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

Area of Science:

• Neuroscience
• Psychiatry
• Machine Learning

Background:

• Depression frequently co-occurs with chronic insomnia disorder (CID).
• The orbital frontal cortex (OFC) is implicated as a key brain region linking insomnia and depression.
• Neuroimaging studies suggest altered OFC function in comorbid conditions.

Purpose of the Study:

• To develop a machine learning model to differentiate CID patients with and without depressive symptoms.
• To investigate the role of OFC functional connectivity (FC) as a potential biomarker for comorbid depression in CID.
• To validate the predictive accuracy of the OFC FC-based model in an independent cohort.

Main Methods:

• Seventy CID patients were classified into high (CID-HD) and low (CID-LD) depressive symptom groups.
• OFC functional connectivity (FC) networks were constructed using the OFC as a seed region.
• A linear kernel Support Vector Machine (SVM) model was trained and tested for classification accuracy.

Main Results:

• The OFC FC-based model achieved 76.92% accuracy in classifying CID-HD and CID-LD groups (p = 0.0009).
• The model's area under the receiver operating characteristic curve was 0.84.
• Key predictive features included OFC connectivity with reward, salience, and default mode networks.
• Validation in an independent cohort yielded 67.9% accuracy.

Conclusions:

• OFC functional connectivity patterns can differentiate CID patients with and without depressive symptoms.
• An OFC FC-based machine learning approach shows potential as a biomarker for early diagnosis and intervention.
• This method may aid in managing comorbid depression in chronic insomnia disorder.