Depressed teenager looking away while talking to his therapist

Algorithm predicts suicidal thoughts in teenagers

Image credit: Katarzyna Bialasiewicz/Dreamstime

Researchers in the US have created an algorithm that they say can predict suicidal thoughts and behaviour among adolescents with a 91 per cent accuracy.

The team, comprising of university researchers at Brigham Young University (BYU), Johns Hopkins and Harvard, outlined their machine learning approach in the journal PLOS One. The paper also details risk factors that are leading predictors of suicidal ideation and behaviour among adolescents: online harassment and bullying.

“Suicide is the second leading cause of death among adolescents in the US,” said Michael Barnes, study co-author and associate dean of the BYU College of Life Sciences. “We must have a better understanding of the risk factors – and the protective factors – associated with this heartbreaking issue.”

The study results show researchers can predict with high accuracy which adolescents will exhibit suicidal thoughts (consideration or planning) or suicidal behaviour (attempting) based on experiences they face.

The team analysed data from 179,384 junior high and high school students, along with those who took part in the Student Health and Risk Prevention survey from 2011 to 2017 – the dataset includes responses to over 300 survey questions and over 8,000 bits of demographic information, resulting in 1.2 billion data points that were processed.

After collection, the researchers then applied various algorithms to the data and found a machine-learning model that accurately predicted which adolescents went on to have suicidal thoughts and behaviours (STB) based on the data provided.

The data found females were more likely to experience suicidal thoughts and behaviour (17.7 per cent) than males (10.8 per cent), and that those adolescents without a father in the home were 72.6 per cent more likely to contemplate suicide than those with a father in the home.

Researchers also found that the algorithm discovered which risk factors were the leading predictors of suicidal thoughts and behaviour: being threatened or harassed through digital media, being picked on or bullied by a student at school, and exposure/involvement in serious arguments and yelling at home.

“This analysis finds the most important root causes of suicidal thoughts and behaviour in adolescents and creates risk profiles that give us a clearer picture of adolescents that are at risk,” said study co-author Carl Hanson, professor of public health at BYU. “If you want to wrap your head around what you can do about it, these profiles are one good place to start.”

Although the researchers expected some of the risk factors, such as bullying and harassment, they were surprised to see the heavy influence of family factors. Three of the top 10 predictive factors for STB were tied directly to family situations: being in a family where there are serious arguments, being in a family that argues about the same things over and over, and being in a family that yells and insults each other.

The team said the implications of the research are critical for prevention programming and policymaking. Specifically, they hope policymakers use the STB risk profile and its associate rankings to prepare services, resources, and assessments aimed at school, community, and family settings.

“Clearly, the results speak to the need for prevention and schools may be the best place to start by helping to mitigate bullying and online harassment. The results also show a need to strengthen families,” Hanson said. “For communities, we need programming that can help support and strengthen the family.”

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles