This article is more than 5 years old. Information may no longer be current.

Neurological data accurately predicts alcohol use initiation in adolescents

Neuroimaging data and neuropsychological testing accurately predicted alcohol use initiation by age 18 years among substance-naïve adolescents, according to recent findings.

“Adverse consequences of adolescent drinking include higher rates of violence, missing school, drunk driving, riding with a drunk driver, suicide, and risky sexual behavior, and it accounts for more than 5,000 deaths per year,” Lindsay M. Squeglia, PhD, of Medical University of South Carolina, Charleston, and colleagues wrote. “Thus, being able to identify at-risk children before they initiate heavy alcohol use could have immense clinical and public health implications. However, few investigations have been conducted to gain a greater understanding of individual differences that could lead to adolescent substance use.”

To predict alcohol use initiation by age 18 years, researchers conducted neuropsychological testing and structural and functional MRI among healthy substance-naïve adolescents (n = 137). Study participants, aged 12 to 14 years, were followed annually to age 18 years. Researchers used random forest classification models to generate individual alcohol use outcome predictions.

By age 18 years, 51% of the cohort initiated moderate-to-heavy alcohol use.

The final random forest model was 74% accurate, with 74% sensitivity and 73% specificity.

The model included 34 predictors of alcohol use by age 18 years, including being male, higher socioeconomic status, early dating, more externalizing behaviors, positive alcohol expectancies, worse executive functioning, and thinner cortices and decreased brain activation in diffusely distributed brain regions.

Including neuropsychological, structural and functional MRI data significantly increased prediction accuracy.

“Understanding neurocognitive factors that predate substance use initiation is crucial to specifying the consequences of substance use on brain development, as well as identifying at-risk youths and potential targets of preventive efforts. The random forest scripts used in this study are now published to allow other groups to replicate findings, in the hope that a final, validated model can be used clinically to predict adolescent alcohol use,” the researchers concluded, – by Amanda Oldt

Disclosure: The researchers report no relevant financial disclosures.