Neuroanatomical Classification in a Population-Based Sample of Psychotic Major Depression and Bipolar I Disorder with 1 Year of Diagnostic Stability

Rodrigo Machado-Vieira,Maristela S Schaufelberger,Christos Davatzikos,Jimit Doshi,Geraldo F Busatto,Yangming Ou,Marcus V Zanetti,Paulo R Menezes,Mauricio H Serpa,Marcia Scazufca,Luiz K Ferreira

doi:10.1155/2014/706157

Rodrigo Machado-Vieira, Maristela S Schaufelberger + Show 9 more

Open Access

https://doi.org/10.1155/2014/706157

Copy DOI

Abstract

The presence of psychotic features in the course of a depressive disorder is known to increase the risk for bipolarity, but the early identification of such cases remains challenging in clinical practice. In the present study, we evaluated the diagnostic performance of a neuroanatomical pattern classification method in the discrimination between psychotic major depressive disorder (MDD), bipolar I disorder (BD-I), and healthy controls (HC) using a homogenous sample of patients at an early course of their illness. Twenty-three cases of first-episode psychotic mania (BD-I) and 19 individuals with a first episode of psychotic MDD whose diagnosis remained stable during 1 year of followup underwent 1.5 T MRI at baseline. A previously validated multivariate classifier based on support vector machine (SVM) was employed and measures of diagnostic performance were obtained for the discrimination between each diagnostic group and subsamples of age- and gender-matched controls recruited in the same neighborhood of the patients. Based on T1-weighted images only, the SVM-classifier afforded poor discrimination in all 3 pairwise comparisons: BD-I versus HC; MDD versus HC; and BD-I versus MDD. Thus, at the population level and using structural MRI only, we failed to achieve good discrimination between BD-I, psychotic MDD, and HC in this proof of concept study.

Highlights

Mood disorders share a large number of clinical and neurobiological features
More frequent in bipolar disorder (BD), psychotic symptoms may be present in some patients with major depressive disorder (MDD) [3]
The authors found modest diagnostic accuracy (DA) of up to 73% in the differentiation between BD type I (BD-I) patients versus healthy controls (HC) when the classification was performed with the grey matter (GM) and 78% for the analysis based on the white matter (WM)

Summary

Introduction

Mood disorders share a large number of clinical and neurobiological features. The nonspecificity and variability of symptoms over time are frequent causes of misdiagnosis in patients with bipolar disorder (BD) [1, 2]. More frequent in BD, psychotic symptoms may be present in some patients with major depressive disorder (MDD) [3]. BioMed Research International patients presenting depressive episodes with psychotic features are at increased risk for developing BD [2, 4]. A medical tool that reliably differentiates patients with psychotic MDD from BD at an early stage of the illness would be highly useful to aid psychiatrists to improve diagnostic accuracy and, treatment response and prognosis in the clinical practice. Neuroanatomical pattern classification is a relative new technique that holds promise in solving diagnosis and outcome issues in psychiatry [5]. This new method for brain image analysis allows voxelwise between-group comparisons and classification of scans at an individual basis [5, 6]. Once the pattern of abnormalities which better discriminates two groups is defined, this morphological signature can be used to classify images at an individual basis, and measures of diagnostic accuracy (DA) can be obtained [5, 6]

Methods

Results

Discussion

Conclusion