Probing the clinical and brain structural boundaries of bipolar and major depressive disorder

Tao Yang,Ruizhi Mao,Na Zhu,Guoqing Zhao,Xing Wang,Zuowei Wang,Rubai Zhou,Yousong Su,Daihui Peng,Sophia Frangou,Weiping Xia,Lakshmi N Yatham,Yiru Fang,Jia Huang,Xiao Lin,Yun Wang,Raymond W Lam,Jun Chen

doi:10.1038/s41398-020-01169-7

Abstract

Bipolar disorder (BD) and major depressive disorder (MDD) have both common and distinct clinical features, that pose both conceptual challenges in terms of their diagnostic boundaries and practical difficulties in optimizing treatment. Multivariate machine learning techniques offer new avenues for exploring these boundaries based on clinical neuroanatomical features. Brain structural data were obtained at 3 T from a sample of 90 patients with BD, 189 patients with MDD, and 162 healthy individuals. We applied sparse partial least squares discriminant analysis (s-PLS-DA) to identify clinical and brain structural features that may discriminate between the two clinical groups, and heterogeneity through discriminative analysis (HYDRA) to detect patient subgroups with reference to healthy individuals. Two clinical dimensions differentiated BD from MDD (area under the curve: 0.76, P < 0.001); one dimension emphasized disease severity as well as irritability, agitation, anxiety and flight of ideas and the other emphasized mostly elevated mood. Brain structural features could not distinguish between the two disorders. HYDRA classified patients in two clusters that differed in global and regional cortical thickness, the distribution proportion of BD and MDD and positive family history of psychiatric disorders. Clinical features remain the most reliable discriminant attributed of BD and MDD depression. The brain structural findings suggests that biological partitions of patients with mood disorders are likely to lead to the identification of subgroups, that transcend current diagnostic divisions into BD and MDD and are more likely to be aligned with underlying genetic variation. These results set the foundation for future studies to enhance our understanding of brain–behavior relationships in mood disorders.

Highlights

Mood disorders, primarily major depressive disorder (MDD) and bipolar disorder (BD), jointly affect up 20% of the population over their lifetime[1] and rank amongst the most significant causes of disability worldwide[1]
Regardless of diagnosis, patients underperformed in the Wisconsin Card sorting test (WCST) compared to healthy individuals in terms of percentage of perseverative responses, percentage of total errors, percentage of conceptual level responses, number of categories completed, and total number required for completing the first category (Supplementary Table S3)
The results showed that the two disorders in our study could be distinguished from each other with moderate accuracy based on clinical features but not brain structure

Summary

Introduction

Primarily major depressive disorder (MDD) and bipolar disorder (BD), jointly affect up 20% of the population over their lifetime[1] and rank amongst the most significant causes of disability worldwide[1]. Both disorders present with recurrent depressive psychopathology while manic symptoms are the diagnostic hallmark of BD2. The significant symptomatic overlap between MDD and BD across the entire course of these disorders and the dominance of depressive symptoms at the early stages of BD often delays the correct identification of BD cases[7] with significant implications for treatment decisions[8], clinical outcomes[9], and service use[10].

Objectives

Methods

Results

Conclusion