Semi-structured interviews (SSIs) are a commonly employed data-collection method in healthcare research, offering in-depth qualitative insights into subject experiences. Despite their value, the manual analysis of SSIs is notoriously time-consuming and labor-intensive, in part due to the difficulty of extracting and categorizing emotional responses, and challenges in scaling human evaluation for large populations. In this study, we develop RACER, a Large Language Model (LLM) based expert-guided automated pipeline that efficiently converts raw interview transcripts into insightful domain-relevant themes and sub-themes. We used RACER to analyze SSIs conducted with 93 healthcare professionals and trainees to assess the broad personal and professional mental health impacts of the COVID-19 crisis. RACER achieves moderately high agreement with two human evaluators (72%), which approaches the human inter-rater agreement (77%). Interestingly, LLMs and humans struggle with similar content involving nuanced emotional, ambivalent/dialectical, and psychological statements. Our study highlights the opportunities and challenges in using LLMs to improve research efficiency and opens new avenues for scalable analysis of SSIs in healthcare research.
MAGI: Multi-Agent Guided Interview for Psychiatric Assessment
Tsinghua University（清华大学）；Central South University（中南大学）；Beijing Institute of Technology（北京理工大学）；Sichuan University（四川大学）；Lingxin AI（灵心人工智能公司）；University of International Relations（国际关系学院）；Central University of Finance and Economics（中央财经大学）
ChatCounselor: A Large Language Models for Mental Health Support
Hong Kong University（香港大学）；Hong Kong University of Science and Technology（香港科技大学）；The International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；Ohio State University（俄亥俄州立大学）
Can AI Relate: Testing Large Language Model Response for Mental Health Support
New York University（纽约大学）；Grossman School of Medicine（格罗斯曼医学院）；Massachusetts Institute of Technology（麻省理工学院）；University of California, Los Angeles（加州大学洛杉矶分校）
SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques
Texas A&M University - Corpus Christi（德克萨斯A&M大学-科珀斯克里斯蒂分校）；University of Missouri（密苏里大学）；Delft University of Technology（代尔夫特理工大学）；University of Texas Rio Grande Valley（德克萨斯大学里奥格兰德谷分校）
Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols
Beijing University of Posts and Telecommunications（北京邮电大学）；Harbin Institute of Technology（哈尔滨工业大学）；Renyixun Health Technology Co., Ltd.（仁医讯健康科技有限公司）；GDIIST（广东省智能制造研究所）；Tencent（腾讯）
MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
Tsinghua University（清华大学）；University of Washington（华盛顿大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Massachusetts Institute of Technology（麻省理工学院）
Consistent Client Simulation for Motivational Interviewing-based Counseling
Beijing Institute of Technology（北京理工大学）；Singapore Management University（新加坡管理大学）；Australian National University（澳大利亚国立大学）；ThoughtFull；Singapore Institute of Technology（新加坡科技设计大学）；National Institute of Education（新加坡国立教育学院）；Singapore University of Social Sciences（新加坡社科大学）；National University of Singapore（新加坡国立大学）
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
Tianqiao and Chrissy Chen Institute（天桥和克里斯西·陈研究所）；EverMind AI Inc.（EverMind AI公司）；Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine（上海精神卫生中心，上海交通大学医学院）
Large Language Model-Powered Conversational Agent Delivering Problem-Solving Therapy (PST) for Family Caregivers: Enhancing Empathy and Therapeutic Alliance Using In-Context Learning
Florida State University（佛罗里达州立大学）；University of Washington（华盛顿大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
