EUVIMEDEUVIMED entdecken
Crossref

Radiology report quality improvement through structured provider feedback: a data-driven initiative

Madhvi Yadav, Saubhagya Srivastava, Minal Jagtiani, Yingke Xu, Dante Pezzutti, Nathan M Cross, Manjiri Dighe

Abdominal Radiology · 30.06.2026

DOI: 10.1007/s00261-026-05654-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, online erschienen am 30.06.2026. Verfasst von Madhvi Yadav und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Washington Medical Center, Seattle, USA. madhvi@uw.edu. Die Arbeit nennt 17 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To evaluate EHR-embedded provider feedback workflow for identifying probable concerns in radiology reports and to assess large language model (LLM)-assisted classification of free text comments. METHODS: We collected reports over 11 months (December 2024-October 2025) in this single-centered quality improvement initiative. Link was embedded in EHR (Epic), which directed providers to a voluntary REDCap form. Form captured satisfaction, report adequacy, follow-up requests, and free-text comments. Analysis included free text issue categorizations with Llama 3.3, for five pre-defined non-mutually exclusive categories, and sentiment analysis. Agreement with two radiologists was assessed using Cohen's kappa. Descriptive statistics were reported. RESULTS: Of 270 responses, 267 were included in the final analysis. Corresponded to 0.026% of 1,010, 219 final reports generated. Overall, 52.8% (141/267) of responses were rated ≥ 4 stars, 44.6% (119/267) indicated that the reports "somewhat" or "did not" address the clinical question, and 28.1% requested a follow-up in this voluntary cohort. Free-text comments were provided in 65.9% (176/267) of responses. 162 comments had a classifiable concern, of 176 free-text comments. The most frequent issue categories were clinical clarity and completeness (91.4%, 148/162), followed by actionability and recommendations (30.9%, 50/162). Kappa agreement showed moderate to substantial agreement between reviewers and LLM (0.607-0.734). CONCLUSION: Structured provider feedback can complement traditional peer review by capturing deficiencies that may go unnoticed by radiologists to radiologists' review alone. Human - LLM agreement was moderate to substantial, warranting further evaluation for scalable model.

Schlagwörter

Stichwörter der Autor:innen

Large language model integrated workflowQuality improvementRadiology reporting

Autor:innen und Institutionen

  • Department of Radiology, University of Washington Medical Center, Seattle, USA. madhvi@uw.edu.
  • Department of Radiology, University of Iowa Health Care, Iowa City, USA.
  • Department of Radiology, University of Washington Medical Center, Seattle, USA.

Zitieren

APA

Yadav, M., Srivastava, S., Jagtiani, M., Xu, Y., Pezzutti, D., Cross, N. M., & Dighe, M. (2026). Radiology report quality improvement through structured provider feedback: a data-driven initiative. Abdominal Radiology. https://doi.org/10.1007/s00261-026-05654-3

Vancouver

Yadav M, Srivastava S, Jagtiani M, Xu Y, Pezzutti D, Cross NM, et al. Radiology report quality improvement through structured provider feedback: a data-driven initiative. Abdominal Radiology. 2026. doi:10.1007/s00261-026-05654-3

BibTeX
@article{Yadav2026,
  author = {Yadav, Madhvi and Srivastava, Saubhagya and Jagtiani, Minal and Xu, Yingke and Pezzutti, Dante and Cross, Nathan M and Dighe, Manjiri},
  title = {Radiology report quality improvement through structured provider feedback: a data-driven initiative},
  journal = {Abdominal Radiology},
  year = {2026},
  doi = {10.1007/s00261-026-05654-3}
}
Kostenlos starten →