arXiv subjects

Satomi Shiraishi

Publications and source records attributed to Satomi Shiraishi.

4 recordsLinked to original sources

arXiv2026

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

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).

cs.CL↗

arXiv2025

RadOnc-GPT: An Autonomous LLM Agent for Real-Time Patient Outcomes Labeling at Scale

Manual labeling limits the scale, accuracy, and timeliness of patient outcomes research in radiation oncology. We present RadOnc-GPT, an autonomous large language model (LLM)-based agent capable of independently retrieving patient-specific information, iteratively assessing evidence, and returning structured outcomes. Our evaluation explicitly validates RadOnc-GPT across two clearly defined tiers of increasing complexity: (1) a structured quality assurance (QA) tier, assessing the accurate retrieval of demographic and radiotherapy treatment plan details, followed by (2) a complex clinical outcomes labeling tier involving determination of mandibular osteoradionecrosis (ORN) in head-and-neck cancer patients and detection of cancer recurrence in independent prostate and head-and-neck cancer cohorts requiring combined interpretation of structured and unstructured patient data. The QA tier establishes foundational trust in structured-data retrieval, a critical prerequisite for successful complex clinical outcome labeling.

cs.AI↗

arXiv2024

Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses from Closed-Domain LLM vs. Clinical Teams

In-basket message interactions play a crucial role in physician-patient communication, occurring during all phases (pre-, during, and post) of a patient's care journey. However, responding to these patients' inquiries has become a significant burden on healthcare workflows, consuming considerable time for clinical care teams. To address this, we introduce RadOnc-GPT, a specialized Large Language Model (LLM) powered by GPT-4 that has been designed with a focus on radiotherapeutic treatment of prostate cancer with advanced prompt engineering, and specifically designed to assist in generating responses. We integrated RadOnc-GPT with patient electronic health records (EHR) from both the hospital-wide EHR database and an internal, radiation-oncology-specific database. RadOnc-GPT was evaluated on 158 previously recorded in-basket message interactions. Quantitative natural language processing (NLP) analysis and two grading studies with clinicians and nurses were used to assess RadOnc-GPT's responses. Our findings indicate that RadOnc-GPT slightly outperformed the clinical care team in "Clarity" and "Empathy," while achieving comparable scores in "Completeness" and "Correctness." RadOnc-GPT is estimated to save 5.2 minutes per message for nurses and 2.4 minutes for clinicians, from reading the inquiry to sending the response. Employing RadOnc-GPT for in-basket message draft generation has the potential to alleviate the workload of clinical care teams and reduce healthcare costs by producing high-quality, timely responses.

cs.AI↗

arXiv2018

Measurement of Dispersion of a Clinical Proton Therapy Beam

Purpose: To measure dispersion of a clinical proton therapy beam. Methods and Materials: The proton center at our institution uses a Hitachi PROBEAT V synchrotron that delivers beams with energies ranging from 70 to 230 MeV to five treatment rooms, four of which have gantries and one fixed beam. For this study, the magnetic field strengths of all optics in the transport line were varied to measure the dispersion of 230 MeV beams in each of the four gantry rooms. Beam position was measured using the Spot Position Monitor (SPM), a multi-wire proportional counter (MWPC) in the nozzle approximately 0.5 meters upstream of the treatment isocenter. Measured beam positions as a function of momentum offset were fitted to a linear function to extract dispersion. In one gantry, dispersions for 70 and 140 MeV beams were also measured. Because spot position is continuously monitored during treatments and a position deviation will abort the beam delivery, the dispersion at the spot position monitor was used to set an upper limit of range uncertainty originating from momentum deviation. When dispersion was approximately zero, dose rate measurements were used to set an upper limit of momentum deviation that could reach the patient. Results: Dispersion was 0.45 m, 0.48 m and 0.30 m for 70 MeV, 140 MeV, and 230 MeV beams in a gantry, respectively, corresponding to 0.3 mm, 1.0 mm and 3.5 mm maximum range uncertainty during treatments. For 230 MeV beams, dispersion ranged from 0 to 0.73 m across the four gantries, corresponding to the upper limits of range uncertainty due to momentum deviation of 1.4 to 6.2 mm (0.4 to 1.9% in fractional range uncertainty). Conclusions: The measured dispersion was both energy- and gantry-dependent and ranged from 0 to 0.73 m.

physics.med-ph↗