Computer Program IDs Teens at Risk of Mental Illness

Computer programs may be able to identify teenagers most at risk of mental disorders such as anxiety and depression by analyzing brain scans, researchers say.

When it comes to mental illnesses, spotting those at high risk early in life is critical for treatment.

"Anxiety and mood disorders can have a devastating effect on the individuals concerned and on their families and friends," said researcher Mary Phillips at the University of Pittsburgh. "If we are able to identify those individuals at greatest risk early on, we can offer early and appropriate interventions to delay, or even prevent, onset of these terrible conditions."

Latest Videos From

Watch full video here:

Most psychiatric disorders typically emerge in adolescence or early adulthood. However, there are no known biological markers that can accurately predict which adolescents may or may not develop these illnesses.

Even genetic risk cannot accurately predict the risk an individual faces. For example, a family history of bipolar disorder confers a 10 percent risk of future bipolar disorder as well as a 10 to 25 percent risk of disorders such as attention deficit hyperactivity disorder, major depression or anxiety disorders, but it is impossible to accurately determine whether an individual will develop these disorders.

Now, scientists reveal that computer programs can distinguish between brain scans of healthy, at-risk adolescents and healthy adolescents without such risk of mental disorders.

"We have a technique which shows enormous potential to help us identify which adolescents are at true risk of developing anxiety and mood disorders, especially where there is limited clinical or genetic information," said researcher Janaina Mourão-Miranda, a computer neuroscientist at University College London.

Researchers looked at 16 healthy adolescents who each had a bipolar parent, as well as 16 healthy adolescents whose parents had no history of psychiatric illness. While the volunteers took part in two tasks in which they had to determine the gender of pairs of faces with emotional expressions — happy and neutral or fearful and neutral — they had their brains scanned with functional magnetic resonance imaging.  Previous studies have shown the brains of those with mood disorders respond differently when looking at emotional facial expressions than those without such disorders. [10 Facts About the Teen Brain]

In three out of four cases, the computer program accurately identified the teen who belonged to either the low-risk or high-risk group. Follow-up interviews 12 months to 45 months later showed that those teens identified as high risk often did develop mental disorders such as anxiety and depression.

"This was a preliminary study," Mourão-Miranda cautioned. "This work needs to be replicated with more people."

Interestingly, the researchers found the program was best able to discriminate between adolescents in the low-risk and high-risk groups when they were shown neutral faces. This supports previous studies suggesting that people with anxiety or mood disorders are more likely to perceive neutral faces as ambiguous or potentially threatening.

"Focusing on the brain's response to neutral faces could help us diagnose the risk of mental disorders," Mourão-Miranda told LiveScience.

Future research could see if this approach works for a wide variety of other mental illnesses.

"This might not only help us diagnose neurological and psychiatric disorders in general, but also determine the course they take and how they might respond to treatment," Mourão-Miranda said.

The scientists detailed their findings online today (Feb. 15) in the journal PLoS ONE.