Deep learning reveals hidden patterns in youth mental health

The personal yet global struggle with mental health may be more evident than ever. However, many people still find it difficult to access the support they need. In Japan, suicide is sadly the leading cause of death among young people. Researchers, including those from the University of Tokyo, conducted a six-year study to better understand the myriad factors that can influence the mental health of adolescents. After surveying 2,344 young people and their parents and processing the results using computer-based deep learning, they were able to classify young people into her five categories. Approximately 40% of the participants were classified as having some sort of problem. Of these, almost 10% had mental health problems that were not recognized by their caregivers. This group had the highest risk of self-harm and suicidal thoughts. Identifying the factors that can lead young people to suicide and who is most at risk is key to supporting prevention efforts and early intervention.

Last year in Japan, 514 young people and children under the age of 18 tragically lost their lives to suicide. This is the highest number for this age group since records began in 1978. Sadly, suicide is the number one cause of death for people between the ages of 15 and 34, according to data from Japan’s Ministry of Health, Labor and Welfare. While suicide rates among adults have generally declined over the past 10 to 15 years, the opposite has been noted among adolescents. Officials suspect that school-related issues, difficult personal and family relationships, and the effects of a prolonged pandemic may have contributed to the high death toll.

The World Health Organization (WHO) recognizes suicide as a major global public health concern, but there is no evidence-based intervention or evidence-based intervention that can lead to worsening mental health outcomes. It also states that suicide can be prevented by addressing the contributing factors. Researchers from the University of Tokyo and the Tokyo Metropolitan Institute of Medical Science analyzed data on a variety of adolescent problems assessed by both adolescents and their caregivers, and found that young people who may be at risk for suicide-related has been identified.

We recently discovered that young people who are thought to be OK by their caregivers are actually at the highest risk for suicide-related causes. Therefore, rather than relying solely on caregivers, it is important that society as a whole plays an active role in recognizing and supporting young people who have difficulty seeking help and whose suffering is often overlooked. ”

Daiki Nagaoka, doctoral student, Department of Psychiatry and Neurology, University of Tokyo, hospital psychiatrist

The research team surveyed adolescents and their caregivers in Tokyo over a six-year period. Participants complete a self-report questionnaire, answering questions about psychological and behavioral issues such as depression, anxiety, self-harm, and inattention, as well as feelings about family and school life. The research team also took into account factors such as maternal health during pregnancy, involvement in bullying, and the psychological state of caregivers. The study began when the children were 10 years old and was repeated when they were 12, 14, and 16 years old. Overall, 3,171 adolescents participated, and 2,344 pairs of adolescents and their parents participated throughout the study.

“Psychiatry faces the challenge of understanding the diverse and dynamic nature of adolescent psychopathology. Previous studies typically assess adolescent psychopathology based on the trajectory of just two or three indicators. In contrast, our approach was able to classify adolescents based on many symptoms.” By using deep learning techniques, we can analyze trajectories simultaneously. This facilitated a more comprehensive understanding,” Nagaoka explained.

Deep learning, a computer program that mimics the learning processes of our brains, allowed the team to analyze the large amounts of data they collected to find patterns in responses. By grouping the trajectories of psychological and behavioral problems identified in the study, they were able to classify youth into five groups, which they named based on their main characteristics: not internalized, internalized, contradictory, externalized, and severe.

The largest group consisted of 2,344 youth, 60.5% of whom were classified as ‘not affected’ by suicidal behavior.

The remaining 40% were found to be negatively affected in some way. The “internalizing” group (16.2%) persistently internalized their problems and exhibited symptoms of depression, anxiety, and withdrawal. The “ambivalent” group (9.9%) experienced depressive symptoms and “psychotic-like experiences,” but their caregivers did not recognize them as having such problems. The “externalizing” group (9.6%) exhibited hyperactivity, inattention, and/or behavioral problems, but few other problems. Finally, the smallest group was classified as ‘severe’ (3.9%), dealing with caregiver-perceived chronic difficulties, particularly psychotic-like experiences and obsessive-compulsive behaviors.

Of all groups, young people in the ‘ambivalent’ category were at highest risk for self-harm and suicidal ideation. Researchers found that they could significantly predict who would be included in this group based on whether the child avoided treatment for depression and whether their caregivers also had mental health problems. . Researchers have found that the mental state of caregivers influences the mental health of adolescents through both genetic factors and the caregiving environment, including the caregiver’s ability to pay attention to difficulties that adolescents may face. It suggests that it may be possible. Although this study has some limitations, the team was still able to identify a number of risk factors that can be used to predict which group a youth will fall into.

“In my daily practice as a psychiatrist, I have found that existing diagnostic criteria often do not adequately address the diverse and fluid challenges that adolescents experience.” Dr. Nagaoka said. “We aimed to better understand these difficulties so that we could provide appropriate support. We then sought to understand how psychopathological problems in young people interact with the people and environment around them and We want to better understand how change can change. We recognize that many young people face challenges and serious problems but are hesitant to seek help.” As a society, we need to establish supportive systems and structures. ”