Data61 gamifies psychiatry to reduce misdiagnosis

By on
Data61 gamifies psychiatry to reduce misdiagnosis
Data61's Dr Amir Dezfouli. Credit: CSIRO

Detecting bipolar and complex disorders faster.

A team of researchers at CSIRO’s Data61 used a simple computer game together with AI techniques to help mental health practitioners diagnose and characterise complex disorders, and offer tailored treatments.

The researchers were able to use the game and AI techniques to identify behavioural patterns in 101 participants.

The game, which was presented at the D61+ LIVE event in Sydney, presents individuals with two choices and tracks their behaviour as they respond.

Data collected through the game is analysed by neural networks, which can then untangle the nuanced behavioural differences between people with depression or bipolar disorder and healthy individuals.

Lead author of the research, Dr Amir Dezfouli, a neuroscientist and machine learning expert at CSIRO’s Data61, said the research is an important step in the emerging field of computational psychiatry.

“Artificial intelligence and deep learning techniques allow us to analyse complex datasets and make accurate models of the brain processes involved in psychiatric disorders,” he said.

“Characterising mental health disorders in granular detail could allow clinicians to develop more personalised treatment plans based on an individual’s unique diagnosis.”

Dezfouli added that almost 70 percent of bipolar patients are initially misdiagnosed under current methods, with around one third of these patients remaining misdiagnosed for 10 years or more.

“If we can understand how the brain works, we can develop more accurate processes for diagnosis and more effective treatments for people with mental health disorders.”

Dezfouli also hopes the game will be an additional data-backed decision-making tool that builds on existing diagnosis materials, such as the Diagnostic and Statistical Manual (DSM) and the International Classification of Diseases (ICD).

“The strength of the computer game is that unlike traditional mental health assessments, the results can directly reflect the brain processes that are affected due to the disorders, as individuals are responding to stimuli rather than direct questions about their mental state.”

Dr Richard Nock, machine learning group leader at Data61, said that while the game and other AI-powered tools have enormous potential to overcome challenges in health, security and the environment, they must be deployed with privacy, ethics and inclusiveness at its core.

“We need to design systems that deliver benefits individually and collectively," Nock said.

“The artificial neural network was specifically designed to produce interpretable results, and will augment the capabilities of clinicians and psychiatrists.”

The research paper, Disentangled behavioral representations, has been accepted at the 2019 Conference on Neural Information Processing Systems (NeurIPS), a machine learning conference taking place in Vancouver in December.

Got a news tip for our journalists? Share it with us anonymously here.
Copyright © . All rights reserved.

Most Read Articles

Log In

  |  Forgot your password?