English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Major depressive disorder is a serious and heterogeneous psychiatric disorderthat needs accurate diagnosis. Resting-state functional MRI (rsfMRI), whichcaptures multiple perspectives on brain structure, function, and connectivity,is increasingly applied in the diagnosis and pathological research of mentaldiseases. Different machine learning algorithms are then developed to exploitthe rich information in rsfMRI and discriminate MDD patients from normalcontrols. Despite recent advances reported, the discrimination accuracy hasroom for further improvement. The generalizability and interpretability of themethod are not sufficiently addressed either. Here, we propose a machinelearning method (MFMC) for MDD discrimination by concatenating multiplefeatures and stacking multiple classifiers. MFMC is tested on the REST-meta-MDDdata set that contains 2428 subjects collected from 25 different sites. MFMCyields 96.9% MDD discrimination accuracy, demonstrating a significantimprovement over existing methods. In addition, the generalizability of MFMC isvalidated by the good performance when the training and testing subjects arefrom independent sites. The use of XGBoost as the meta classifier allows us toprobe the decision process of MFMC. We identify 13 feature values related to 9brain regions including the posterior cingulate gyrus, superior frontal gyrusorbital part, and angular gyrus, which contribute most to the classificationand also demonstrate significant differences at the group level. The use ofthese 13 feature values alone can reach 87% of MFMC's full performance whentaking all feature values. These features may serve as clinically usefuldiagnostic and prognostic biomarkers for mental disorders in the future.

Multi-feature concatenation and multi-classifier stacking: an  interpretable and generalizable machine learning method for MDD  discrimination with rsfMRI