面向急诊医生的双阶段轻量级患者病历摘要生成
Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians
AI总结：
本文提出一种在嵌入式设备上运行的双阶段离线患者病历摘要系统，通过检索和生成架构，在30秒内为急诊医生提供关键发现和上下文相关叙述，保护隐私并提升效率。
摘要：
电子健康记录（EHRs）包含大量非结构化的临床数据，这些数据可能使试图识别关键信息的急诊医生不堪重负。我们提出了一种完全在嵌入式设备上运行的两阶段摘要生成系统，能够在保护患者隐私的同时实现离线临床摘要生成。在我们的方法中，一种双设备架构首先使用Jetson Nano-R（检索）检索相关的患者记录部分，然后在另一台Jetson Nano-S（摘要生成）上生成结构化摘要，并通过轻量级套接字链接进行通信。摘要输出包含两部分：（1）关键发现的固定格式列表，（2）针对临床医生查询的上下文特定叙述。检索阶段使用本地存储的EHRs，将长笔记分割成语义连贯的部分，并针对每个查询搜索最相关的部分。生成阶段使用本地托管的小型语言模型（SLM）从检索到的文本生成摘要，在两台NVIDIA Jetson设备的约束下运行。我们首先对七个参数低于7B的开源SLMs进行了基准测试，以确定可行的模型。我们引入了LLM-as-Judge评估机制，从事实准确性、完整性和清晰度方面评估摘要质量。在MIMIC-IV和去标识化的真实EHRs上的初步结果表明，我们完全离线的系统能够在30秒内有效生成有用的摘要。
英文摘要：
Electronic health records (EHRs) contain extensive unstructured clinical data that can overwhelm emergency physicians trying to identify critical information. We present a two-stage summarization system that runs entirely on embedded devices, enabling offline clinical summarization while preserving patient privacy. In our approach, a dual-device architecture first retrieves relevant patient record sections using the Jetson Nano-R (Retrieve), then generates a structured summary on another Jetson Nano-S (Summarize), communicating via a lightweight socket link. The summarization output is two-fold: (1) a fixed-format list of critical findings, and (2) a context-specific narrative focused on the clinician's query. The retrieval stage uses locally stored EHRs, splits long notes into semantically coherent sections, and searches for the most relevant sections per query. The generation stage uses a locally hosted small language model (SLM) to produce the summary from the retrieved text, operating within the constraints of two NVIDIA Jetson devices. We first benchmarked six open-source SLMs under 7B parameters to identify viable models. We incorporated an LLM-as-Judge evaluation mechanism to assess summary quality in terms of factual accuracy, completeness, and clarity. Preliminary results on MIMIC-IV and de-identified real EHRs demonstrate that our fully offline system can effectively produce useful summaries in under 30 seconds.
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。
