Background Characterization of the dynamics of functional brain network has gained increased attention in the study of depression. However, most studies have focused on single temporal dimension, while ignoring spatial dimensional information, hampering the discovery of validated biomarkers for depression. Purpose To integrate temporal and spatial functional MRI variability features of dynamic brain network in machine‐learning techniques to distinguish patients with major depressive disorder (MDD) from healthy controls (HCs). Study Type Prospective. Population A discovery cohort including 119 patients and 106 HCs and an external validation cohort including 126 patients and 124 HCs from Rest‐meta‐MDD consortium. Field Strength/Sequence A 3.0 T/resting‐state functional MRI using the gradient echo sequence. Assessment A random forest (RF) model integrating temporal and spatial variability features of dynamic brain networks with separate feature selection method (MSFS) was implemented for MDD classification. Its performance was compared with three RF models that used: temporal variability features (MTVF), spatial variability features (MSVF), and integrated temporal and spatial variability features with hybrid feature selection method (MHFS). A linear regression model based on MSFS was further established to assess MDD symptom severity, with prediction performance evaluated by the correlations between true and predicted scores. Statistical Tests Receiver operating characteristic analyses with the area under the curve (AUC) were used to evaluate models' performance. Pearson's correlation was used to assess relationship of predicted scores and true scores. P < 0.05 was considered statistically significant. Results The model with MSFS achieved the best performance, with AUCs of 0.946 and 0.834 in the discovery and validation cohort, respectively. Additionally, altered temporal and spatial variability could significantly predict the severity of depression (r = 0.640) and anxiety (r = 0.616) in MDD. Data Conclusion Integration of temporal and spatial variability features provides potential assistance for clinical diagnosis and symptom prediction of MDD. Evidence Level 2. Technical Efficacy Stage 2.

BackgroundPrevious studies have found qualitative structural and functional brain changes in major depressive disorder (MDD) patients. However, most studies ignored the complementarity of multisequence MRI neuroimaging features and cannot determine accurate biomarkers.PurposeTo evaluate machine‐learning models combined with multisequence MRI neuroimaging features to diagnose patients with MDD.Study TypeProspective.SubjectsA training cohort including 111 patients and 90 healthy controls (HCs) and a test cohort including 28 patients and 22 HCs.Field Strength/SequenceA 3.0 T/T1‐weighted imaging, resting‐state functional MRI with echo‐planar sequence, and single‐shot echo‐planar diffusion tensor imaging.AssessmentRecruitment and integration were used to reflect the dynamic changes of functional networks, while gray matter volume and fractional anisotropy were used to reflect the changes in the morphological and anatomical network. We then fused features with significant differences in functional, morphological, and anatomical networks to evaluate a random forest (RF) classifier to diagnose patients with MDD. Furthermore, a support vector machine (SVM) classifier was used to verify the stability of neuroimaging features. Linear regression analyses were conducted to investigate the relationships among multisequence neuroimaging features and the suicide risk of patients.Statistical TestsThe comparison of functional network attributes between patients and controls by two‐sample t‐test. Network‐based statistical analysis was used to identify structural and anatomical connectivity changes between MDD and HCs. The performance of the model was evaluated by receiver operating characteristic (ROC) curves.ResultsThe performance of the RF model integrating multisequence neuroimaging features in the diagnosis of depression was significantly improved, with an AUC of 93.6%. In addition, we found that multisequence neuroimaging features could accurately predict suicide risk in patients with MDD (r = 0.691).Data ConclusionThe RF model fusing functional, morphological, and anatomical network features performed well in diagnosing patients with MDD and provided important insights into the pathological mechanisms of MDD.Evidence Level1.Technical EfficacyStage 2.