Computer programs may be able to differentiate between the brain scans of healthy adolescents and those at risk of developing psychiatric disorders. At-risk adolescents could be identified and helped before the disease took hold and required more dramatic intervention. It could be these disorders which become apparent during formative years and may alter a person’s life could be treated or even avoided.
Prediction of these types of disorders is difficult because they have no known biomarkers and genetic factors have not been a reliable indicator.
The study which showed it’s possible involved 16 health teens who each had a parent with bipolar disorder and 16 adolescents without history of psychiatric illness. Functional magnetic resonance imaging was utilized to watch their brain activity as they were asked to identify the gender of a series of emotionally expressive faces. When the computer program was asked to predict probability of psychiatric illness based on the fMRI scans, it was accurate in three out of four incidents.
Leading researcher, Dr. Janaina Mourai-Miranda, a Wellcome Trust Research Career Development Fellow at the University College London stated, “Combining machine learning and neuro-imaging, 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.”
“Anxiety and mood disorders can have a devastating effect on the individuals concerned and on their families and friends. 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,” said Professor Mary Phillips, from the Clinical and Translational Affective Neuroscience Program at the University of Pittsburgh and co-author.
Source: MedicalNewsToday, PLoS ONE