Connect with us
  • Elysium

Neuropsychology news

How deep learning is tackling mental health

New insight can help in suicide and self harm prevention in young people and help tailor support to their needs



Deep learning is helping to identify young people most in need of mental health support. 

A new six-year study has helped to shed new light on the myriad of factors which can impact adolescent mental health. 

Through surveying 2,344 young people and their caregivers, and using computer-based deep learning to process the results, researchers were able to identify five categories for the young people to be grouped into, which will help to bring new levels of insight into their situations. 

Nearly 40 per cent of those involved were classified as groups with some problems. Of these, almost 10 per cent lived with mental health problems which had not been identified by their caregivers. This group were most at risk of self-harm and suicidal ideation. 

Identifying the factors which may lead young people to suicide and who is most at risk is key to supporting preventive efforts and early intervention.

The World Health Organization (WHO) identifies suicide as a major global public health concern, but also says it is preventable through evidence-based interventions and by addressing factors that can lead to poor mental health.

Researchers from the University of Tokyo and the Tokyo Metropolitan Institute of Medical Science are analysing data on various problems in adolescence which were assessed both by self and caregivers, resulting in identification of young people who may be at suicide-related risk.

“We recently found that adolescents who were considered to have no problems by their caregivers actually had the highest suicide-related risk,” said Daiki Nagaoka, a doctoral student in the Department of Neuropsychiatry at the University of Tokyo and a hospital psychiatrist. 

“So it is important that society as a whole, rather than solely relying on caregivers, takes an active role in recognising and supporting adolescents who have difficulty in seeking help and whose distress is often overlooked.”

The team surveyed adolescents and their caregivers in Tokyo over a period of six years. The participants complete self-report questionnaires, answering questions on psychological and behavioural problems such as depression, anxiety, self-harm and inattention, as well as their feelings about family and school life. The team also made note of factors such as maternal health during pregnancy, involvement in bullying and the caregivers’ psychological state. 

The study began when the children were ten years old, and checked in with them again at ages 12, 14 and 16. Overall, 3,171 adolescents took part, with 2,344 pairs of adolescents and their caregivers participating throughout the full study.

Deep learning, a computer program that mimics the learning process of our brains, enabled the team to analyse the large amounts of data they collected to find patterns in the responses. By grouping the trajectories of the psychological and behavioural problems identified in the survey, they could classify the adolescents into five groups, which they named based on their key characteristic: unaffected, internalising, discrepant, externalising and severe.

The largest group, at 60.5 per cent of the 2,344 adolescents, was made up of young people who were classified as “unaffected” by suicidal behaviour.

The remaining 40 per cent were found to be negatively affected in some way. The ‘internalising’ group (16.2 per cent) persistently internalised problems and showed depressive symptoms, anxiety and withdrawal. 

The ‘discrepant’ group (9.9 per cent) experienced depressive symptoms and “psychotic-like experiences,” but had not been recognised as having such problems by their caregivers. The ‘externalising’ group (9.6 per cent) displayed hyperactivity, inattention and/or behavioural issues but few other problems. 

Finally, the smallest group was categorised as ‘severe (3.9 per cent) and dealt with chronic difficulties which their caregivers were aware of, in particular, psychotic-like experiences and obsessive-compulsive behaviour.

Of all the groups, young people in the ‘discrepant’ category were at highest risk of self-harm and suicidal thoughts. 

The researchers found that they could significantly predict who would be included in this group based on if the child avoided seeking help for depression, and if their caregiver also had a mental health problem. They suggest that the caregiver’s mental state could impact the adolescent’s mental health through both genetic factors and parenting environment, such as the caregiver’s ability to pay attention to the difficulties an adolescent might face. 

Although this research has several limitations, it still enabled the team to identify a number of risk factors which could be used to predict which groups adolescents might fall into.

“In daily practice as a psychiatrist, I observed that existing diagnostic criteria often did not adequately address the diverse and fluid difficulties experienced by adolescents,” said Nagaoka. 

“We aimed to better understand these difficulties so that appropriate support can be provided. Next we want to better understand how adolescents’ psychopathological problems interact and change with the people and environment around them. 

“Recognising that numerous adolescents face challenges and serious issues, yet hesitate to seek help, we must establish supportive systems and structures as a society.”