TY  - JOUR
PY  - 2022//
TI  - Structural differences in adolescent brains can predict alcohol misuse
JO  - Elife
A1  - Rane, Roshan Prakash
A1  - de Man, Evert Ferdinand
A1  - Kim, JiHoon
A1  - Görgen, Kai
A1  - Tschorn, Mira
A1  - Rapp, Michael A.
A1  - Banaschewski, Tobias
A1  - Bokde, Arun L. W.
A1  - Desrivieres, Sylvane
A1  - Flor, Herta
A1  - Grigis, Antoine
A1  - Garavan, Hugh
A1  - Gowland, Penny A.
A1  - Brühl, Rüdiger
A1  - Martinot, Jean-Luc
A1  - Martinot, Marie-Laure Paillère
A1  - Artiges, Eric
A1  - Nees, Frauke
A1  - Papadopoulos Orfanos, Dimitri
A1  - Lemaitre, Herve
A1  - Paus, Tomas
A1  - Poustka, Luise
A1  - Fröhner, Juliane
A1  - Robinson, Lauren
A1  - Smolka, Michael N.
A1  - Winterer, Jeanne
A1  - Whelan, Robert
A1  - Schumann, Gunter
A1  - Walter, Henrik
A1  - Heinz, Andreas
A1  - Ritter, Kerstin
SP  - e77545
EP  - e77545
VL  - 11
IS  - 
N2  - 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 ten 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.<p />  <p>Language: en</p>
LA  - en
SN  - 2050-084X
UR  - http://dx.doi.org/10.7554/eLife.77545
ID  - ref1
ER  -