Performance of GPT-5 in the Interpretation of IBD Histopathology Reports

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.

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.

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.

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.