Modeling essential connections in obsessive–compulsive disorder patients using functional MRI

Xiaodan Xing,Feng Shi,Zhen Wei,Xiang Sean Zhou,Qiong Yang,Xu Chu,Qingfeng Li,Hongying Han,Ziwen Peng,Lili Jin,Yiqiang Zhan,Chuanyong Xu,Zhong Xue

doi:10.1002/brb3.1499

Abstract

ObjectObsessive–compulsive disorder (OCD) is a mental disease in which people experience uncontrollable and repetitive thoughts or behaviors. Clinical diagnosis of OCD is achieved by using neuropsychological assessment metrics, which are often subjectively affected by psychologists and patients. In this study, we propose a classification model for OCD diagnosis using functional MR images.MethodsUsing functional connectivity (FC) matrices calculated from brain region of interest (ROI) pairs, a novel Riemann Kernel principal component analysis (PCA) model is employed for feature extraction, which preserves the topological information in the FC matrices. Hierarchical features are then fed into an ensemble classifier based on the XGBoost algorithm. Finally, decisive features extracted during classification are used to investigate the brain FC variations between patients with OCD and healthy controls.ResultsThe proposed algorithm yielded a classification accuracy of 91.8%. Additionally, the well‐known cortico–striatal–thalamic–cortical (CSTC) circuit and cerebellum were found as highly related regions with OCD. To further analyze the cerebellar‐related function in OCD, we demarcated cerebellum into three subregions according to their anatomical and functional property. Using these three functional cerebellum regions as seeds for brain connectivity computation, statistical results showed that patients with OCD have decreased posterior cerebellar connections.ConclusionsThis study provides a new and efficient method to characterize patients with OCD using resting‐state functional MRI. We also provide a new perspective to analyze disease‐related features. Despite of CSTC circuit, our model‐driven feature analysis reported cerebellum as an OCD‐related region. This paper may provide novel insight to the understanding of genetic etiology of OCD.

Highlights

Obsessive–compulsive disorder (OCD) is a mental disorder with an approximate lifetime prevalence of 1%–3% (Angst et al, 2005)
Patients suffering from obsessions have persistent intrusive thoughts, and patients suffering from compulsions have repetitive behaviors. Despite of these symptoms and their impairment to patients' social functioning, it is highly possible that OCD can rise to a wide spectrum of additional psychiatric disorders, including major depressive disorder (MDD), tics, and panic disorder (PD; Angst et al, 2005; Ruscio, Stein, Chiu, & Kessler, 2010)
A classifier using Riemann kernel principal component analysis (PCA) was proposed, which preserves the topological information of functional connectivity matrices and outperforms traditional classifiers such as linear PCA or other linear decomposition algorithm

Summary

Introduction

Obsessive–compulsive disorder (OCD) is a mental disorder with an approximate lifetime prevalence of 1%–3% (Angst et al, 2005). The diagnosis of OCD is achieved by (a) neuropsychological metrics, such as YBOCS (Goodman, Price, Rasmussen, Mazure, Delgado, et al, 1989; Goodman, Price, Rasmussen, Mazure, Fleischmann, et al, 1989), Obsessive–Compulsive Inventory (OCI; Foa et al, 2002), and CY-BOCS for children (Scahill et al, 1997), (b) physical tests, such as complete blood count and alcohol/drug tests, and (c) interview by psychologists. Such diagnosis methods are affected by psychologists' subjection, and symptoms of comorbidities interfere with the diagnosis. A more objective diagnosis model is desirable for accurate and robust measurements

Objectives

Methods

Findings

Conclusion