Evaluating ChatGPT ‐5 for Detection of Barrett's Esophagus and Grading of Esophagitis: A Multiclass Endoscopic Image Analysis
JGH Open · 2026-07 · 10 (7)
DOI: 10.1002/jgh3.70452 ↗Kurz gefasst
Fachartikel in der Zeitschrift JGH Open, online erschienen am 22.07.2026. Verfasst von Hamza R Khan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gastroenterology & Advanced Endoscopy Rutgers New Jersey Medical School Newark New Jersey USA. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Aims
Gastroesophageal reflux disease can progress to reflux esophagitis and Barrett's esophagus (BE), making accurate endoscopic diagnosis important. Artificial intelligence tools like ChatGPT‐5 may assist image interpretation, though data on newer large language models remains limited. This study evaluated ChatGPT‐5 for BE detection and LA esophagitis severity classification. Methods and Results Endoscopic images from the HyperKvasir dataset were analyzed, including BE, esophagitis A, esophagitis B–D, and normal Z‐line images. Four standardized prompts were assessed: (1) BE versus normal, (2) esophagitis versus normal, (3) LA‐grade severity (A vs. B–D), and (4) BE versus severe esophagitis. ChatGPT‐5 was evaluated in auto mode. Two investigators analyzed 640 unique images, yielding 1280 evaluations. Sensitivity, specificity, positive/negative predictive values (PPV/NPV), F1 scores, and accuracy were calculated. In binary tasks, sensitivity was highest for severe esophagitis (B–D) (0.774). Binary accuracy was similar across tasks (~0.64), with the highest for severe esophagitis (0.655). In three‐class analyses, severe esophagitis performed best (sensitivity 0.506, specificity 0.761, accuracy 0.438), with performance improving alongside disease severity. PPV trended higher for severe esophagitis compared with normal mucosa ( p ~ 0.03), though significance was not retained after multiple‐comparison correction. In the BE‐severe esophagitis‐normal comparison, severe esophagitis achieved the highest sensitivity (0.590), specificity (0.790), and accuracy (0.521). PPV trended higher for severe esophagitis versus normal mucosa ( p ~ 0.05), though significance was not maintained after multiplicity adjustment. NPVs exceeded PPVs across all paradigms.
Conclusion
ChatGPT‐5 demonstrated moderate performance for esophageal image interpretation, performing best for severe esophagitis and worst for mild esophagitis/BE. Binary prompting outperformed multiclass formats, and the model functioned better as a rule‐out tool.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Gastroenterology & Advanced Endoscopy Rutgers New Jersey Medical School Newark New Jersey USA.
- Department of Medicine SUNY Downstate Health Sciences Brooklyn New York USA.
ORCID-Profile: Hamza R Khan, Owais M Aftab, Ahmed H Al-Khazraji
Zitieren
APA
Khan, H. R., Mirza, I., Aftab, O. M., Shah, Y., & Al-Khazraji, A. H. (2026). Evaluating ChatGPT ‐5 for Detection of Barrett's Esophagus and Grading of Esophagitis: A Multiclass Endoscopic Image Analysis. JGH Open, 10(7). https://doi.org/10.1002/jgh3.70452
Vancouver
Khan HR, Mirza I, Aftab OM, Shah Y, Al-Khazraji AH. Evaluating ChatGPT ‐5 for Detection of Barrett's Esophagus and Grading of Esophagitis: A Multiclass Endoscopic Image Analysis. JGH Open. 2026;10(7). doi:10.1002/jgh3.70452
BibTeX
@article{Khan2026,
author = {Khan, Hamza R and Mirza, Ibraheem and Aftab, Owais M and Shah, Yash and Al-Khazraji, Ahmed H},
title = {Evaluating ChatGPT ‐5 for Detection of Barrett's Esophagus and Grading of Esophagitis: A Multiclass Endoscopic Image Analysis},
journal = {JGH Open},
year = {2026},
volume = {10},
number = {7},
doi = {10.1002/jgh3.70452}
}
EUVIMED