To develop a multimodal deep learning–based classification model for adolescent bipolar depression (ABD) with verbal auditory hallucinations (AVHs).
Approach:
Key Findings:
The model achieved an optimal classification accuracy of 71.43% on the fixed test set, demonstrating balanced classification performance with precision, recall, and F1-score all reaching 0.75.
Interpretation:
The study proposes a novel multimodal Transformer-based framework for classifying ABD patients with AVHs, demonstrating preliminary technical feasibility.
Limitations:
The study is based on a small dataset of 47 patients.
Results may not generalize beyond the specific population studied.
Conclusion:
The advanced model architecture effectively integrates heterogeneous data for classification tasks.
