Citation

Rane RP, de Man EF, Kim JH, Görgen K, Tschorn M, Rapp MA, Banaschewski T, Bokde ALW, Desrivieres S, Flor H, Grigis A, Garavan H, Gowland PA, Brühl R, Martinot JL, Martinot MLP, Artiges E, Nees F, Papadopoulos Orfanos D, Lemaitre H, Paus T, Poustka L, Fröhner J, Robinson L, Smolka MN, Winterer J, Whelan R, Schumann G, Walter H, Heinz A, Ritter K. Elife 2022; 11: e77545.

Copyright

(Copyright © 2022, dLife Sciences Plublications, Ltd)

DOI

10.7554/eLife.77545

PMID

35616520

Abstract

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.

Language: en

Keywords

neuroscience; computational biology; none; systems biology