Tracking human infectious diseases
The Disease Networks and Mobility (DiNeMo) Project explores how human infectious diseases found overseas might spread in Australia and overseas, and how these movements can be predicted. 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.
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. However, significant increases in the volume of people and goods entering Australia has also increased the risk of infectious diseases being imported.
Using travel data from the International Air Transportation Association, as well as dengue incidence rates from the Global Health Data Exchange, the spread of dengue can be understood and predicted, allowing countries including Australia to develop plans to protect the country against the increasing risk of infectious diseases.
This computational model combines monthly air passenger travel data, country-level dengue incidence rates, and seasonal statistics on the disease to detect the number of dengue importations on a global scale, rather than assessing the risk of importation like existing models.
By understanding the travel behaviour of infected individuals, we can estimate the number of infections that are imported into different countries each month, with this tool determining the infections’ country of origin and the routes along which dengue is most likely spread.
The idea for the tool was triggered by the 2008/2009 dengue outbreak in Cairns, which saw 900 cases of the disease, including one death. The 2008/09 outbreak was triggered by a single infected traveller who returned from Indonesia and passed on the virus to local mosquitoes. This computational model provides a useful tool to assist public health authorities with dengue preparedness, and helping authorities to identify those locations where new dengue outbreaks may occur, following the arrival of infected passengers.
As of December 2019, this tool has established the travel route from Puerto Rico to Florida as having the highest predicted volume of dengue-infected passengers travelling to a non-endemic region, followed by Guadeloupe and Martinique (islands located in the Caribbean) to France.
Forecasting spread through AI
In collaboration with University of NSW, our Data61 team have developed a new artificial intelligence (AI) powered tool to predict serious diseases.
The tool combines natural language processing, data science and statistical time series modelling to identify specific syndrome keywords and their context mentioned in Twitter posts, facilitating the early detection of outbreaks despite expected daily, weekly and seasonal influences.
Preventing the spread of misinformation
Our Data61 researchers have developed an algorithm that detects social bot activity on Twitter in real-time could prevent the spread of misinformation and make it easier for first responders to detect major events.
The algorithm uses machine learning, artificial intelligence (AI) and natural language processing (NLP) to distinguish between genuine conversations and bot-generated messages, creating a set of ‘factual’ parameters and rapid filtering system for real-time results.
Tracking human infectious diseases
The Disease Networks and Mobility (DiNeMo) Project explores how human infectious diseases found overseas might spread in Australia and overseas, and how these movements can be predicted. 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.
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. However, significant increases in the volume of people and goods entering Australia has also increased the risk of infectious diseases being imported.
Using travel data from the International Air Transportation Association, as well as dengue incidence rates from the Global Health Data Exchange, the spread of dengue can be understood and predicted, allowing countries including Australia to develop plans to protect the country against the increasing risk of infectious diseases.
This computational model combines monthly air passenger travel data, country-level dengue incidence rates, and seasonal statistics on the disease to detect the number of dengue importations on a global scale, rather than assessing the risk of importation like existing models.
By understanding the travel behaviour of infected individuals, we can estimate the number of infections that are imported into different countries each month, with this tool determining the infections’ country of origin and the routes along which dengue is most likely spread.
The idea for the tool was triggered by the 2008/2009 dengue outbreak in Cairns, which saw 900 cases of the disease, including one death. The 2008/09 outbreak was triggered by a single infected traveller who returned from Indonesia and passed on the virus to local mosquitoes. This computational model provides a useful tool to assist public health authorities with dengue preparedness, and helping authorities to identify those locations where new dengue outbreaks may occur, following the arrival of infected passengers.
As of December 2019, this tool has established the travel route from Puerto Rico to Florida as having the highest predicted volume of dengue-infected passengers travelling to a non-endemic region, followed by Guadeloupe and Martinique (islands located in the Caribbean) to France.
Forecasting spread through AI
In collaboration with University of NSW, our Data61 team have developed a new artificial intelligence (AI) powered tool to predict serious diseases.
The tool combines natural language processing, data science and statistical time series modelling to identify specific syndrome keywords and their context mentioned in Twitter posts, facilitating the early detection of outbreaks despite expected daily, weekly and seasonal influences.
Preventing the spread of misinformation
Our Data61 researchers have developed an algorithm that detects social bot activity on Twitter in real-time could prevent the spread of misinformation and make it easier for first responders to detect major events.
The algorithm uses machine learning, artificial intelligence (AI) and natural language processing (NLP) to distinguish between genuine conversations and bot-generated messages, creating a set of ‘factual’ parameters and rapid filtering system for real-time results.