King's College London

Research portal

Detecting Neuroimaging Biomarkers for Depression: A Meta-Analysis of Multivariate Pattern Recognition Studies

Research output: Contribution to journalArticle

Joseph Kambeitz, Carlos Cabral, Matthew D. Sacchet, Ian H. Gotlib, Roland Zahn, Mauricio H. Serpa, Martin Walter, Peter Falkai, Nikolaos Koutsouleris

Original languageEnglish
JournalBiological Psychiatry
Early online date9 Nov 2016
DOIs
StatePublished - 9 Nov 2016

Documents

King's Authors

Abstract

Introduction Multiple studies have examined functional and structural brain alteration in patients diagnosed with from Major Depressive Disorder (MDD). The introduction of multivariate statistical methods allows investigators to utilize data concerning these brain alterations to generate diagnostic models that accurately differentiate patients with MDD from healthy controls. However, there is substantial heterogeneity in the reported results, the methodological approaches, and the clinical characteristics of participants in these studies. Method We conducted a meta-analysis of all studies using neuroimaging (volumetric measures derived from T1 weighted images, task-based functional MRI, resting-state MRI, or diffusion-tensor imaging) in combination with multivariate statistical methods to differentiate patients diagnosed with MDD from healthy controls. Results Thirty-three (k=33) samples including n=912 patients with MDD and n=894 healthy control subjects were included in the meta-analysis. Across all studies, patients with MDD were separated from healthy control subjects with 77% sensitivity and 78% specificity. Classification based on resting-state MRI (sensitivity of 85%, specificity of 83%) and on DTI data (sensitivity of 88%, specificity of 92%) outperformed classification based on structural MRI (sensitivity of 70%, specificity of 71%) and task-based functional MRI (sensitivity 74%, specificity 77%). Discussion Our results demonstrate the high representational capacity of multivariate statistical methods to identify neuroimaging-based biomarkers of depression. Future studies are needed to elucidate whether multivariate neuroimaging analysis has the potential to generate clinically useful tools for the differential diagnosis of affective disorders and the prediction of both treatment response and functional outcome.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454