Early detection of depression is crucial for implementing interventions. Deep learning-based computer vision (CV), semantic, and acoustic analysis have enabled the automated analysis of visual and auditory signals.

We proposed an automated depression detection model based on artificial intelligence (AI) that combined visual, audio and text clues. Moreover, we validated the model's performance in multiple scenarios, including interviews with chatbot.

A chatbot for depressive symptom inquiry powered by GPT-2.0 was developed. The Brief Affective Interview Task was designed as supplement. Audio-video and textual clues were captured during interview, and features of different modalities were fused using a network with a multi-head cross-attention mechanism. To validate the model's generalizability, we conducted external validation using an independent dataset.

(1)In the …