EUVIMEDEUVIMED entdecken
Crossref

Comparative evaluation of multimodal large language models for Mayo Endoscopic Subscore grading in ulcerative colitis

Xiao-Yi Zhao, Yue Shen, Jun-Jie He, Qun-Yan Zhou, Li-Sha Jiang, Zi-Ru Zhou, Fang-Mei An, Qiang Zhan, Jing Sun, Wei Feng

World Journal of Gastroenterology · 28.06.2026 · 32 (24)

DOI: 10.3748/wjg.118690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Journal of Gastroenterology, online erschienen am 28.06.2026. Verfasst von Xiao-Yi Zhao und 9 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND Ulcerative colitis (UC) is a chronic inflammatory disorder that typically affects adults aged 20-40 years and presents with hematochezia and diarrhea. Endoscopic evaluation using the Mayo Endoscopic Subscore (MES; 0-3) is standard for assessing disease severity, but grading depends heavily on endoscopist experience and is prone to interobserver variability. Recent advances in multimodal large language models (MLLMs), such as GPT and Gemini, enable automated interpretation of medical images and text, offering potential for objective and reproducible MES grading. However, their accuracy and consistency across intestinal segments remain largely untested. AIM To compare the diagnostic accuracy of five MLLMs in UC MES evaluation and to assess consistency across segments and grades. METHODS We collected 402 endoscopic images from patients with UC covering the entire colon. Three experienced experts independently graded all images according to MES criteria, and 283 images with a unanimous consensus were included as the reference standard. These images were evaluated by five MLLMs and two senior physicians under two conditions: Without segmental context and with anatomical segmental information. Model and physician performance were compared, and stratified analyses were conducted by intestinal segment and MES grade. RESULTS The diagnostic accuracies of the two inflammatory bowel disease physicians were 81.6% and 78.4%, respectively, with strong interobserver agreement (κ = 0.692). Among the MLLMs, GPT-5 achieved the highest overall performance (F1 = 0.720) with accuracy comparable with that of physician 2 (71.7% vs 78.4%, P = 0.068). Other models exhibited significantly lower performance (all P < 0.001). The sigmoid colon was the most accurately assessed region (mean F1 = 0.682), whereas the rectum and ileocecal region were the most challenging (0.447 and 0.493, respectively). The addition of segmental information improved the accuracy of lower-performing models. Both models and physicians showed the lowest accuracy for MES = 1, reflecting the subjective nature of mild disease activity. CONCLUSION This study suggested that GPT-5 holds potential for static-image-based MES grading, but performance varies and requires external validation and optimization. Future work will optimize artificial intelligence endoscopy through tuning and multimodality.

Zitieren

APA

Zhao, X., Shen, Y., He, J., Zhou, Q., Jiang, L., Zhou, Z., An, F., Zhan, Q., Sun, J., & Feng, W. (2026). Comparative evaluation of multimodal large language models for Mayo Endoscopic Subscore grading in ulcerative colitis. World Journal of Gastroenterology, 32(24). https://doi.org/10.3748/wjg.118690

Vancouver

Zhao X, Shen Y, He J, Zhou Q, Jiang L, Zhou Z, et al. Comparative evaluation of multimodal large language models for Mayo Endoscopic Subscore grading in ulcerative colitis. World Journal of Gastroenterology. 2026;32(24). doi:10.3748/wjg.118690

BibTeX
@article{Zhao2026,
  author = {Zhao, Xiao-Yi and Shen, Yue and He, Jun-Jie and Zhou, Qun-Yan and Jiang, Li-Sha and Zhou, Zi-Ru and An, Fang-Mei and Zhan, Qiang and Sun, Jing and Feng, Wei},
  title = {Comparative evaluation of multimodal large language models for Mayo Endoscopic Subscore grading in ulcerative colitis},
  journal = {World Journal of Gastroenterology},
  year = {2026},
  volume = {32},
  number = {24},
  doi = {10.3748/wjg.118690}
}
Kostenlos starten →