The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology
Summary
This paper presents The Daily Dose (TDD), an LLM-driven system for automated clinical summarization and clinical-trial identification integrated into routine radiation oncology practice, with early evaluation showing positive usability and time savings.
View Cached Full Text
Cached at: 05/27/26, 09:02 AM
# The Daily Dose: Workflow-Integrated Large Language Model Automation for Clinical Summarization and Trial Identification in Radiation Oncology Source: [https://arxiv.org/abs/2605.26346](https://arxiv.org/abs/2605.26346) Authors:[Jason Holmes](https://arxiv.org/search/cs?searchtype=author&query=Holmes,+J),[Federico Mastroleo](https://arxiv.org/search/cs?searchtype=author&query=Mastroleo,+F),[Mariana Borras\-Osorio](https://arxiv.org/search/cs?searchtype=author&query=Borras-Osorio,+M),[Srinivas Seetamsetty](https://arxiv.org/search/cs?searchtype=author&query=Seetamsetty,+S),[Satomi Shiraishi](https://arxiv.org/search/cs?searchtype=author&query=Shiraishi,+S),[Mirek Fatyga](https://arxiv.org/search/cs?searchtype=author&query=Fatyga,+M),[Judy C\. Boughey](https://arxiv.org/search/cs?searchtype=author&query=Boughey,+J+C),[Cornelius A\. Thiels](https://arxiv.org/search/cs?searchtype=author&query=Thiels,+C+A),[William G\.Breen](https://arxiv.org/search/cs?searchtype=author&query=G.Breen,+W),[Daniel J\. Ma](https://arxiv.org/search/cs?searchtype=author&query=Ma,+D+J),[Daniel K\. Ebner](https://arxiv.org/search/cs?searchtype=author&query=Ebner,+D+K),[David M\. Routman](https://arxiv.org/search/cs?searchtype=author&query=Routman,+D+M),[Brady S\. Laughlin](https://arxiv.org/search/cs?searchtype=author&query=Laughlin,+B+S),[Carlos E\. Vargas](https://arxiv.org/search/cs?searchtype=author&query=Vargas,+C+E),[Samir H\. Patel](https://arxiv.org/search/cs?searchtype=author&query=Patel,+S+H),[Sujay A\. Vora](https://arxiv.org/search/cs?searchtype=author&query=Vora,+S+A),[Nadia N\. Laack](https://arxiv.org/search/cs?searchtype=author&query=Laack,+N+N),[Andrew Y\.K\. Foong](https://arxiv.org/search/cs?searchtype=author&query=Foong,+A+Y),[Wei Liu](https://arxiv.org/search/cs?searchtype=author&query=Liu,+W),[Mark R\. Waddle](https://arxiv.org/search/cs?searchtype=author&query=Waddle,+M+R) [View PDF](https://arxiv.org/pdf/2605.26346) > 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 $\\alpha$\. 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 \(overall Cronbach's $\\alpha$ = 0\.97\)\. ## Submission history From: Jason Holmes PhD \[[view email](https://arxiv.org/show-email/961fdff1/2605.26346)\] **\[v1\]**Mon, 25 May 2026 21:43:19 UTC \(586 KB\)
Similar Articles
Human-in-the-Loop Large Language Model Framework for Identification of Cutaneous Immune-Related Adverse Events
This paper presents a retrieval-augmented, multi-agent LLM framework with human-in-the-loop for detecting cutaneous immune-related adverse events from clinical notes, achieving higher accuracy, improved inter-rater agreement, and halved review time compared to manual review.
MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation
This paper introduces MTDiag, a multi-turn diagnostic dialogue dataset for evaluating Large Language Models in realistic clinical diagnostic scenarios, addressing limitations of static QA benchmarks.
A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
This paper presents RaDaR, a 32B open-source reasoning LLM trained on public and synthetic rare disease cases, which outperforms larger models like DeepSeek-R1 in diagnosis benchmarks and improves physician accuracy by 21.44 percentage points in a randomized trial.
Large Language Models as Unified Multimodal Learners for Clinical Prediction
The paper proposes converting multimodal patient data (text, labs, vitals) into a single natural language sequence and fine-tuning LLMs for clinical prediction, achieving comparable or better performance than specialized fusion architectures across three tasks.
Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies
This paper surveys clinical communication processing using LLM-generated synthetic data and presents 13 case studies across EMS reports, nurse handoffs, and more, showing that synthetic data can bootstrap clinical NLP systems.