Home > Structural differences in adolescent brainscan predict alcohol misuse.

Rane, Roshan Prakash and de Man, Evert Ferdinand and Kim, JiHoon and Görgen, Kai and Tschorn, Mira and Rapp, Michael A and Banaschewski, Tobias and Bokde, Arun L W and Desrivieres, Sylvane and Flor, Herta and Grigis, Antoine and Garavan, Hugh and Gowland, Penny A and Brühl, Rüdiger and Martinot, Jean-Luc and Martinot, Marie-Laure Paillere and Artiges, Eric and Nees, Frauke and Papadopoulos Orfanos, Dimitri and Lemaitre, Herve and Paus, Tomas and Poustka, Luise and Fröhner, Juliane and Robinson, Lauren and Smolka, Michael N and Winterer, Jeanne and Whelan, Robert and Schumann, Gunter and Walter, Henrik and Heinz, Andreas and Ritter, Kerstin (2022) Structural differences in adolescent brainscan predict alcohol misuse. eLife, 11, https://doi.org/10.7554/elife.77545.

External website: https://elifesciences.org/articles/77545

Alcohol misuse during adolescence (AAM) has been associated with disruptive development of adolescent brains. In this longitudinal machine learning (ML) study, we could predict AAM significantly from brain structure (T1-weighted imaging and DTI) with accuracies of 73 -78% in the IMAGEN dataset (n∼1182). Our results not only show that structural differences in brain can predict AAM, but also suggests that such differences might precede AAM behavior in the data. We predicted 10 phenotypes of AAM at age 22 using brain MRI features at ages 14, 19, and 22. Binge drinking was found to be the most predictable phenotype. The most informative brain features were located in the ventricular CSF, and in white matter tracts of the corpus callosum, internal capsule, and brain stem. In the cortex, they were spread across the occipital, frontal, and temporal lobes and in the cingulate cortex. We also experimented with four different ML models and several confound control techniques. Support Vector Machine (SVM) with rbf kernel and Gradient Boosting consistently performed better than the linear models, linear SVM and Logistic Regression. Our study also demonstrates how the choice of the predicted phenotype, ML model, and confound correction technique are all crucial decisions in an explorative ML study analyzing psychiatric disorders with small effect sizes such as AAM.

Item Type
Publication Type
International, Open Access, Article
Drug Type
Intervention Type
Prevention, Harm reduction
26 May 2022
Identification #
eLife Sciences Publications Ltd

Repository Staff Only: item control page