RTHistory: An automated tool for the extraction and presentation of radiotherapy course history for continuity of care applications
Journal of Applied Clinical Medical Physics · 2026-11 · 27 (11)
DOI: 10.1002/acm2.70910 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 14.11.2026. Verfasst von Justin B Hink und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California, USA. Hauptthemen laut MEDLINE: Radiotherapy Planning, Computer-Assisted, Software, Continuity of Patient Care, Neoplasms. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Transfer of radiation treatment records is a common task for radiotherapy clinics, as treatment history impacts future treatment planning, including prescription dose, fractionation, and normal tissue constraint selections. Currently, gathering radiation records relies on manual searches within treatment planning databases and Record and Verify (R&V) systems, a process that is time‐consuming and subject to human error. Particularly challenging is discerning which plans were treated, and for how many fractions, in cases of treatment adaptation or early termination.
Purpose
In this technical note, we present RTHistory , an open‐source software tool that automates the extraction process for R&V systems that implement DICOM Query/Retrieve and summarizes the treatment history in a format optimized for efficient clinical readability and visual triage.
Methods
RTHistory was configured to query multiple clinical systems through the DICOM protocol. The query process begins with downloading and analyzing the RTRecords, which document beam delivery. From these, internal DICOM object references are followed to gather the relevant planning files, including dose, simulation scan, and structure set. RTHistory then parses these DICOM files to create a treatment summary PDF report that describes the plan labels, prescription doses, treatment start and end dates, number of fractions treated, and a graphical representation of the dose washes of the treated plans. Rigorous software unit testing and error handling procedures were implemented to ensure reliability and accuracy of the extracted data.
Results
RTHistory was evaluated on a clinical cohort of 61 patients comprising 177 distinct treatment plans across six anatomical sites from our institutional database, which included the ARIA/Eclipse R&V system and treatment planning system. Manual verification against clinical ARIA and Eclipse records confirmed 100% agreement in reconstructing delivered DICOM‐RT objects (177/177 plans), with none of 439 undelivered plans included (specificity: 100%; 95% CI: 99.2%–100%). Performance testing for patients with at least one treatment planned in Eclipse ( n = 51 patients) yielded a median overall patient run time of 115.4 s (aggregate per‐plan: 59.5 s, 95% bootstrap confidence interval: 45.6–72.1 s), which scaled directly with the number of CT series (93.4 20.0 s per series). In a direct comparison across 42 patients, manual abstraction required a mean active hands‐on time of 342.0 378.0 s (median: 192.0 s, range: 90.0–2214.0 s), whereas the software ran unattended with a mean execution time of 228.0 282.0 s (median: 114.0 s, range: 48.0–1318.6 s).
Conclusion
RTHistory offers a solution to improve continuity of care by facilitating accurate information sharing through the automated extraction and presentation of treatment history. Looking ahead, integration into institutional workflows holds promise for enhancing patient care and decision‐making in oncological treatment, while reducing the manual burden on clinical staff and mitigating transcription risks in re‐irradiation workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California, USA.
ORCID-Profile: Justin B Hink, Andrew Krupien, Jack Neylon
Zitieren
APA
Hink, J. B., Abdulkadir, Y., Krupien, A., Boyle, P., Low, D. A., Neylon, J., & Lamb, J. (2026). RTHistory: An automated tool for the extraction and presentation of radiotherapy course history for continuity of care applications. Journal of Applied Clinical Medical Physics, 27(11). https://doi.org/10.1002/acm2.70910
Vancouver
Hink JB, Abdulkadir Y, Krupien A, Boyle P, Low DA, Neylon J, et al. RTHistory: An automated tool for the extraction and presentation of radiotherapy course history for continuity of care applications. Journal of Applied Clinical Medical Physics. 2026;27(11). doi:10.1002/acm2.70910
BibTeX
@article{Hink2026,
author = {Hink, Justin B and Abdulkadir, Yasin and Krupien, Andrew and Boyle, Peter and Low, Daniel A and Neylon, Jack and Lamb, James},
title = {RTHistory: An automated tool for the extraction and presentation of radiotherapy course history for continuity of care applications},
journal = {Journal of Applied Clinical Medical Physics},
year = {2026},
volume = {27},
number = {11},
doi = {10.1002/acm2.70910}
}
EUVIMED