Predicting clinical responses in major depression using intrinsic functional connectivity

There has been increasing interest in multivariate pattern analysis (MVPA) as a means of distinguishing psychiatric patients from healthy controls using brain imaging. However, it remains unclear whether MVPA methods can accurately estimate the medication status of psychiatric patients. This study aims to develop an MVPA approach to accurately predict the antidepressant medication status of individuals with major depression on the basis of whole-brain resting-state functional connectivity MRI (rs-fcMRI). We investigated data from rs-fcMRI of 24 medication-naive depressed patients, 16 out of whom subsequently underwent antidepressant treatment and achieved clinical recovery, and 29 demographically similar controls. By training a linear support vector machine classifier and combining it with principal component analysis, the medication-naive patients were identified from the healthy controls with 100% accuracy. In addition, we found reliable correlations between MVPA prediction scores and clinical symptom severity. Moreover, the most discriminative functional connections were located within or across the cerebellum and default mode, affective, and sensorimotor networks, indicating that these networks may play important roles in major depression. Most importantly, only approximate to 30% of these discriminative connections were normalized in clinically recovered patients after antidepressant treatment. The current study may not only show the feasibility of estimating medication status by MVPA of whole-brain rs-fcMRI data in major depression but also shed new light on the pathological mechanism of this disorder.