Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges

大型语言模型在心理健康领域的应用：应用、创新与伦理挑战的系统综述

Abstract: We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools, prompt engineering, multimodal learning, and ethical considerations.

摘要： 我们对大型语言模型（LLM）在医疗健康领域的应用进行了综述，涵盖了社交媒体分析、临床对话代理、治疗支持工具、提示工程（Prompt Engineering）、多模态学习以及伦理考量等方面。

We integrate findings from interdisciplinary studies utilizing diverse data sources such as social media posts, electronic medical records, and multimodal inputs to enable early detection of depression, suicide risk assessment, personalized therapy support, and psychoeducational content generation.

我们整合了跨学科研究的成果，这些研究利用社交媒体帖子、电子病历和多模态输入等多种数据源，旨在实现抑郁症的早期检测、自杀风险评估、个性化治疗支持以及心理教育内容的生成。

Our review highlights advancements in LLM models and annotation strategies that enhance interpretability and clinical relevance, while we also emphasize the critical role of prompt engineering for domain adaptation.

我们的综述重点介绍了在增强可解释性和临床相关性方面的 LLM 模型及标注策略的进展，同时也强调了提示工程在领域适应（Domain Adaptation）中的关键作用。

We also discuss emerging multimodal fusion techniques integrating text, speech, and sensor data for improved mental health diagnosis and monitoring.

我们还讨论了新兴的多模态融合技术，该技术通过整合文本、语音和传感器数据，以改善心理健康的诊断与监测。

Finally, we address ongoing ethical, sociotechnical, and regulatory challenges, and advocate frameworks to ensure safe, equitable, and accountable deployment of LLMs in real-world mental health care.

最后，我们探讨了当前面临的伦理、社会技术及监管挑战，并倡导建立相关框架，以确保 LLM 在现实心理健康护理中的安全、公平和负责任的部署。