnovationAus, February, 2019.

Data61 using machine learning to track human infectious diseases in Australia, ZDNET, February, 2019.

CSIRO researchers build tools to map and predict infectious disease outbreaks, news.com.au, February, 2019.

Related Publications

M. Kim, D. Paini, R. Jurdak, Modeling stochastic processes in disease spread across a heterogeneous social system, Proceedings of the National Academy of Sciences, 116 (2) 401-406, 2019. pdf

M. Kim, D. Paini, R. Jurdak, Real-world diffusion dynamics based on point process approaches: a review, Artificial Intelligence Review, September, 2018. pdf

M. Shahzamal, R. Jurdak. B. Mans, F. De Hoog, “A Graph Model with Indirect Co-location Links,” In proceedings of the 14th International Workshop on Mining and Learning with Graphs, co-located with KDD, London, UK, August, 2018. 

M. Shahzamal, R. Jurdak, B. Mans, A. El Shoghri, F. De Hoog, ” Impacts of Indirect Contacts in Emerging Infectious Diseases on Social Networks,” In proceedings of Big Data Analysis for Social Computing @ PAKDD, Melbourne, Australia, June, 2018.

M. Shahzamal, R. Jurdak, R. Arablouei, M. Kim, K.  Thilakarathna, B. Mans, “Airborne Disease Propagation on Large Scale Social Contact Network,” In proceedings of the Second International Workshop on Social Sensing (SocialSens), as part of CPSWeek, Pittsburg, USA, April, 2017.

M. Kim, R. Jurdak, “Heterogeneous Social Signals Capturing Real-world Diffusion Processes,” In proceedings of the Second International Workshop on Social Sensing (SocialSens), as part of CPSWeek, Pittsburg, USA, April, 2017.

K. Zhang, R. Arablouei, and R. Jurdak, “Predicting Prevalence of Influenza-Like Illness in Australia From Geo-Tagged Tweets,” In proceedings of the 1st International Workshop on Social Computing (IWSC), as part of the 26th International World Wide Web (WWW) Conference, Perth, Australia, April, 2017.

S. Khan, N. Bergmann, R. Jurdak and B. Kusy, “Mobility in Cities: Comparative Analysis of Mobility Models Using Geo-tagged Tweets in Australia,” In proceedings of the IEEE 2nd International Conference on Big Data Analysis (ICBDA), Bejing, China, March, 2017.

K. Zhao and R. Jurdak, “Understanding the spatiotemporal pattern of grazing cattle movement,” Nature Scientific Reports, 6:31967 EP, August 2016.

Thomas B, Jurdak R, Zhao K, Atkinson I (2016) Diffusion in Colocation Contact Networks: The Impact of Nodal Spatiotemporal Dynamics. PLoS ONE 11(8): e0152624. doi:10.1371/journal. pone.0152624

R. Jurdak, A. Elfes, B. Kusy, A. Tews, W. Hu, E. Hernandez, N. Kottege, P. Sikka, ”Autonomous Surveillance for Biosecurity”, Trends in Biotechnology, 33(4):201-207, April, 2015.

R. Jurdak, K. Zhao, J. Liu, M. AbouJaoude, M. Cameron, D. Newth, “Understanding Human Mobility from Twitter,” PLOS ONE, 10(7): e0131469. doi:10.1371/journal.pone.0131469. July, 2015.

J. Liu, K. Zhao, S. Khan, M. Cameron, R. Jurdak, “Multi-scale Population and Mobility Estimation with Geo-tagged Tweets,” In proceedings of 31st IEEE International Conference on Data Engineering (ICDE) Workshop BioBAD 2015, Seoul Korea, April 2015.

M. Trad, R. Jurdak, and R. Rana, “Guiding Ebola Patients to Suitable Health Facilities: An SMS-based Approach,” F1000 Research 4:43, February 2015.