Background: Major depressive disorder (MDD) is a debilitating mental illness with more than 50% of patients not achieving an adequate response using first-line treatments. Reliable models that predict antidepressant treatment outcome are needed to guide clinical decision making. We aimed to build predictive models of treatment improvement for MDD patients using machine learning approaches based on fMRI resting-state functional connectivity patterns.
Methods: Resting-state fMRI data were acquired from 192 untreated MDD patients at recruitment, and their severity of depression was assessed by Hamilton Rating Scale for Depression (HAMD) at baseline. Patients were given medication after the initial MR scan and their symptoms were monitored through HAMD for a period of six months. Connectome-based predictive modeling (CPM) algorithms were implemented to predict the improvement in HAMD score at one month from resting-state connectivity at baseline. Additionally, by selectively combining the features from all leave-one-out iterations in the model building stage, we created a consensus model that could be generalized to predict improvement in HAMD score in samples of non-overlapping subjects at different time points.
Results: Using baseline functional connectivity, CPM successfully predicted symptom improvement of depression at one month. In addition, a consensus 'MDD improvement model' could predict symptom improvement for novel individuals at the two-week, one-month, two-month and three-month time points after antidepressant treatment.
Conclusions: Individual pre-treatment functional brain networks contain meaningful information that can be gleaned to build predictors of treatment outcome. The identified MDD improvement networks could be an appropriate biomarker for predicting individual therapeutic response of antidepressant treatment. Replication and validation using other large datasets will be a key next step before these models can be used in clinical practice.
Copyright © 2020 Elsevier B.V. All rights reserved.