AI can detect anxiety and depression in a child’s speech

The study conducted by researchers at the University of Vermont in the USA suggests a machine learning algorithm might provide a fast and easy way of diagnosing anxiety and depression – conditions that are difficult to spot and often overlooked in young people.

“We need quick, objective tests to catch kids when they are suffering,” said study lead author Ellen McGinnis, who is a clinical psychologist at the university’s Medical Centre’s Vermont Centre for Children, Youth and Families. “The majority of kids under eight are undiagnosed,” she added.

Early diagnosis of these conditions is critical as children respond well to treatment while their brains are still developing, according to the researchers, but if they are left untreated they are at greater risk of substance abuse and suicide later in life.

Standard diagnosis involves a 60-90-minute semi-structured interview with a trained clinician and their primary caregiver.

McGinnis, along with University of Vermont biomedical engineer and study senior author Ryan McGinnis, have been looking at ways to overcome this, by using artificial intelligence and machine learning to make diagnosis faster and more reliable.

For the study, the researchers used an adapted version of a mood induction task called the Trier-Social Stress Task, which is intended to cause feelings of stress and anxiety in a participant.

A group of 71 children between the ages of three and eight were asked to improvise a three-minute story and told that they would be judged based on how interesting the story was.

The researcher acting as the judge remained stern throughout the speech, giving only neutral or negative feedback. After 90 seconds, and again with 30 seconds left, a buzzer would sound, and the judge would tell them how much time was left.

McGinnis said: “The task is designed to be stressful, and to put them in the mindset that someone was judging them.”

The children were also diagnosed using a structured clinical interview and parent questionnaire, both well-established ways of identifying internalising disorders in children.

The researchers then used a machine learning algorithm to analyse statistical features of the audio recordings of each child’s story and link them to the child’s diagnosis.

The study found the algorithm was highly successful at diagnosing children, and that the middle phase of the recordings, between the two buzzers, was the most predictive of a diagnosis.

Ryan McGinnis explained that “the algorithm was able to identify children with a diagnosis of an internalising disorder with 80 per cent accuracy,” and added that in most cases, it “compared really well to the accuracy of the parent checklist.”

According to the study, the system can also give the results much more quickly, with the algorithm requiring just a few seconds of processing time once the task is complete to provide a diagnosis.

The algorithm identified eight different audio features of the children’s speech, but three in particular stood out as highly indicative of internalising disorders: low-pitched voices, with repeatable speech inflections and content, and a higher-pitched response to the surprising buzzer.

Ellen McGinnis stated that these features fit well with what you might expect from an individual suffering from depression.

McGinnis observed that “a low-pitched voice and repeatable speech elements mirrors what we think about when we think about depression: speaking in a monotone voice, repeating what you’re saying.”

Around one in five children suffer from anxiety and depression, collectively known as “internalising disorders.” But because children under the age of eight can’t reliably articulate their emotional suffering, adults need to be able to infer their mental state and recognise potential mental health problems.

However, waiting lists for appointments with psychologists, insurance issues, and failure to recognise the symptoms by parents all contribute to children missing out on treatment.

Following from the successful voice analysis study, Ellen McGinnis said there next step will be to develop the speech analysis algorithm into a universal screen tool for clinical use, via a smartphone app, for example, that could record and analyse results immediately.

The voice analysis could also be combined with the motion analysis into a battery of technology-assisted diagnostic tools, to help identify children at risk of anxiety and depression before even their parents suspect that anything is wrong.

The research has been published in the Journal of Biomedical and Health Informatics.

At the start of May 2019, a study found that free apps to help people stop smoking or cope with depression have been leaking highly personal data to third parties, often without informing their users.