Second-order morphometric similarity networks predict response to transcutaneous auricular vagus nerve stimulation in major depressive disorder: a two-center study - Summary - MDSpire
Advertisement
Second-order morphometric similarity networks predict response to transcutaneous auricular vagus nerve stimulation in major depressive disorder: a two-center study
To develop and externally validate a morphometric similarity network-based prediction model for treatment response to transcutaneous auricular vagus nerve stimulation (taVNS) in major depressive disorder (MDD).
Approach:
Participants: 122 antidepressant-free MDD patients were recruited from two centers, with structural MRI conducted before and after 8 weeks of taVNS.
Data Analysis: Baseline morphometric similarity network features were extracted, and a LASSO logistic regression model was trained and validated.
Key Findings:
MSN-II showed significant predictive performance (AUC = 0.792 ± 0.158; permutation P < 0.001) and generalized well to external validation (AUC = 0.856, 95% CI: 0.693–0.978).
The left orbitofrontal cortex area 13 (L_OFC_A13; β = –0.649) was identified as the strongest predictor of treatment response.
Non-responders had higher baseline MSN-II in L_OFC_A13 (P = 0.021) and significant post-treatment decreases (P < 0.001), while responders remained stable (Time × Group interaction, P = 0.005).
Interpretation:
MSN-II features from limbic regions may serve as predictive biomarkers for taVNS response in MDD, with L_OFC_A13 identified as a key area.
Limitations:
The study's sample size was limited to 122 participants, which may affect the generalizability of the findings.
The study design was observational and did not include a control group.
Conclusion:
MSN-II provides promising predictive capabilities for individualized treatment planning in MDD using taVNS.
