Enhanced Large Language Models for Effective Screening of Depression and Anxiety

2025-01-15

AI Summary

To address the scarcity of clinical data, high annotation costs, and significant ethical risks in depression and anxiety screening, this paper proposes EmoScan: a novel system leveraging a first-of-its-kind controllable dialogue synthesis pipeline to construct PsyInterview, a synthetic dataset comprising 1,157 interview dialogues. EmoScan enables the first explainable, joint screening by large language models for DSM-5 fine-grained disorders (e.g., major depressive disorder). It integrates clinical guideline constraints, multi-turn affective state tracking, and explanation generation via instruction tuning and domain alignment. Experiments demonstrate that EmoScan achieves a fine-grained screening F1-score of 0.7467—surpassing GPT-4—explanation quality with a BERTScore of 0.9408, and cross-dataset generalization F1 of 0.67. Human–AI co-evaluation confirms its significantly superior clinical interviewing capability over all baselines.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Emotional Intelligence

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Depressive and anxiety disorders are widespread, necessitating timely identification and management. Recent advances in Large Language Models (LLMs) offer potential solutions, yet high costs and ethical concerns about training data remain challenges. This paper introduces a pipeline for synthesizing clinical interviews, resulting in 1,157 interactive dialogues (PsyInterview), and presents EmoScan, an LLM-based emotional disorder screening system. EmoScan distinguishes between coarse (e.g., anxiety or depressive disorders) and fine disorders (e.g., major depressive disorders) and conducts high-quality interviews. Evaluations showed that EmoScan exceeded the performance of base models and other LLMs like GPT-4 in screening emotional disorders (F1-score=0.7467). It also delivers superior explanations (BERTScore=0.9408) and demonstrates robust generalizability (F1-score of 0.67 on an external dataset). Furthermore, EmoScan outperforms baselines in interviewing skills, as validated by automated ratings and human evaluations. This work highlights the importance of scalable data-generative pipelines for developing effective mental health LLM tools.

Problem

• Cost-effective Solutions
• Ethical Concerns
• Mental Health Disorders

Innovation

• Large-scale Data Generation
• EmoScan System
• Mental Health Application