Machine learning could replace subjective diagnosis of mental health disorders

    AI is taking over almost every industry and the health industry has some of the biggest benefits to gain. Machine Learning, a discipline of AI, is showing good signs of being able to superseed human capabilities in accurately identifying mental health disorders.

    CSIRO have announced the results of a study of 101 participants, that used ML to diagnose bipolar or depression. The error rate was between 20 – 30% and while that isn’t yet better than humans and isn’t ready for clinical use, it does show a promising sign for the future.

    The machine-learning system detects patterns in data: a process known as ‘training’. Like autonomous driving’s use of computer vision, the results get better, with the more data you can provide it. It’s expected to improve as it’s fed more data on how people play the game.

    “One of the big challenges in psychiatry is misdiagnosis.

    It gives us first-hand information about what is happening in the brain, which can be an alternative route of information for diagnosis.

    Dr Amir Dezfouli, neuroscientist and machine learning expert at Data61.

    The immediate aim is to build a tool that will help clinicians, but the long-term goal is to replace subjective diagnosis altogether. Between depression and bipolar disorder, there’s a significant incidence of misdiagnosis of bipolar people as being depressed, as much as 60%. Around one third of them remain misdiagnosed for more than 10 years.

    It is estimated that within 5 years, computers could be making the diagnosis, rather than humans as we improve the ability for AI to understand the complex human brain.

    The study involved having users play a simple game game where you select between two boxes on screen. One box rewards you with greater frequency than the other; you have to collect the most points.

    Whether you stick with orange or experiment with blue, or just randomly alternate – these decisions paint a picture of how your brain works.

    Often the traditional signatures of mental illness are too subtle for humans to notice, but it’s the kind of thing machine-learning AI thrives on. Now CSIRO researchers have developed a system they say can peer into the mind with significant accuracy, and could revolutionise mental health diagnosis.

    Last year, researchers reported they had found a way of analysing language from Facebook status updates to predict future diagnoses of depression.

    More information at CSIRO.

    Jason Cartwright
    Jason Cartwright
    Creator of techAU, Jason has spent the dozen+ years covering technology in Australia and around the world. Bringing a background in multimedia and passion for technology to the job, Cartwright delivers detailed product reviews, event coverage and industry news on a daily basis. Disclaimer: Tesla Shareholder from 20/01/2021


    1. Would not that be funny. Doc, I can’t work because I’m bonkers. Computer: you are just a lazy shit with an attitude problem. No sympathetic computers out there. And don’t get too angry, I’m half joking, but only half…

    Leave a Reply


    Latest posts


    Related articles