The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology

每日剂量：放射肿瘤学中用于临床总结与临床试验识别的工作流集成大语言模型自动化系统

Abstract: Objective: To describe the design and early clinical evaluation of The Daily Dose (TDD), an LLM-driven, automated clinical summarization and clinical-trial identification system integrated into routine radiation oncology practice. 摘要： 目的： 旨在描述“每日剂量”（The Daily Dose, TDD）的设计与早期临床评估。该系统是一个由大语言模型（LLM）驱动的自动化临床总结与临床试验识别系统，已集成至放射肿瘤学的日常实践中。

Design: Mixed-methods evaluation using a cross-sectional, anonymous clinician survey administered after 1 month of system deployment. 设计： 采用混合方法评估，在系统部署一个月后，对临床医生进行了一项横断面匿名问卷调查。

Exposure: Daily automated delivery of physician-specific email summaries generated using RadOnc-GPT, including patient schedules, concise EHR-derived clinical-status summaries, and automated identification of potentially relevant clinical trials for new or consult visits. 干预措施： 每日自动发送由 RadOnc-GPT 生成的医生专属电子邮件摘要，内容包括患者日程安排、从电子健康记录（EHR）中提取的简明临床状态总结，以及针对新患者或会诊患者自动识别的潜在相关临床试验。

Main Outcomes and Measures: Primary outcomes included self-reported usability, satisfaction, perceived usefulness, perceived impact on workflow, time savings, and intention for continued use. Internal consistency reliability was assessed using Cronbach’s $\alpha$. 主要结果与指标： 主要结果包括自我报告的可用性、满意度、感知有用性、对工作流的感知影响、节省的时间以及持续使用的意愿。内部一致性信度通过 Cronbach’s $\alpha$ 系数进行评估。

Results: Among 55 respondents, 52 (94.5%) worked in radiation oncology, and 38 (69.1%) were attending physicians. Most participants (83.6%) reported using TDD daily or several times per week. Mean (SD) scores were 3.89 (1.04) for usability and satisfaction, 3.43 (1.24) for perceived usefulness, and 3.80 (1.17) for impact and future use (5-point Likert scale). Overall satisfaction was positively associated with perceived time savings ($p < .001$). Participants reported variable time savings, with 27% estimating $\geq 10$ minutes saved per day. The questionnaire demonstrated excellent internal consistency (overall Cronbach’s $\alpha$ = 0.97). 结果： 在 55 名受访者中，52 名（94.5%）从事放射肿瘤学工作，38 名（69.1%）为主治医师。大多数参与者（83.6%）报告称每天或每周多次使用 TDD。在 5 分制李克特量表中，可用性与满意度的平均分（标准差）为 3.89 (1.04)，感知有用性为 3.43 (1.24)，影响与未来使用意愿为 3.80 (1.17)。总体满意度与感知到的时间节省呈正相关（$p < .001$）。参与者报告的时间节省情况各异，其中 27% 的人估计每天可节省 $\geq 10$ 分钟。问卷表现出极佳的内部一致性（总体 Cronbach’s $\alpha$ = 0.97）。