How children talk may predict future mental health issues

By Stephen Beech

How children talk can indicate their risk of future mental health problems years before they develop, according to new research.

Linguistic models that analyzed the words youngsters used when talking about stressful events proved more accurate at predicting future mental well-being issues than a panel of human experts.

Researchers used four natural language processing models to evaluate recorded interviews with more than 200 children, aged nine to 13, as they talked about stressful events in their lives.

The models were "very accurate" at predicting whether they developed mental health conditions six years later, according to the findings published in the journal Nature Mental Health.

Across the models, the American research team found that the style of the children's speech mattered more than the content.

In other words, how children constructed their sentences - such as use of small connector words like "and", "to", and "but" - was more predictive than the children's actual descriptions of stress.

Study lead author Chase Antonacci said: "We believe this study provides a robust proof of concept for the development of scalable tools that identify markers of risk before individuals are diagnosed."

He says that adolescence is when depression and anxiety most often emerge, and once these disorders take hold, they are notoriously difficult to treat.

The years leading up to diagnosis are a critical but poorly understood window, and doctors have had no scalable way to identify which children are on a path toward illness.

A number of methods have been used to assess mental health risk in children, usually involving clinician assessments, but none could be feasibly implemented for large groups.

More objective methods require blood samples or specialized equipment to measure the stress hormone cortisol, physiological reactions to stress, or the length of telomeres - the protective caps on chromosomes that shorten under chronic psychological distress.

Study senior author Ian Gotlib said: "These factors - cortisol, stress reactivity, and telomere length - all have some predictive utility, but speech is something that is inexpensive and scalable.

"It's easy, it's accessible, and it may be a stronger predictor of the development of problems than any of these other factors alone."

Gotlib's lab, at Stanford University in California, studies early-life stress and ways that the environment shapes children's brain development and increases risk for mental health problems.

More from this section

Why is gynecology still using a Civil War-era tool?

Woman credits her dog for spotting breast cancer

Fueled by AI and smoky skies, more Americans are struggling with 'anticipatory anxiety'

His team originally conducted the in-depth interviews used in the current study as part of a larger project that is following a group of young people over several years.

The audio-recorded interviews with the nine- to 13-year-olds are each about 90 minutes long and cover several topics including stressful events.

The researchers first interviewed the children using a traumatic events screening inventory, also known as TESI.

For the inventory, a panel of experts reviewed the interviews and rated the severity of each child's stressors, which can range from financial insecurity and parental divorce to abuse and experiencing a natural disaster.

The panel then assigned a single number that reflected the child's cumulative experience of stress.

Antonacci, a neuroscience doctoral student in Stanford's School of Humanities and Sciences, said: "We realised that there was probably so much richness, variability, and nuance that we were losing by reducing these clinical interviews to a single number, so we thought about other ways we could leverage those audio recordings."

For the new study, the researchers analysed the interviews using four different natural language processing models.

The models have been used in other research to detect signals of mental health and emotional functioning but have mostly been applied to text written by adults to identify current symptoms.

Because young children don't generally write as much as adults do, the researchers wanted to see whether the models could be used to analyse recorded interviews of children's speech to predict who would develop disorders up to six years later.

The results across the models highlighted the predictive power of linguistic style, consistent with previous research showing that patterns in the use of certain words - such as a focus on first-person pronouns and frequent use of prepositions and conjunctions - are indicative of mental health issues.

While not as predictive as linguistic style, the content of the speech did show important links to either future problems or resilience.

The statements associated most strongly with risk described extreme physical violence - such as being punched or choked - or harsh social exclusion, such as feeling an entire school was against them.

Resilience was linked with statements about social support and activities such as sports and school clubs.

Mentions of mental healthcare itself - references to therapists or counselors - emerged as one of the strongest protective signals.

Gotlib says the findings show "great potential" for a language-based assessment, but the next step involves testing the models with a larger dataset.

He added: "If these findings hold, it means we may be able to just take smartphone recordings of children talking, analyse that speech, and identify which children are at risk, years before they might develop a disorder."