“We had a COVID focus, but we know that beyond COVID and the things we do there we can apply to the other diseases,” Dr Thomas said.
“I was really impressed with what the teams put forward and what they achieved over the datathon, and beyond the two winners there’s a lot of good ideas to explore.”
Google and Amazon made their data sets available for participants to use, something Dr Thomas said was the core of how modern artificial intelligence projects worked.
“What we’re finding with the growth of AI is AI is able to make a lot of sense of data, particularly around predictive analytics or those deep insights that traditionally required a lot of human brainpower,” he said.
One of the two winning projects was Clearer Consent, which aims to develop a user interface that will allow people who don’t speak English to give informed consent in a medical setting.
Applied mathematician Tobin South, the lead on Clearer Consent, said the goal would be to modify existing chatbot interfaces and off-the-shelf question-answering software to become something fit for purpose on a hospital front line.
“A big challenge in healthcare is informed consent, the doctor gives you all these forms, says tick the boxes, don’t drive for the next couple of days, but many people don’t really understand what’s going on,” University of South Australia masters student said.
“Lots of people have language barriers to using these forms and there’s also cultural considerations that you can’t cram onto a one-page form.
“The solution involving AI was to develop a way to ask questions in the patient’s native language, and have them be able to type their own questions or concerns into the program and have it understand them and give meaningful answers back.”
The other project singled out for praise was Vision AI, which aims to use deep learning software to develop a system to do initial scanning of X-rays and other medical imaging and flag potential issues for doctors to have a closer look at.
Dr Thomas said in addition to the two winners, a number of other datathon projects would be developed further in the future.
He said the AI Hub focused on medical applications of artificial intelligence because there was already proven value of the work in the field but planned to expand that focus in the future.
“This is the next generation we’re into with AI is how we make use of that data and build those next generation systems,” he said.
“We see AI as a really transformative technology that’s really going to change our industries quite dramatically over the next 10 years, from agriculture, environment and mining, to defence and cybersecurity.”
Stuart Layt covers health, science and technology for the Brisbane Times. He was formerly the Queensland political reporter for AAP.