August 10, 2020

Check our latest Events.

Check our latest Events.

Utilising AI and Social Media for Early Disease Outbreak Detection

AI and Social Media for Early Disease Outbreak Detection
0Shares

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.

An example of this is the thunderstorm asthma epidemic that hit Melbourne three years ago.

According to a recent press release, 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 6 pm of that day.

Significance of the New Tool

  • Dr Aditya Joshi, Postdoctoral Fellow at CSIRO’s Data61, explained that a key challenge in the case of acute disease events is to detect them as soon as possible to assist health agencies.
  • This will help them respond swiftly in emergency situations.
  • He noted that the popularity of social media makes it a valuable source of information for epidemic intelligence.
  • The researchers have developed a technique, which was able to detect the disease outbreak up to nine hours before it was officially reported and before the first news story broke.
  • They can draw upon informal sources such as social media data to understand how acute disease events occur.
  • They can then detect when and where an outbreak is likely to occur. This means hospitals and public health agencies can be as prepared as possible.

How it Works

  • 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 (AI), which are natural language processing and statistical time series modelling, and a four-step process.
  • This will ensure the tweets containing the keywords were indeed reports of health conditions as well as 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 in order to distinguish between symptoms and unrelated mentions of the keywords.

Benefits of the New Tool

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

This system can be used in the future to provide health authorities and the community early warning of a serious and sudden health event.

Early detection could significantly improve the 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.

OpenGov Academy

In line with smart nation efforts of encouraging AI technology adoption, OpenGov has launched its OpenGov Academy, in collaboration with AlphaZetta.

The OpenGov Academy facilitates and promotes AI masterclasses, workshops and customised courses that are conducted by AlphaZetta and supported by OpenGov.

This academy will feature masterclasses across various levels: C-suite, management, business, and, expert.

The classes have been created to impart understanding – taught in an intuitive, accessible way, keeping formulae and mathematics to a bare minimum and taking an innate, visual approach.

Data literacy, AI and data science, and strategic decision making with data are some of the classes offered by the academy.

For more information, visit: OpenGov Academy

0Shares
Share on linkedin
Share on LinkedIN
Share on facebook
Share on Facebook