Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias
Singapore General Hospital（新加坡中央医院）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Singapore Eye Research Institute（新加坡眼科研究所）；Singapore National Eye Center（新加坡国家眼科中心）；Byers Eye Institute, Stanford University（斯坦福大学拜尔斯眼科研究所）；National University of Singapore（新加坡国立大学）
Yu He Ke, Rui Yang, Sui An Lie, Taylor Xin Yi Lim, Hairil Rizal Abdullah, Daniel Shu Wei Ting, Nan Liu
Background: Cognitive biases in clinical decision-making significantly contribute to errors in diagnosis and suboptimal patient outcomes. Addressing these biases presents a formidable challenge in the medical field.
Objective: This study explores the role of large language models (LLMs) in mitigating these biases through the utilization of a multi-agent framework. We simulate the clinical decision-making processes through multi-agent conversation and evaluate its efficacy in improving diagnostic accuracy.
Methods: A total of 16 published and unpublished case reports where cognitive biases have resulted in misdiagnoses were identified from the literature. In the multi-agent framework, we leveraged GPT-4 to facilitate interactions among four simulated agents to replicate clinical team dynamics. Each agent has a distinct role: 1) To make the final diagnosis after considering the discussions, 2) The devil's advocate and correct confirmation and anchoring bias, 3) The tutor and facilitator of the discussion to reduce premature closure bias, and 4) To record and summarize the findings. A total of 80 simulations were evaluated for the accuracy of initial diagnosis, top differential diagnosis and final two differential diagnoses.
Results: In a total of 80 responses evaluating both initial and final diagnoses, the initial diagnosis had an accuracy of 0% (0/80), but following multi-agent discussions, the accuracy for the top differential diagnosis increased to 71.3% (57/80), and for the final two differential diagnoses, to 80.0% (64/80).
Conclusions: The framework demonstrated an ability to re-evaluate and correct misconceptions, even in scenarios with misleading initial investigations. The LLM-driven multi-agent conversation framework shows promise in enhancing diagnostic accuracy in diagnostically challenging medical scenarios.
MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents
Theta Health Inc.（西塔健康公司）；Chen Frontier Lab for AI and Mental Health, Tianqiao and Chrissy Chen Institute（天桥脑科学研究院陈天桥雒芊芊脑科学研究院AI与精神健康前沿实验室）；Shanghai Mental Health Center（上海市精神卫生中心）；Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）；Shanghai Clinical Research Center for Mental Health（上海市精神疾病临床医学中心）；Shanghai Key Laboratory of Psychotic Disorders（上海市精神疾病重点实验室）
Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation
Sun Yat-sen University（中山大学）；Alibaba group（阿里巴巴集团）；Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology（广东省火灾科学与智能应急技术重点实验室）；Pazhou Lab（琶洲实验室）
Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；City University of Macau, Macao SAR, China（澳门城市大学）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室）
ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations
Microsoft Research（微软研究院）；Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属上海市精神卫生中心老年精神科）
Language-Based Digital Twins for Elderly Cognitive Assistance
Ritchie School of Engineering and Computer Science, University of Denver（丹佛大学里奇工程与计算机科学学院）；Department of Neurology, Massachusetts General Hospital, Harvard Medical School（哈佛医学院麻省总医院神经内科）
CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Shanghai Institute of Artificial Intelligence for Education, East China Normal University（华东师范大学教育人工智能研究所）；School of Data Science, Fudan University（复旦大学数据科学学院）；Huawei Noah’s Ark Lab（华为诺亚实验室）
LETGAMES: An LLM-Powered Gamified Approach to Cognitive Training for Patients with Cognitive Impairment
Shanghai University of Finance and Economics（上海财经大学）；Northwest Polytechnical University（西北工业大学）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；College of Computer Science, Sichuan University（四川大学计算机学院）
The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation
School of Information Science and Engineering, Lanzhou University（信息科学与工程学院，兰州大学）；School of Medical Technology, Beijing Institute of Technology（医学技术学院，北京理工大学）
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback
School of Computer Science, Peking University（北京大学计算机学院）；Key Laboratory of High Confidence Software Technologies(PKU), MOE, China（教育部高可信软件技术重点实验室）；Beijing Jiaotong University（北京交通大学）
Towards Explainable Conversational AI for Early Diagnosis with Large Language Models
Department of Information and Communication Technology（信息与通信技术系）；Bangladesh University of Professionals（孟加拉专业大学）；Institute of Information Technology（信息技术研究所）；Jahangirnagar University（贾汗吉尔纳瓦德大学）
Cross-Linguistic Persona-Driven Data Synthesis for Robust Multimodal Cognitive Decline Detection
Engineering Research Center of Intelligent Theranostics Technology and Instruments, Ministry of Education, School of Biomedical Engineering and Informatics, Nanjing Medical University（智能诊疗技术与仪器工程研究中心、教育部、生物医学工程与信息学院、南京医科大学）；Institute of Biomedical Engineering, University of Oxford（生物医学工程研究所、牛津大学）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)（高性能计算研究所、科技研究局（A*STAR））；Department of Neurology, National Neuroscience Institute, Singapore, 308433, Singapore（神经病学部、新加坡国家神经科学研究所）；Duke-NUS Medical School, Singapore, 169857, Singapore（新加坡国立大学医学院）
Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour
York University（约克大学）；Vector Institute（向量研究所）；Rotman Research Institute（罗特曼研究学院）；Dalhousie University（达尔豪斯大学）；Centre for Addiction & Mental Health（成瘾与心理健康中心）；KITE Research Institute（KITE研究机构）
RadVLM: A Multitask Conversational Vision-Language Model for Radiology
Department of Radiology, Kobe University（金泽大学放射科）；Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系）；Department of Advanced Imaging in Medical Magnetic Resonance, Kyoto University（京都大学医学磁共振高级成像部门）；Department of Quantitative Biomedicine, University of Zurich（苏黎世大学定量生物医学系）；Diagnostic and Interventional Radiology, University Hospital Zurich（苏黎世大学医院诊断与介入放射科）
National Computer System Engineering Research Institute of China（中国国家计算机系统工程研究所）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Emotion Recognition in Conversations (ERC) has gained increasing attention for developing empathetic machines. Recently, many approaches have been devoted to perceiving conversational context by deep learning models. However, these approaches are insufficient in understanding the context due to lacking the ability to extract and integrate emotional clues. In this work, we propose novel Contextual Reasoning Networks (DialogueCRN) to fully understand the conversational context from a cognitive perspective. Inspired by the Cognitive Theory of Emotion, we design multi-turn reasoning modules to ext…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Humans quite frequently interact with conversational agents. The rapid advancement in generative language modeling through neural networks has helped advance the creation of intelligent conversational agents. Researchers typically evaluate the output of their models through crowdsourced judgments, but there are no established best practices for conducting such studies. Moreover, it is unclear if cognitive biases in decision-making are affecting crowdsourced workers' judgments when they undertake these tasks. To investigate, we conducted a between-subjects study with 77 crowdsourced workers to …
