Researchers from CSIRO’s Data61, the data science arm of Australia’s national science agency, and UNSW Sydney’s Kirby Institute have developed a new tool that harnesses artificial intelligence and Twitter for the earlier detection of acute disease events, such as the thunderstorm asthma epidemic that hit Melbourne three years ago today.

Additional Resources

Thunderstorm asthma is the triggering of an asthma attack by environmental conditions directly caused by a local thunderstorm. The sudden outbreak in Melbourne on 21 November 2016 inundated emergency services and hospitals resulting in over 8000 hospital admissions by 6pm that day.

Dr Aditya Joshi, Postdoctoral Fellow at CSIRO’s Data61, said a key challenge in the case of acute disease events is to detect them as soon as possible to assist health agencies to respond swiftly in emergency situations.

"The popularity of social media makes it a valuable source of information for epidemic intelligence," Dr Joshi said.

"We developed a technique that was able to detect the disease outbreak up to nine hours before it was officially reported and before the first news story broke.

"We can draw upon informal sources such as social media data to understand how acute disease events occur, and we can detect when and where an outbreak is likely to occur. This means hospitals and public health agencies can be as prepared as possible."

Using anonymised and publicly available Twitter data, the tool analysed more than 3 million tweets containing keywords related to asthma such as "breath" and "coughing".

The technique combines two fields of artificial intelligence — natural language processing and statistical time series modelling — and a four-step process to ensure the tweets containing the keywords were indeed reports of health conditions and to remove duplicates where an individual might tweet more than once about their condition.

Natural language processing, or NLP, is the ability of a computer program to process human language. The tool uses NLP based on word embeddings, to distinguish between symptoms and unrelated mentions of the keywords.

Professor Raina MacIntyre, Head of Biosecurity Research Program, Kirby Institute, UNSW Sydney said that this work is a remarkable contribution to public health research.

"In future, this system can be used to provide health authorities and the community early warning of a serious and sudden health event," Professor MacIntyre said.

"Early detection could significantly improve our capability to mitigate the impact of epidemics."

The tool can be used to detect other outbreaks such as Influenza, Ebola and the Zika virus. It draws on Data61’s Emergency Situation Awareness system, which analyses Twitter messages posted during disasters and crises to support disaster response efforts.

More information about thunderstorm asthma and how to stay safe can be found at Epidemic thunderstorm asthma .

Hear our news first

Want to hear our news as it happens, and be the first to see our most exciting stories? Subscribing to our news releases and newsletters including Snapshot will give you the latest info.

Images

  • View of lightning stiking city buildings through a high rise window.

    Researchers have developed a new tool that harnesses AI and Twitter for earlier detection of disease outbreaks, such as the thunderstorm asthma epidemic in Melbourne three years ago.

    Download image

Additional information

About the research

The paper, Harnessing Tweets for Early Detection of an Acute Disease Event was co-authored by Aditya Joshi , Ross Sparks, James McHugh, Sarvnaz Karimi, Cecile Paris , C. Raina MacIntyre and was published in the Epidemiology Journal.

News release contact

Chris Chelvan

Communication Advisor

Contact us

 
Your contact details

First name must be filled in

We'll need to know what you want to contact us about so we can give you an answer.