Print Close

Local-Global Correlation Fusion-Based GNN for Prediction of Antidepressant Response

Poster No:

1155

Submission Type:

Abstract Submission

Authors:

Rui Liu¹, Ximan Hou¹, Shuyu Liu², Kaini Qiao¹, Aihong Yu¹, Gang Wang¹

Institutions:

¹Beijing Anding Hospital, Capital Medical University, Beijing, China, ²Medical Robot Research Institute, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China

First Author:

Rui Liu
Beijing Anding Hospital, Capital Medical University
Beijing, China

Co-Author(s):

Ximan Hou
Beijing Anding Hospital, Capital Medical University
Beijing, China

Shuyu Liu
Medical Robot Research Institute, School of Biomedical Engineering, Shanghai Jiao Tong University
Shanghai, China

Kaini Qiao
Beijing Anding Hospital, Capital Medical University
Beijing, China

Aihong Yu
Beijing Anding Hospital, Capital Medical University
Beijing, China

Gang Wang
Beijing Anding Hospital, Capital Medical University
Beijing, China

Introduction:

Depressed mood and anhedonia are two core symptoms of major depressive disorder (MDD), mediated by reward and emotion regulation circuit of the brain, which plays an important role in the pathophysiology of depression and the prediction of antidepressant response. The purpose of this study was to identify the neuroimaging biomarkers for the prediction of remission in MDD patients based on the features of reward and emotion regulation circuit and clinical characteristics before treatment.

Methods:

230 untreated MDD patients were enrolled from Beijing Anding Hospital. The patients received SSRIs for 8 weeks /12 weeks. The resting state fMRI data and clinical data were collected before treatment. A local-global GNN model was established with the features of reward and emotion regulation circuit and clinical characteristics from 164 MDD patients to distinguish patients in remission from those in non-remission. The performance of the model was evaluated using 5-fold cross-validation. Furthermore, 66 MDD patients were used as an independent validation set to evaluate the model's performance.

Results:

The accuracy of the model for predicting remission after 8 /12 weeks of SSRIs was 76.21% (sensitivity = 75.20%, specificity = 77.48%, AUC = 0.78). The result was validated in an independent validation set (ACC = 72.73%, sensitivity = 73.53%, specificity = 71.88%, AUC = 0.74). Ablation experiments indicated that imaging features contribute more significantly than clinical features. The brain regions involved in the most contributing imaging features mainly include the right globus pallidus, bilateral putamen, left hippocampus, bilateral thalamus, and bilateral anterior cingulate gyrus.

·Fig. 1 Performance validation of the prediction model.

Conclusions:

In conclusion, we demonstrated that the acute-phase efficacy of SSRI treatment in MDD patients can be predicted using functional connectivity features of the emotion regulation and reward circuits, with imaging features carrying significantly more weight than clinical features. These results indicated that neuroimaging features of reward and emotion regulation circuit are potential predictors for the response of antidepressant drugs. In the future, it is necessary to increase the sample size for multi-site independent validation to provide a reference for precise treatment of depression.

Modeling and Analysis Methods:

Classification and Predictive Modeling ¹

fMRI Connectivity and Network Modeling ²

Keywords:

Affective Disorders

FUNCTIONAL MRI

Modeling

Treatment

^1|2Indicates the priority used for review

Abstract Information

By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.

I accept

The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:

I do not want to participate in the reproducibility challenge.

Please indicate below if your study was a "resting state" or "task-activation” study.

Resting state

Healthy subjects only or patients (note that patient studies may also involve healthy subjects):

Patients

Was this research conducted in the United States?

Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.

Yes

Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.

Not applicable

Please indicate which methods were used in your research:

Functional MRI

Computational modeling

For human MRI, what field strength scanner do you use?

3.0T

Provide references using APA citation style.

Not applicable

UNESCO Institute of Statistics and World Bank Waiver Form

I attest that I currently live, work, or study in a country on the UNESCO Institute of Statistics and World Bank List of Low and Middle Income Countries list provided.