ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations

ClinicBot：一款基于临床指南、具备优先证据检索增强生成（RAG）及可验证引用的临床聊天机器人

Abstract: Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes medical contexts where precision is essential.

摘要： 临床诊断要求答案必须准确、可验证，并明确基于官方指南。尽管大型语言模型在自然语言处理方面表现出色，但它们产生“幻觉”的倾向削弱了其在对精确度要求极高的医疗环境中的实用性。

Existing retrieval-augmented generation (RAG) systems treat all evidence equally, producing noisy context and generic answers misaligned with clinical practice. We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1) structured extraction of clinical guidelines into semantic units (recommendations, tables, definitions, narrative) with explicit provenance, (2) evidence prioritization that ranks content by clinical significance and guideline structure rather than textual similarity, and (3) a web-based interface that presents concise, actionable answers with verifiable evidence.

现有的检索增强生成（RAG）系统往往同等对待所有证据，导致生成的上下文包含噪声，且给出的通用答案与临床实践不符。我们推出了 ClinicBot，这是一个通过以下三项关键进展将指南建议转化为可信临床支持的 AI 系统：（1）将临床指南结构化提取为语义单元（建议、表格、定义、叙述），并明确来源；（2）采用证据优先级排序，根据临床意义和指南结构而非文本相似度对内容进行排序；（3）提供基于 Web 的界面，呈现简洁、可操作且附带可验证证据的答案。

We will demonstrate ClinicBot using diabetes questions from real patients and an additional diabetes risk assessment tool that is faithful to the American Diabetes Association (ADA) Standards of Care in Diabetes (2025). The demonstration will illustrate how semantic knowledge extraction and hierarchical evidence ranking can reliably operate in a multi-agent setting to process complex clinical guidelines at scale.

我们将通过真实患者的糖尿病相关问题，以及一个严格遵循《美国糖尿病协会（ADA）糖尿病诊疗标准（2025）》的糖尿病风险评估工具来演示 ClinicBot。该演示将展示语义知识提取和分层证据排序如何在多智能体环境中可靠运行，从而大规模处理复杂的临床指南。