Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration

TL;DR

This paper presents an interactive framework for depression detection in clinical interviews that models thematic content and correlations explicitly, allowing clinician intervention and improving detection accuracy significantly.

Contribution

It introduces a novel interactive depression detection framework that explicitly models intra- and inter-theme correlations and incorporates clinician-like feedback for better accuracy.

Findings

Achieved 35% improvement over state-of-the-art in depression detection accuracy.

Effectively models thematic correlations in clinical interview dialogues.

Enables interactive theme importance adjustment for clinicians.

Abstract

Automatic depression detection provides cues for early clinical intervention by clinicians. Clinical interviews for depression detection involve dialogues centered around multiple themes. Existing studies primarily design end-to-end neural network models to capture the hierarchical structure of clinical interview dialogues. However, these methods exhibit defects in modeling the thematic content of clinical interviews: 1) they fail to capture intra-theme and inter-theme correlation explicitly, and 2) they do not allow clinicians to intervene and focus on themes of interest. To address these issues, this paper introduces an interactive depression detection framework. This framework leverages in-context learning techniques to identify themes in clinical interviews and then models both intra-theme and inter-theme correlation. Additionally, it employs AI-driven feedback to simulate the interests of clinicians, enabling interactive adjustment of theme importance. PDIMC achieves absolute improvements of 35\% and 12\% compared to the state-of-the-art on the depression detection dataset DAIC-WOZ, which demonstrates the effectiveness of modeling theme correlation and incorporating interactive external feedback.