Orbitofrontal Cortex Functional Connectivity-Based Classification for Chronic Insomnia Disorder Patients With Depression Symptoms

Abstract

Depression is a common comorbid symptom in patients with chronic insomnia disorder (CID). Previous neuroimaging studies found that the orbital frontal cortex (OFC) might be the core brain region linking insomnia and depression. Here, we used a machine learning approach to differentiate CID patients with depressive symptoms from CID patients without depressive symptoms based on OFC functional connectivity. Seventy patients with CID were recruited and subdivided into CID with high depressive symptom (CID-HD) and low depressive symptom (CID-LD) groups. The OFC functional connectivity (FC) network was constructed using the altered structure of the OFC region as a seed. A linear kernel SVM-based machine learning approach was carried out to classify the CID-HD and CID-LD groups based on OFC FC features. The predict model was further verified in a new cohort of CID group (n = 68). The classification model based on the OFC FC pattern showed a total accuracy of 76.92% (p = 0.0009). The area under the receiver operating characteristic curve of the classification model was 0.84. The OFC functional connectivity with reward network, salience network and default mode network contributed the highest weights to the prediction model. These results were further validated in an independent CID group with high and low depressive symptom (accuracy = 67.9%). These findings provide a potential biomarker for early diagnosis and intervention in CID patients comorbid with depression based on an OFC FC-based machine learning approach.

Keywords: depression; functional connectivity; insomnia; machine learning; orbitofrontal cortex.

FIGURE 1

The mask and results of OFC based VBM analysis. (A) The OFC analysis mask for VBM analysis; (B) the group difference of OFC based VBM analysis, then the result (right OFCant) was selected for OFC FC analysis. OFC, orbital frontal cortex; OFCmed, medial OFC; OFCant, anterior OFC; OFClat, lateral OFC; OFCpost, posterior OFC; FC, functional connectivity.

FIGURE 2

Classification model for discriminating CID-HD from CID-LD patients based on the functional connectivity map of the right anterior orbital frontal cortex. (A) Histogram of function values for each group. (B) Confusion matrix of all folds. (C) Prediction values per fold of the classification model. Positive function values for CID-LD patients indicate true positives. Negative function values for CID-HD participants indicate true negatives. (D) Receiver operating characteristic curve (ROC) showing the area under the curve was 0.84. True positives = sensitivity; false-positives = 1 – specificity.

FIGURE 3

OFC FC network weight images (per ROI) for discriminating CID-HD and CID-LD patients. OFC, orbital frontal cortex; FC, functional connectivity; CID-HD, chronic insomnia disorder with high depressive symptoms; CID-LD, CID with low depressive symptoms; MCC, middle cingulate cortex; mOFC, medial orbital frontal cortex; INS, insula; POFC, inferior par opercularis frontal cortex; PCC, posterior cingulate cortex; MTG, middle temporal gyrus.