Abstract
BackgroundAntidepressant medications are suggested as the first-line treatment in patients with major depressive disorder (MDD). However, the drug therapy outcomes vary from person to person. The functional activity of the brain and DNA methylation levels correlate with the antidepressant efficacy. To predict the early antidepressant responses in MDD and establish the prediction framework, we aimed to apply multidimensional data based on the resting-state activity of the brain and HTR1A/1B methylation. MethodsThe values of Amplitude of Low-Frequency Fluctuations (ALFF) and regional homogeneity (ReHo) were measured as variables in 116 brain regions along with 181 CpG sites in the promoter region of HTR1A/1B and 11 clinical characteristics. After performing the feature reduction step using the least absolute shrinkage and selection operator (LASSO) method, the selected variables were put into Support Vector Machines (SVM), Random Forest (RF), Naïve Bayes (NB), and logistic regression (LR), consecutively, to construct the prediction models. The models’ performance was evaluated by the Leave-One-Out Cross-Validation. ResultsThe LR model composed of the selected multidimensional features reached a maximum performance of 78.57% accuracy and 0.8340 area under the ROC curve (AUC). The prediction accuracies based on multidimensional datasets were found to be higher than those obtained from the data based only on fMRI or methylation. LimitationsA relatively small sample size potentially restricted the usage of our prediction framework in clinical applications. ConclusionOur study revealed that combining the data of brain imaging and DNA methylation could provide a complementary effect in predicting early-stage antidepressant outcomes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have