EUVIMEDEUVIMED entdecken
Crossref

Automated Identification of Radiotherapy Courses From US Department of Veterans Affairs Administrative Data

William Schreyer iD, Ryan Melson iD, Christopher Anderson, Cecelia Madison iD, Evangelia Katsoulakis iD, Reid F Thompson iD

JCO Clinical Cancer Informatics · 2025

DOI: 10.1200/cci-25-00088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von William Schreyer und 5 weiteren Autor:innen. Beteiligte Einrichtung: Portland VA Research Foundation, Portland, OR. Hauptthemen laut MEDLINE: United States Department of Veterans Affairs, Neoplasms, Electronic Health Records, Radiotherapy. Die Arbeit nennt 35 Literaturangaben. Gefördert von: CSRD VA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Radiotherapy is a critically important cancer treatment; however, its details are often not well represented in electronic health record data sets. US Veterans' radiation courses are further distributed across a range of medical centers, both internal and external to the Veterans Health Administration (VHA), inhibiting analysis of radiotherapy treatment across this population. METHODS We train and test a suite of supervised machine learning models for the accurate prediction of radiation course dates using billing and diagnostic codes from a combination of VHA and Centers for Medicare and Medicaid Services (CMS) databases. We use a separate heuristic algorithm to assemble course date predictions into complete radiation treatments. RESULTS Our top model predicts radiation course dates with compelling accuracy (macro-average of 0.914 across classes). The retrospective application of our model and assembly algorithm to radiation procedure dates for 1,331,342 patients identified 1,526,660 predicted courses of radiotherapy. CONCLUSION The identified courses were collected into a shared resource to facilitate future VHA-based studies, and our predictive model is available for application to a wider range of non-VHA data sets, particularly those leveraging CMS data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

United States Department of Veterans AffairsNeoplasmsElectronic Health RecordsRadiotherapyHumansUnited StatesMachine LearningAlgorithmsRetrospective StudiesDatabases, Factual

Autor:innen und Institutionen

  • Portland VA Research Foundation, Portland, OR.
  • Department of Biomedical Engineering, Oregon Health and Science University, Portland, OR.
  • VA Salt Lake City Healthcare System, VA Informatics and Computing Infrastructure (VINCI) Group, Salt Lake City, UT.
  • Department of Radiation Oncology, Tampa General Hospital, Tampa, FL.
  • Division of Hospital and Specialty Medicine, Portland VA Healthcare System, Portland, OR.
  • Department of Radiation Medicine, Oregon Health and Science University, Portland, OR.

ORCID-Profile: William Schreyer, Ryan Melson, Cecelia Madison, Evangelia Katsoulakis, Reid F Thompson

Förderung

  • CSRD VA

Zitieren

APA

Schreyer, W., Melson, R., Anderson, C., Madison, C., Katsoulakis, E., & Thompson, R. F. (2025). Automated Identification of Radiotherapy Courses From US Department of Veterans Affairs Administrative Data. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00088

Vancouver

Schreyer W, Melson R, Anderson C, Madison C, Katsoulakis E, Thompson RF. Automated Identification of Radiotherapy Courses From US Department of Veterans Affairs Administrative Data. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00088

BibTeX
@article{Schreyer2025,
  author = {Schreyer, William and Melson, Ryan and Anderson, Christopher and Madison, Cecelia and Katsoulakis, Evangelia and Thompson, Reid F},
  title = {Automated Identification of Radiotherapy Courses From US Department of Veterans Affairs Administrative Data},
  journal = {JCO Clinical Cancer Informatics},
  year = {2025},
  doi = {10.1200/cci-25-00088}
}
Kostenlos starten →