Abstract
This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 shared task B. We present a novel approach to diagnosing clinical dermatology cases by integrating large multimodal models, specifically leveraging the capabilities of GPT-4V under a retriever and a re-ranker framework. Our investigation reveals that GPT-4V, when used as a retrieval agent, can accurately retrieve the correct skin condition 85% of the time using dermatological images and brief patient histories. Additionally, we empirically show that Naive Chain-of-Thought (CoT) works well for retrieval while Medical Guidelines Grounded CoT is required for accurate dermatological diagnosis. Further, we introduce a Multi-Agent Conversation (MAC) framework and show its superior performance and potential over the best CoT strategy. The experiments suggest that using naive CoT for retrieval and multi-agent conversation for critique-based diagnosis, GPT-4V can lead to an early and accurate diagnosis of dermatological conditions. The implications of this work extend to improving diagnostic workflows, supporting dermatological education, and enhancing patient care by providing a scalable, accessible, and accurate diagnostic tool.
Abstract (translated)
本文介绍了我们团队在MEDIQA-ClinicalNLP2024共享任务B中的参与。我们提出了一种通过整合大型多模态模型来诊断临床皮肤病的新方法,特别是通过利用GPT-4V在检索器和排序器框架下的能力。我们的研究结果表明,当GPT-4V用作检索器时,85%的皮肤病病例可以准确地检索到正确的皮肤状况。此外,我们通过实验实证研究了Naive Chain-of-Thought(CoT)在检索方面的效果,同时指出需要医疗指南 grounded CoT 来进行准确的皮肤病诊断。进一步,我们引入了 Multi-Agent Conversation(MAC)框架,并证明了其在批判性诊断方面的卓越表现和潜力超过最佳CoT策略。实验结果表明,使用naive CoT进行检索和multi-agent conversation用于批评性诊断,GPT-4V可以实现对皮肤病情况的早期准确诊断。本工作的影响范围还在于改善诊断工作流程,支持皮肤病教育,以及通过提供可扩展、易用且准确的诊断工具来提高患者护理。
URL
https://arxiv.org/abs/2404.17749