Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias

📄 arXiv: 2401.14589v2 📥 PDF

作者: Yu He Ke, Rui Yang, Sui An Lie, Taylor Xin Yi Lim, Hairil Rizal Abdullah, Daniel Shu Wei Ting, Nan Liu

分类: cs.CL, cs.AI

发布日期: 2024-01-26 (更新: 2024-05-12)

备注: 21 pages, 3 figures

💡 一句话要点

利用多智能体对话提升诊断准确性以应对认知偏差问题

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 认知偏差 临床决策 大型语言模型 多智能体框架 诊断准确性 医学教育 决策支持系统

📋 核心要点

  1. 核心问题：临床决策中的认知偏差导致误诊，影响患者结果，现有方法难以有效应对这些偏差。
  2. 方法要点：本研究提出利用大型语言模型通过多智能体对话框架来模拟临床团队讨论，以减轻认知偏差。
  3. 实验或效果：实验结果显示，经过多智能体讨论后，顶级和最终鉴别诊断的准确率分别提高至71.3%和80.0%。

📝 摘要（中文）

背景：临床决策中的认知偏差显著导致诊断错误和患者结果不佳。解决这些偏差在医学领域面临巨大挑战。目标：本研究探讨大型语言模型（LLMs）在通过多智能体框架减轻这些偏差中的作用。我们模拟临床决策过程，通过多智能体对话评估其在提高诊断准确性方面的有效性。方法：从文献中识别出16个因认知偏差导致误诊的案例报告。在多智能体框架中，我们利用GPT-4促进四个模拟代理之间的互动，以复制临床团队动态。结果：在80个评估初始和最终诊断的响应中，初始诊断准确率为0%，但经过多智能体讨论后，顶级鉴别诊断的准确率提高至71.3%，最终两个鉴别诊断的准确率提高至80.0%。结论：该框架展示了重新评估和纠正误解的能力，LLM驱动的多智能体对话框架在诊断挑战性医疗场景中提升诊断准确性方面显示出前景。

🔬 方法详解

问题定义：本研究旨在解决临床决策中因认知偏差导致的误诊问题。现有方法在识别和纠正这些偏差方面存在不足，导致患者结果不佳。

核心思路：本研究的核心思路是利用大型语言模型（LLMs）通过多智能体对话框架，模拟临床团队的讨论过程，以减轻认知偏差的影响。通过角色分配，促进更全面的讨论和决策。

技术框架：整体架构包括四个模拟代理，每个代理承担不同角色：1) 最终诊断者，2) 反对者，纠正确认和锚定偏差，3) 辅导者，减少过早关闭偏差，4) 记录者，汇总讨论结果。通过80次模拟评估初始和最终诊断的准确性。

关键创新：该研究的关键创新在于将大型语言模型应用于多智能体对话框架，能够有效模拟临床团队的动态，促进更准确的诊断决策。这与传统的单一决策者方法本质上不同。

关键设计：在设计中，采用了GPT-4作为对话生成模型，确保了多智能体之间的有效互动。每个代理的角色和功能经过精心设计，以最大限度地减少认知偏差的影响。

📊 实验亮点

实验结果显示，在80个案例中，初始诊断准确率为0%，经过多智能体讨论后，顶级鉴别诊断准确率提升至71.3%，最终两个鉴别诊断准确率提升至80.0%。这一显著提升表明该框架在纠正误解和提高诊断准确性方面的有效性。

🎯 应用场景

该研究的潜在应用领域包括医疗诊断、临床决策支持系统和医学教育。通过引入多智能体对话框架，可以在复杂的临床场景中提高诊断准确性，从而改善患者的治疗效果。未来，该方法有望在其他领域的决策支持中得到推广。

📄 摘要（原文）

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 Methods: A total of 16 published and unpublished case reports where cognitive biases have resulted in misdiagnoses were identified from the literature.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.