Transfer Learning of Deep Neural Networks Pretrained Using the ABCD Dataset for General Psychopathology Prediction in Korean Adolescents.

Abstract

Background: In this study, we examined whether a deep neural network (DNN), trained to predict the general psychopathology factor (p factor) using functional magnetic resonance imaging (fMRI) data from adolescents in the ABCD (Adolescent Brain Cognitive Development) Study, would generalize to Korean adolescents.

Methods: We trained a scanner-generalization neural network (SGNN) to predict p factor scores from resting-state functional connectivity (RSFC) data of 6905 ABCD Study adolescents, controlling for MRI scanner-related confounds. Then, we transferred the pretrained SGNN to a DNN to predict p factor scores for 125 adolescents, including healthy individuals and individuals with major depressive disorder, using data from Seoul National University Hospital (SNUH). We compared the transferred DNN's performance with that of kernel ridge regression (KRR) and a baseline DNN.

Results: The transferred DNN outperformed KRR (0.17 ± 0.16; 0.60 ± 0.07) and the baseline DNN (0.17 ± 0.16; 0.69 ± 0.11), with a higher Pearson's correlation coefficient (0.29 ± 0.18) and lower mean absolute error (0.59 ± 0.09; p < .005). We identified the default mode network (DMN) and visual network (VIS) as crucial functional networks for predicting p factors across both datasets. The dorsal attention network was specific to the ABCD Study dataset, while the cingulo-opercular and ventral attention networks were specific to the SNUH dataset.

Conclusions: The transferred SGNN successfully generalized to Korean adolescents. Altered RSFC in the DMN and VIS may serve as promising biomarkers for p factor prediction across diverse populations, addressing heterogeneity in demographics, diagnoses, and MRI scanner characteristics.