Ascent:基于模型上下文协议的真实世界临床数据分析智能体系统
Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis
查看机构详情
- Bayer AG(拜耳公司)
机构由 AI 辅助整理,请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
Ascent是一个基于模型上下文协议的智能体系统,用于真实世界临床数据分析,通过EpiTrap数据集验证,相比固定流程在原生和标准化模式上准确率分别提升27和20个百分点。
中文摘要 AI 辅助
从真实世界临床数据回答流行病学问题需要医学编码、模式感知的SQL,以及对人群、分母和时间等隐含选择的验证。我们提出Ascent,一个智能体系统,通过共享的模型上下文协议工具接口,为标准化和原生模式提供医学编码、问答和队列分析功能。我们引入EpiTrap数据集,用于测试系统是否能避免公认的药物流行病学错误,并比较固定流程与不同模型和编排器上的智能体。在能力强的模型上,智能体在原生和标准化模式上分别比固定流程平均提高27和20个百分点的准确率。这些增益需要更多的工具调用和更长的运行时间。实际项目的经验凸显了该系统在可行性评估、诊断迭代和专家引导分析中的价值。
英文摘要
Answering epidemiological questions from real-world clinical data requires medical coding, schema-aware SQL, and validation of implicit choices about populations, denominators, and time. We present Ascent, an agentic system that exposes medical coding, question answering, and cohort analysis through a shared Model Context Protocol tool surface for standardized and native schemas. We introduce EpiTrap, a dataset testing whether systems avoid recognized pharmacoepidemiological errors, and compare a fixed pipeline with agents across models and orchestrators. With capable models, agents improve accuracy over the fixed pipeline by an average of 27 and 20 percentage points on native and standardized schemas, respectively. These gains require more tool calls and longer runtimes. Experience from real projects highlights the system's value for feasibility assessment, diagnostic iteration, and expert-guided analysis.