Large Language Model Translation of BI-RADS Breast Imaging Reports into Arabic: A Blinded Expert Evaluation of Diagnostic Communication Safety
Diagnostics · 07.08.2026 · 16 (16) · 2495
DOI: 10.3390/diagnostics16162495 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 07.08.2026. Verfasst von Mohammad Alarifi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Radiological Sciences Department, College of Applied Medical Sciences, King Saud University, Riyadh 4545, Saudi Arabia. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Saud University, Deanship of Scientific Research, King Saud University, Riyadh, Saudi Arabia.
Abstract (Originalsprache)
Background/Objectives: Breast imaging reports contain Breast Imaging Reporting and Data System (BI-RADS) assessments and management recommendations that may be difficult for patients to understand across languages. Large language models (LLMs) may support patient-facing communication, but clinically important details must be preserved. This study compared radiologists’ opinions regarding the quality, clinical fidelity, safety of wording, and communication usefulness of patient-friendly Arabic translations of BI-RADS breast imaging reports generated by three LLMs.
Methods
Five de-identified reports representing BI-RADS categories 0, 2, 3, 4, and 6 were translated from English into Arabic by DeepSeek, ChatGPT, and Gemini using an identical structured prompt. Fifty radiologists rated the blinded outputs across eight 5-point domains. Model ratings were compared using Friedman tests, Kendall’s W, and multiplicity-adjusted Wilcoxon signed-rank tests. Laterality was also verified against the source reports.
Results
Gemini achieved the highest overall mean score (3.73 ± 0.78), followed by DeepSeek (3.54 ± 0.73) and ChatGPT (3.03 ± 0.70). The overall model effect was significant (χ2 = 34.11, df = 2, p < 0.001; Kendall’s W = 0.341). Gemini and DeepSeek each outperformed ChatGPT across all eight domains (adjusted p < 0.001), and Gemini outperformed DeepSeek overall (adjusted p = 0.009). No laterality errors were identified among the 15 translations.
Conclusions
Performance remained model-dependent despite the shared prompt. Among the participating radiologists, Gemini received the highest expert ratings, while DeepSeek remained competitive. Because errors involving BI-RADS categories, laterality, measurements, lesion location, or recommendations could change diagnostic understanding, LLM-generated Arabic translations should serve as radiologist-reviewed communication aids rather than autonomous substitutes for clinical explanation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Radiological Sciences Department, College of Applied Medical Sciences, King Saud University, Riyadh 4545, Saudi Arabia.
- College of Health Sciences, University of Wisconsin-Milwaukee, Milwaukee, WI 53211, USA.
- Health Informatics Department, Faculty of Public Health and Tropical Medicine, Jazan University, Jazan 45142, Saudi Arabia.
- Radiology Department, Prince Sultan Military Medical City, Riyadh 12233, Saudi Arabia.
ORCID-Profile: Mohammad Alarifi, Jake Luo, Abdulrahman Jabour, Yazeed Alashban, Meaad Almusined, Maram Mobara, Alhanouf Alshedi, Mansour Almanaa
Förderung
- King Saud University
- Deanship of Scientific Research, King Saud University, Riyadh, Saudi Arabia
Zitieren
APA
Alarifi, M., Luo, J., Jabour, A., Alashban, Y., Almusined, M., Mobara, M., Alshedi, A., & Almanaa, M. (2026). Large Language Model Translation of BI-RADS Breast Imaging Reports into Arabic: A Blinded Expert Evaluation of Diagnostic Communication Safety. Diagnostics, 16(16), 2495. https://doi.org/10.3390/diagnostics16162495
Vancouver
Alarifi M, Luo J, Jabour A, Alashban Y, Almusined M, Mobara M, et al. Large Language Model Translation of BI-RADS Breast Imaging Reports into Arabic: A Blinded Expert Evaluation of Diagnostic Communication Safety. Diagnostics. 2026;16(16):2495. doi:10.3390/diagnostics16162495
BibTeX
@article{Alarifi2026,
author = {Alarifi, Mohammad and Luo, Jake and Jabour, Abdulrahman and Alashban, Yazeed and Almusined, Meaad and Mobara, Maram and Alshedi, Alhanouf and Almanaa, Mansour},
title = {Large Language Model Translation of BI-RADS Breast Imaging Reports into Arabic: A Blinded Expert Evaluation of Diagnostic Communication Safety},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {16},
pages = {2495},
doi = {10.3390/diagnostics16162495}
}
EUVIMED