TY - JOUR

T1 - Generalizability of treatment outcome prediction in major depressive disorder using structural MRI

T2 - A NeuroPharm study

AU - Beliveau, Vincent

AU - Hedeboe, Ella

AU - Fisher, Patrick M

AU - Dam, Vibeke H

AU - Jørgensen, Martin B

AU - Frokjaer, Vibe G

AU - Knudsen, Gitte M

AU - Ganz, Melanie

N1 - Copyright © 2022 The Author(s). Published by Elsevier Inc. All rights reserved.

PY - 2022

Y1 - 2022

N2 - Brain morphology has been suggested to be predictive of drug treatment outcome in major depressive disorders (MDD). The current study aims at evaluating the performance of pretreatment structural brain magnetic resonance imaging (MRI) measures in predicting the outcome of a drug treatment of MDD in a large single-site cohort, and, importantly, to assess the generalizability of these findings in an independent cohort. The random forest, boosted trees, support vector machines and elastic net classifiers were evaluated in predicting treatment response and remission following an eight week drug treatment of MDD using structural brain measures derived with FastSurfer (FreeSurfer). Models were trained and tested within a nested cross-validation framework using the NeuroPharm dataset (n = 79, treatment: escitalopram); their generalizability was assessed using an independent clinical dataset, EMBARC (n = 64, treatment: sertraline). Prediction of antidepressant treatment response in the Neuropharm cohort was statistically significant for the random forest (p = 0.048), whereas none of the models could significantly predict remission. Furthermore, none of the models trained using the entire NeuroPharm dataset could significantly predict treatment outcome in the EMBARC dataset. Although our primary findings in the NeuroPharm cohort support some, but limited value in using pretreatment structural brain MRI to predict drug treatment outcome in MDD, the models did not generalize to an independent cohort suggesting limited clinical applicability. This study emphasizes the importance of assessing model generalizability for establishing clinical utility.

AB - Brain morphology has been suggested to be predictive of drug treatment outcome in major depressive disorders (MDD). The current study aims at evaluating the performance of pretreatment structural brain magnetic resonance imaging (MRI) measures in predicting the outcome of a drug treatment of MDD in a large single-site cohort, and, importantly, to assess the generalizability of these findings in an independent cohort. The random forest, boosted trees, support vector machines and elastic net classifiers were evaluated in predicting treatment response and remission following an eight week drug treatment of MDD using structural brain measures derived with FastSurfer (FreeSurfer). Models were trained and tested within a nested cross-validation framework using the NeuroPharm dataset (n = 79, treatment: escitalopram); their generalizability was assessed using an independent clinical dataset, EMBARC (n = 64, treatment: sertraline). Prediction of antidepressant treatment response in the Neuropharm cohort was statistically significant for the random forest (p = 0.048), whereas none of the models could significantly predict remission. Furthermore, none of the models trained using the entire NeuroPharm dataset could significantly predict treatment outcome in the EMBARC dataset. Although our primary findings in the NeuroPharm cohort support some, but limited value in using pretreatment structural brain MRI to predict drug treatment outcome in MDD, the models did not generalize to an independent cohort suggesting limited clinical applicability. This study emphasizes the importance of assessing model generalizability for establishing clinical utility.

U2 - 10.1016/j.nicl.2022.103224

DO - 10.1016/j.nicl.2022.103224

M3 - Journal article

C2 - 36252556

VL - 36

JO - NeuroImage: Clinical

JF - NeuroImage: Clinical

SN - 2213-1582

M1 - 103224

ER -