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

2026-05-25

AI Summary

This study addresses the inefficiencies in radiation oncology clinical workflows caused by cumbersome patient information aggregation and suboptimal clinical trial matching. It introduces RadOnc-GPT, a large language model integrated into routine clinical practice to automatically synthesize electronic health record data and generate daily personalized emails containing patients’ schedules, clinical status summaries, and matched trial recommendations. By seamlessly combining LLM-driven information distillation with trial matching, the system significantly enhances workflow efficiency: 83.6% of radiation oncology users engaged with it frequently, 27% saved at least 10 minutes daily, and overall user satisfaction averaged 3.89 out of 5, with high internal consistency (Cronbach’s α = 0.97).

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. Design: Mixed-methods evaluation using a cross-sectional, anonymous clinician survey administered after 1 month of system deployment. 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. 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 $α$. 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 $α$ = 0.97).

Problem

• clinical summarization
• trial identification
• radiation oncology
• workflow integration
• information overload

Innovation

• Large Language Model
• Clinical Summarization
• Clinical Trial Matching
• Workflow Integration
• Radiation Oncology