Classification of Irritable Bowel Syndrome Using Brain Functional Connectivity Strength and Machine Learning

Irritable Bowel Syndrome (IBS) is a prevalent condition characterized by dysregulated brain-gut interactions. Despite its widespread impact, the brain mechanism of IBS remains incompletely understood, and there is a lack of objective diagnostic criteria and biomarkers. This study aims to investigate brain network alterations in IBS patients using the functional connectivity strength (FCS) method and to develop a support vector machine (SVM) classifier for distinguishing IBS patients from healthy controls (HCs).

Thirty-one patients with IBS and thirty age and sex-matched HCs were enrolled in this study and underwent resting-state functional magnetic resonance imaging (fMRI) scans. We applied FCS to assess global brain functional connectivity changes in IBS patients. An SVM-based machine - learning approach was then used to evaluate whether the altered FCS regions could serve as fMRI-based markers for classifying IBS patients and HCs.

Compared to the HCs, patients with IBS showed significantly increased FCS in the left medial orbitofrontal cortex (mOFC) and decreased FCS in the bilateral cingulate cortex/precuneus (PCC/Pcu) and middle cingulate cortex (MCC). The machine-learning model achieved a classification accuracy of 91.9% in differentiating IBS patients from HCs.

These findings reveal a unique pattern of FCS alterations in brain areas governing pain regulation and emotional processing in IBS patients. The identified abnormal FCS features have the potential to serve as effective biomarkers for IBS classification. This study may contribute to a deeper understanding of the neural mechanisms of IBS and aid in its diagnosis in clinical practice.