Performance of GPT‐5 in the Interpretation of IBD Histopathology Reports
United European Gastroenterology Journal · 2026
DOI: 10.1002/ueg2.70161 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift United European Gastroenterology Journal, 2026. Verfasst von Marcello Maida und 19 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine and Surgery, University of Enna "Kore", Enna, Italy. Hauptthemen laut MEDLINE: Inflammatory Bowel Diseases, Colitis, Ulcerative, Crohn Disease. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
Histopathological interpretation is crucial for diagnosing inflammatory bowel disease (IBD), distinguishing between Crohn's Disease (CD), Ulcerative Colitis (UC), IBD‐Unclassified (IBD‐U), and Non‐IBD colitis (NIBDC). However, interobserver variability and limited expertise can reduce diagnostic accuracy. Large Language Models (LLMs) such as GPT‐5 may offer clinical support in interpreting histology reports.
Methods
We analyzed 100 real‐life histological reports from ileo‐colonoscopies, equally representing CD, UC, IBD‐U, and NIBDC, collected across five Italian healthcare centers, including both IBD‐specialized and non‐specialized hospitals. A reference standard was established by an expert pathologist. Independent classifications were generated by GPT‐5, five gastrointestinal pathologists, five IBD‐expert gastroenterologists (GIs), and five non‐expert GIs. Diagnostic performance (accuracy, recall, precision, F1‐score), agreement with the reference standard (Cohen's κ ), and inter‐rater reliability (Fleiss' κ ) were assessed.
Results
GPT‐5 achieved the highest agreement with the reference standard with the highest accuracy (76.0%), compared to pathologists (68.6%), IBD‐experts (69.2%), and non‐experts (63.2%). Agreement with the reference standard was substantial for GPT‐5 ( κ = 0.671) and moderate for human groups ( κ = 0.508–0.588). GPT‐5 showed perfect recall for CD and UC, high recall for NIBDC (96.0%), but poor performance for IBD‐U (recall 8.0%, F1‐score 14.3%). Fleiss' κ indicated moderate agreement among pathologists and IBD‐experts, and fair agreement among non‐experts.
Conclusion
GPT‐5 demonstrated reliable performance in interpreting IBD histological reports, exhibiting high accuracy and strong agreement with the reference standard. While unreliable for IBD‐U, GPT‐5 may serve as a supportive tool in histopathological interpretation of IBD, particularly in centers with limited access to expert pathologists or IBD‐specialists.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine and Surgery, University of Enna "Kore", Enna, Italy.
- Gastroenterology Unit, Umberto I Hospital, Enna, Italy.
- Inflammatory Bowel Disease Unit, "Villa Sofia-Cervello" Hospital, Palermo, Italy.
- Gastroenterology Unit, AO Ordine Mauriziano, Turin, Italy.
- Division of Gastroenterology, "Brotzu" Hospital, Cagliari, Italy.
- Gastroenterology, Department of Clinical Medicine and Surgery, School of Medicine "Federico II" of Naples, Naples, Italy.
ORCID-Profile: Marcello Maida, Rachele Del Sordo, Dario Ligresti, Giovanni Marasco, Vincenzo Villanacci
Zitieren
APA
Maida, M., Vitello, A., Macaluso, F. S., Daperno, M., Mocci, G., Rispo, A., Calabrese, G., Decarli, N. L., Laschi, L., Fattorini, C., Locci, G., Sordo, R. D., Ligresti, D., Tacelli, M., Furnari, M., Sferrazza, S., Marasco, G., Facciorusso, A., Orlando, A., & Villanacci, V. (2026). Performance of GPT‐5 in the Interpretation of IBD Histopathology Reports. United European Gastroenterology Journal. https://doi.org/10.1002/ueg2.70161
Vancouver
Maida M, Vitello A, Macaluso FS, Daperno M, Mocci G, Rispo A, et al. Performance of GPT‐5 in the Interpretation of IBD Histopathology Reports. United European Gastroenterology Journal. 2026. doi:10.1002/ueg2.70161
BibTeX
@article{Maida2026,
author = {Maida, Marcello and Vitello, Alessandro and Macaluso, Fabio Salvatore and Daperno, Marco and Mocci, Giammarco and Rispo, Antonio and Calabrese, Giulio and Decarli, Nicola L and Laschi, Lucrezia and Fattorini, Caterina and Locci, Giorgia and Sordo, Rachele Del and Ligresti, Dario and Tacelli, Matteo and Furnari, Manuele and Sferrazza, Sandro and Marasco, Giovanni and Facciorusso, Antonio and Orlando, Ambrogio and Villanacci, Vincenzo},
title = {Performance of GPT‐5 in the Interpretation of IBD Histopathology Reports},
journal = {United European Gastroenterology Journal},
year = {2026},
doi = {10.1002/ueg2.70161}
}
EUVIMED