将链式思维与检索增强生成相结合增强了从临床笔记中诊断罕见疾病的性能
Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes
AI总结：
本研究提出RAG驱动的CoT和CoT驱动的RAG方法，通过结合链式思维与检索增强生成，提升从临床笔记中诊断罕见疾病的性能。
摘要：
背景：几项研究显示，大型语言模型（LLMs）在基于表型驱动的基因优先级排序方面对罕见疾病存在困难。这些研究通常使用人类表型本体（HPO）术语来提示基础模型如GPT和LLaMA来预测候选基因。然而，在现实世界中，基础模型并未针对领域特定任务如临床诊断进行优化，而输入是无结构的临床笔记而非标准化术语。如何指导LLMs从无结构的临床笔记中预测候选基因或疾病诊断仍是一个重大挑战。方法：我们引入了RAG驱动的CoT和CoT驱动的RAG，这两种方法结合了链式思维（CoT）和检索增强生成（RAG）来分析临床笔记。一个五问的CoT协议模拟专家推理，而RAG从HPO和OMIM（在线孟德尔遗传学人）等来源检索数据。我们对罕见疾病数据集进行了评估，包括5,980个Phenopacket衍生的笔记、255个基于文献的叙述和220个来自费城儿童医院的内部临床笔记。结果：我们发现，最近的基础模型，包括Llama 3.3-70B-Instruct和DeepSeek-R1-Distill-Llama-70B，在候选基因优先级排序方面优于早期版本，如Llama 2和GPT-3.5。我们还显示，RAG驱动的CoT和CoT驱动的RAG在从临床笔记中优先排序候选基因方面均优于基础模型；特别是，使用DeepSeek作为基础模型的两种方法在Phenopacket衍生的临床笔记中实现了超过40%的前10个基因准确率。RAG驱动的CoT在高质量笔记中表现更好，其中早期检索可以将后续推理步骤锚定在领域特定的证据上，而CoT驱动的RAG在处理长篇和嘈杂的笔记时具有优势。
英文摘要：
Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models like GPT and LLaMA to predict candidate genes. However, in real-world settings, foundation models are not optimized for domain-specific tasks like clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major challenge. Methods: We introduce RAG-driven CoT and CoT-driven RAG, two methods that combine Chain-of-Thought (CoT) and Retrieval Augmented Generation (RAG) to analyze clinical notes. A five-question CoT protocol mimics expert reasoning, while RAG retrieves data from sources like HPO and OMIM (Online Mendelian Inheritance in Man). We evaluated these approaches on rare disease datasets, including 5,980 Phenopacket-derived notes, 255 literature-based narratives, and 220 in-house clinical notes from Childrens Hospital of Philadelphia. Results: We found that recent foundations models, including Llama 3.3-70B-Instruct and DeepSeek-R1-Distill-Llama-70B, outperformed earlier versions such as Llama 2 and GPT-3.5. We also showed that RAG-driven CoT and CoT-driven RAG both outperform foundation models in candidate gene prioritization from clinical notes; in particular, both methods with DeepSeek backbone resulted in a top-10 gene accuracy of over 40% on Phenopacket-derived clinical notes. RAG-driven CoT works better for high-quality notes, where early retrieval can anchor the subsequent reasoning steps in domain-specific evidence, while CoT-driven RAG has advantage when processing lengthy and noisy notes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
