A Dual-Channel Prediction-Interpretation Framework with Pre-Trained Language Models and SHAP Explainability

This study addresses the challenges of data noise and model interpretability in depression diagnosis by proposing an intelligent diagnostic framework based on real-world medical scenarios. Utilizing a labeled dataset of 11,188 Chinese online consultation records, we developed a dual-channel architecture integrating BERT/RoBERTa pre-trained models with the SHAP interpretability framework for depression severity classification. Experimental results demonstrated that the BERT model achieved 92% overall accuracy, with 93% accuracy specifically for severe depression detection. SHAP analysis revealed the model’s focus on clinically relevant features like suicidal tendencies and low mood, showing significant alignment with DSM-5 diagnostic criteria. The study confirms pre-trained models’ capability in extracting pathological semantics from medical texts, while the “prediction-interpretation” framework provides a technical prototype for overcoming clinical application barriers of black-box models.