@article{IR,
      author = {Kliamovich, Dakota and Morales, Angelica and Harman,  Gareth and Boyd, Stephen},
      url = {http://digitalcollections.ohsu.edu/record/8240},
      title = {Predicting adolescent binge drinking from brain networks  at rest},
      publisher = {Oregon Health and Science University},
      abstract = {Patterns of alcohol consumption during adolescence differ  from those observed during adulthood; namely, adolescents  are more likely to consume alcohol less frequently, but in  larger quantities per occasion, when compared to adults.  Importantly, this binge-pattern of drinking carries  substantial risks for adverse outcomes, including  involvement in motor vehicle accidents, alcohol poisoning,  and sexual victimization. Although prior work has examined  neural correlates of emergent alcohol use among adolescent  populations, the present study takes a novel, data-driven  approach by incorporating graph theory metrics of  resting-state functional connectivity with predictive  modeling via machine learning. To identify risk factors for  future binge drinking, a subset of participants were  selected from an ongoing prospective longitudinal study  (National Consortium on Alcohol and Neurodevelopment in  Adolescence). All participants were alcohol-na?ve at  baseline (n=150), but 51% (n=77) emerged into binge  drinking over the course of four years of follow-up  assessments (transitioners), while the rest remained  abstinent from alcohol use (controls).},
      number = {IR},
      doi = {https://doi.org/10.6083/tm70mv665},
      recid = {8240},
      address = {2020},
}