Background
Treatment outcomes for patients with major depressive disorder (MDD) are highly variable. It is difficult to predict using clinical and demographic features, and approximately 30-50% of patients with MDD do not respond to first-line medication or psychotherapy. Therefore, treatment selection often begins with a “trial and error” approach, with weeks or months long trials until an effective and well-tolerated treatment is found.
Prior works have assessed utilizing neuroimaging features for treatment outcome prediction. A meta-analysis explored prediction based on electroencephalogram (EEG) and MRI, achieving an area under the curve (AUC) of 0.85. This meta-analysis didn’t specify neuroimaging techniques, limiting insights into the specific role of MRI features for MDD treatment outcomes. Moreover, a meta-analysis of brain MRI features used for outcome prediction in MDD reported an AUC of 0.84. However, the expanding literature, along with limitations and unresolved research questions of prior work, emphasizes the need for further investigation. For example, this meta-analysis omitted separate subgroup meta-analyses for functional and structural MRI (fMRI and sMRI) studies, preventing a detailed understanding of the performance of different MRI modalities. Moreover, for functional MRI studies, the potential differential predictive utility of resting-state fMRI (rsfMRI) and task-based fMRI (tbfMRI) has not been systematically examined. Furthermore, no meta-analyses have compared the predictive potential of MRI and clinical features.
The primary objective of the present meta-analysis was to evaluate the overall performance of clinical and brain MRI features for predicting treatment outcomes for MDD. A secondary objective was to explore the utility of different MRI modalities for predicting treatment outcomes and determine variations in predictive performance for different interventions.
MRI outperforms clinical features in treatment prediction
We included 13 studies that used clinical features to predict treatment outcomes, covering 4301 patients (mean age, 45.1 years; male/female, 1753/2548); and 44 MRI studies recruited 2623 patients (mean age, 38.2 years; male/female, 1109/1514). Within MRI studies, 19 rsfMRI, 13 tbfMRI, and ten sMRI studies were included in modality subgroups; 27 MRI studies utilized antidepressants and nine utilized electroconvulsive therapy (ECT).
The overall log(DOR) of clinical studies for treatment outcome prediction was 1.62 (95% CI 1.16 to 2.09). The AUC of SROC curve was 0.73 (95% CI 0.67 to 0.81), sensitivity was 0.62 (95% CI 0.48 to 0.74), and specificity was 0.76 (95% CI 0.64 to 0.85). No covariates were identified to impact the sensitivity and specificity (P > .05). There was a low heterogeneity observed among studies (I2 = 42.4%). Deeks’ funnel plot asymmetry test did not reveal significant publication bias in the included studies (beta = 0.008, P = .51). No significant correlation was observed between the predicted log(DOR) and true log(DOR) in clinical studies (r = 0.12, P = .71).
The pooled meta-analysis of all included MRI studies revealed an overall log(DOR) of 2.53 (95% CI 2.22 to 2.84). The AUC of the SROC curve was 0.89 (95% CI 0.87 to 0.91). Sensitivity was 0.78 (95% CI 0.75 to 0.81), and specificity was 0.75 (95% CI 0.71 to 0.79). No covariates had a significant impact on overall sensitivity and specificity (P > .05). There was no evidence of heterogeneity observed among studies. Deeks’ funnel plot asymmetry test did not demonstrate significant publication bias in the included studies (beta = 0.001, P = .93). In the meta-regression comparing clinical and MRI studies, we identified significant differences in predicting treatment outcomes (Chi2 = 6.53, P = .03), with the MRI studies exhibiting higher sensitivity (Z = 3.42, P = .001).
rsfMRI better than tbfMRI in specificity
We found a significant difference in the sensitivity and specificity of outcomes predicted by the rsfMRI and tbfMRI subgroups (Chi2 = 8.70, uncorrected P = .013). Specifically, while the sensitivity was similar (Z = -1.13, P = .26), rsfMRI showed higher specificity than tbfMRI (Z = -2.86, P = .004). There was no significant difference in sensitivity and specificity in prediction of treatment outcome between sMRI and rsfMRI subgroups (Chi2 = 1.00, P = .61), between sMRI and tbfMRI subgroups (Chi2 = 1.70, P = .43), or between emotional and cognitive tbfMRI (Chi2 = 1.61, P = 0.45). Furthermore, we found that HDRS score was a significant covariate influencing the prediction in emotional task subgroup (Chi2 = 6.34, P = .04), with a negative impact on its specificity (Z = -2.88, P = .004).
Analysis of features selected for outcome predictions indicated that predictive brain regions were predominantly located within the limbic and default mode networks (DMN) for both rsfMRI and tbfMRI studies. The rsfMRI features included rsFC between ACC and middle frontal gyrus, amygdala, and dlPFC, as well as between medial PFC and posterior cingulate cortex (PCC). Predictive features for tbfMRI included task-based FC between limbic and somatomotor networks, as well as within DMN. Activation of ACC and precuneus in tbfMRI studies also contributed to prediction. The sMRI predictive features for all treatments predominantly included brain regions within limbic network not the DMN, including GMV of hippocampus, GM density of ACC, and CTh of hippocampus.
No differences in prediction but distinct brain features for different interventions
Meta-regression showed no significant differences between antidepressant (SSRI and other antidepressant studies combined) and ECT subgroups (combined across imaging modalities) in sensitivity and specificity (Chi2 = 0.98, P = .61), as well as in SSRIs and ECT (Chi2 = 0.10, P = .95). We observed that sample size significantly affected the predictive efficacy of ECT treatment outcomes (Chi2 = 7.98, P = .02), negatively influencing its sensitivity (Z = -3.50, P < .001).
We found that features for antidepressants, including SSRIs examined separately, were distributed in the limbic network and DMN. Predictive features included rsFC between hippocampus and angular gyrus, and between ACC and supplementary motor area. The task-based FC between DMN and somatomotor networks, and activation of medial PFC, were also significant predictors. In terms of ECT, features related to treatment outcome were mainly found in the limbic network, including rsFC between ACC and dlPFC, GMV of subgenual ACC, as well as CTh of hippocampus.
Predicting treatment outcomes in major depressive disorder using brain magnetic resonance imaging: a meta-analysis
