Enhanced Large Language Models for Effective Screening of Depression and Anxiety

TL;DR

This paper presents EmoScan, an LLM-based system that synthesizes clinical interviews and effectively screens for depression and anxiety, outperforming existing models in accuracy, explanation quality, and generalizability.

Contribution

It introduces PsyInterview, a large dataset of synthetic clinical dialogues, and EmoScan, a novel LLM system for emotional disorder screening with superior performance and interview quality.

Findings

EmoScan achieved an F1-score of 0.7467 in screening accuracy.

It provided high-quality explanations with a BERTScore of 0.9408.

EmoScan demonstrated robust generalizability with an F1-score of 0.67 on external data.

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.