Teens aren’t going to like this: Neuro MRI has helped researchers accurately predict which young persons are likely to become heavy drinkers by the time they turn 18. If readily replicable, the work may suggest modes of pre-problem intervention.
Publishing their findings online Aug. 29 in the American Journal of Psychiatry, Lindsay Squeglia, PhD, of the Medical University of South Carolina and colleagues describe their prospective investigation of the imaging-aided model as applied to 137 participants between the ages of 12 and 14.
Most of the subjects, 97 percent, had never tried alcohol.
The team combined multimodal neuroimaging data—specifically, structural and functional magnetic resonance imaging (sMRI and fMRI)—with neuropsychological testing and demographic info to perform annual assessments.
Crunching these datasets with the random forest machine-learning technique, they achieved 74 percent accuracy, with good sensitivity (74 percent) and specificity (73 percent), at separating the 70 participants who went on to drink moderately or heavily by age 18 from the 67 who remained nondrinkers.
The model contained 34 predictors contributing to alcohol use. These included such demographic and behavioral factors as being male and dating early, neuropsychological factors like worse executive functioning and—as revealed in the imaging component—structural factors such as thinner cortices and less brain activation in diffusely distributed regions of the brain.
The inclusion of the sMRI and fMRI data, combined with the neuropsychological insights, significantly increased the prediction accuracy of the model, the authors conclude.
In their discussion, Squeglia et al. write that underage drinking “is widely recognized as a leading public health and social problem for adolescents in the U.S. Being able to identify at-risk children before they initiate heavy alcohol use could have immense clinical and public health implications.”
In an article from the press office at UC-San Diego Health, senior study author Susan Tapert, PhD, of that institution says the value of this particular study is that it “provides a documented path for other researchers to follow, to replicate and expand upon our findings. Ultimately, of course, the goal is to have a final, validated model that physicians and others can use to predict adolescent alcohol use and prevent it.”