Monash University researchers develop AI aimed at improving suicide prevention
In an effort to help paramedics respond more effectively to potential suicides in Australia, researchers from Monash University and Turning Point, a national addiction treatment centre, are using artificial intelligence (AI) to streamline how relevant ambulance data is filtered and categorised.
The AI project, which received a AU$1.2 million grant as part of the 2019 Google AI Impact Challenge, is a machine learning model that annotates a database of ambulance clinical records into categories such as suicide attempt, suicidal ideation, and self-injury without suicidal intent.
Ambulance clinical records are an important data source to help inform suicide prevention efforts as ambulances are often the first point of contact in a suicide-related crisis, Monash University said.
According to the University, implementing the machine learning model could potentially remove two-thirds of the data processing that is undertaken in this task. The task is currently carried out by humans who have to interpret each paramedic clinical record individually.
See also: University of Sydney researchers to use AI to help prevent heart attacks
Implementing the machine learning model would also result in the timely and cost-effective identification and coding of suicide-related ambulance data, the university said, as well as better inform policy and public health responses for suicide prevention.
"For example, how self-harm incidents can relate to other factors such as violence, drug use, and socioeconomic status," Monash said.
"The project will uncover critical suicide trends and potential points of intervention to better inform policy and public health responses. The technology we're developing will create opportunities for adoption internationally," added Dan Lubman, Turning Point director and Monash University's professor of Addiction Studies and Services.
During the project's development, the two institutions gained access to mentors and tools from Google, in addition to international leaders across the fields of people-centred AI, which Monash University professor of Data Science and project lead Wray Buntine said "amplified our project's overall impact".
With the data that has already been annotated by the machine learning model, the university said the results are currently being presented to policymakers so they can improve their response to suicide-related issues.
The AI Impact Challenge was developed when Google unveiled its AI for Social Good initiative in October 2018 that aims to steer the company's vast resources and expertise in AI to projects with positive impacts on society. The initiative is a joint effort between Google.org, the company's philanthropic arm, and Google engineers and researchers.
If you or anyone you know in Australia needs help contact one of these services:
- Suicide Call Back Service on 1300 659 467
- Lifeline on 13 11 14
- Kids Helpline on 1800 551 800
- MensLine Australia on 1300 789 978
- Beyond Blue on 1300 22 46 36
- Headspace on 1800 650 890
- QLife on 1800 184 527
Related Coverage
- Stuart Russell: Will we choose the right objective for AI before it destroys us all?
- How to track the coronavirus: Dashboard delivers real-time view of the deadly virus
- Average tenure of a CISO is just 26 months due to high stress and burnout
- Data61 using AI and gamification to diagnose mental health patients
- Study: Millennial parents are more likely to consider AI for their kids' health (TechRepublic)