Predicting depressive mood and its longitudinal changes using multimodal brain networks in young healthy adults

Transitioning from a euthymic state to severe depression is a continuous process. Early identification of depressive neural biomarkers in the healthy population can promote effective interventions and reduce the risk of developing depression.

We employed a longitudinal design and adopted the relevance vector regression (RVR) approach and multimodal MRI data to predict the depressive mood [i.e., Beck Depression Inventory (BDI) score] and its longitudinal changes in young healthy adults (N = 121). We constructed three models and compared their performance, which were model using functional connectivity features (FC model), structural connectivity features (SC model), and both FC and SC features (multi-modality model). Based on feature correlations with BDI, these models were further divided into positive and negative models.

For prediction of baseline BDI score, the FC model and multi-modality model exhibited superior predictive performance (rho ≥ 0.39, p < 0.001, R² ≥ 0.14). Feature analysis revealed that, FC involved parietal and prefrontal networks, and SC involved prefrontal and subcortical networks contributed more to the baseline prediction. As for prediction of longitudinal BDI changes, the multi-modality model (rho = 0.41, p < 0.001, R² = 0.09) showed the best performance among the three models. Its feature pattern was similar to that of baseline prediction, also involving brain areas such as the parietal and subcortical networks.

These findings revealed rich information of the neural basis underlying individual depressive mood from a multimodal perspective, which can provide reliable biomarkers for capturing mental health changes and future individualized assessment and intervention.