Introduction

Large language models, such as ChatGPT-4, have significantly enhanced access to Artificial Intelligence (AI) tools. However, their role in clinical practice of gastroenterology remains uncertain¹. Accurate classification of esophageal varices is pivotal in managing patients with portal hypertension as it directly influences prognosis and treatment².

Aims & Methods

This study aimed to assess the potential of ChatGPT-4 as a diagnostic tool to accurately classify esophageal varices, and to compare its diagnostic accuracy and reliability to experienced and trainee endoscopists.
We collected photos taken during esophagogastroduodenoscopy performed at the Endoscopic Units of six tertiary Italian centers. The images were input into blank sheets of ChatGPT-4, which was asked to classify the varices by size, indicate the presence of red markings, and evaluate image quality in terms of insufflation, clarity and lightning. The same set of images and evaluation criteria was shown to six experienced endoscopists (E1, E2, E3, E4, E5, E6), to four junior endoscopists (J1, J2, J3, J4) and to five trainee endoscopists (T1, T2, T3, T4, T5). The evaluations from the experienced endoscopists were used as a Ground Truth. ChatGPT-4 had not undergone any prior task‐specific training for esophageal varices detection and classification.

Results

We collected 327 photos, of which 279 were considered to be of good quality by the experienced endoscopists. In detecting esophageal varices, ChatGPT-4 showed a lower AUC (0.77, 95% CI 0.66-0.88, Se 86.2%, Sp 68.4%) compared to one of the junior endoscopists (J2 AUC 0.92, 95% CI 0.87-0.98, Se 90.4%, Sp 94.4%; p<0.05) and comparable to other endoscopists (p>0.05). ChatGPT-4 showed a lower AUC (0.75, 95% CI 0.70-0.80, Se 67.6%, Sp 81.7%) than 3/4 junior endoscopist and 3/5 trainee endoscopists in distinguishing small (F1) from large (F2-F3) varices (p<0.05). For the classification of F3 varices, ChatGPT-4 achieved a higher AUC (0.71, 95% CI 0.63-0.80, Se 52.8%, Sp 89.7%) compared to one of the trainee endoscopists (T5 AUC 0.58, 95% CI 0.51-0.65; p<0.05) and comparable to that of all endoscopists (p>0.05). In identifying red signs, ChatGPT-4 (AUC 0.58, 95% CI 0.52-0.65, Se 20.5%, Sp 96.2%) performed less effectively than the endoscopists (p<0.05).

Conclusion

ChatGPT-4 achieved diagnostic accuracy comparable to junior and trainee endoscopists in detecting esophageal varices and classifying F3 varices, but it was overperformed in differentiating small (F1) from large varices (F2–F3) and in identifying red signs. While it cannot replace the clinical judgment of an experienced operator, the model shows potential as a supportive tool for training and preliminary triage of endoscopic images. Further refinement and dedicated training on endoscopic sign interpretation are needed to enhance its reliability and applicability in routine clinical practice.

References

1) Klang E, Sourosh A, Nadkarni GN, Sharif K, Lahat A. Evaluating the role of ChatGPT in gastroenterology: a comprehensive systematic review of applications, benefits, and limitations. Therap Adv Gastroenterol. 2023 Dec 25
2) Nguyen GC, Correia AJ, Thuluvath PJ. The impact of cirrhosis and portal hypertension on mortality following colorectal surgery: a nationwide, population- based study. Dis Colon Rectum. 2009 Aug

Introduction

Inflammatory Bowel Disease (IBD) is emerging as a significant but under-recognized health challenge in Africa. Diagnostic delays, limited awareness, and a lack of educational opportunities for healthcare professionals persist. The Inaugural Inflammatory Bowel Disease in Africa Symposium was held on April 10th in Abuja, Nigeria, to foster collaboration in IBD diagnosis and management, promote awareness of medical and surgical care options, and support patient advocacy.

Aims & Methods

A hybrid (in-person and virtual) full-day symposium was designed and developed, bringing together specialists in gastroenterology, surgery, nursing, pathology, radiology, and oncology from across the continent. The program featured expert-led lectures and multidisciplinary team case-based discussions. A post-symposium electronic survey was deployed to assess participants’ satisfaction, knowledge gains, practice impacts, and IBD management challenges and provide recommendations for enhancing future symposia. Quantitative responses were analyzed descriptively; qualitative feedback was thematically categorized.

Results

A total of eighty-four individuals registered, with speakers and faculty representing Nigeria, South Africa, Ghana, Zambia, Zimbabwe, the United States, the United Kingdom, Egypt, and Kenya. Fifty-eight (69%) of 84 completed the survey. These comprise nurses (34.5%), surgeons (27.6%), gastroenterologists (17.2%), radiologists (8.6%), pathologists (6.9%), and oncologists (5.2%). Overall, 93% rated the program as Satisfied, with 88% reporting significant knowledge gains in African-context IBD management. Diagnostic and treatment confidence improved in 83% and 76% of participants, respectively, with 69% gaining skills in biopsy techniques and 67% differentiating IBD mimickers. Major challenges reported included limited access to endoscopy and histopathology, low disease awareness among patients, high diagnostic costs, misdiagnosis as infectious diarrhea or tuberculosis, and lack of referral networks. The absence of multidisciplinary care teams was also noted. A strong majority (95%) supported establishing an African IBD registry, emphasizing the need for sustainable funding, technical infrastructure, and training. Hybrid learning and case-based approaches were preferred for future symposia, with interest in pediatric IBD and resource-adapted care.

Conclusion

The symposium significantly enhanced knowledge and confidence in IBD care among participants while exposing critical gaps in diagnostics, treatment access, and care coordination. These findings highlight the need for sustained collaborative efforts to strengthen IBD education and care. Supporting regional training and cross-disciplinary engagement will be essential to building capacity, improving outcomes, and advancing equitable IBD management across the continent.

Disclosure

Nothing to disclose

Clinical Case Summary

Background: Syphilis is a chronic systemic infection caused by the spirochete Treponema pallidum, often referred to as "the great imitator" due to its ability to affect nearly any organ. Syphilitic hepatitis, or "luetic jaundice," is a rare manifestation, indicating spirochete dissemination to the liver.
Case Report: A 26-year-old female was admitted to the hospital with fever (39.5 °C), fatigue, sweating, tremor, dark urine, pale stools, and significant weight loss (15 kg over two months). She also reported lower extremity muscle and joint pain, cough and slowing of speech. On examination, she had icteric skin, a generalized maculopapular rash, and enlarged cervical lymph nodes. No history of alcohol or drug use was noted.
Laboratory tests revealed elevated levels of both cytolytic and cholestatic liver enzymes, along with increased bilirubin an elevated C-reactive protein.
Abdominal ultrasound and contrast CT showed hepatomegaly, hilar and retroperitoneal lymphadenopathy and splenomegaly.
Viral hepatitis markers (HBsAg, HBV PCR, HCVAb, HCV PCR, anti-HAV IgM, anti-HEV IgM) and antibodies for CMV, EBV, HIV, HSV-1,2 were negative. Wright-Hedelson test for brucellosis and serological markers for autoimmune hepatitis were negative while IgG and cerulopasmin levels were within normal range. Given systemic findings and history, syphilis was considered. Serologic tests were positive for Treponema pallidum (ELISA, TPHA, MRP). Liver biopsy revealed mild active hepatitis. The diagnosis of ^secondary syphilitic hepatitis was made. The patient was started on antimicrobial therapy. During follow-up, liver function tests normalized, and systemic symptoms resolved.
Conclusion: This case underscores the importance of considering syphilis in the differential diagnosis of unexplained hepatitis. Although rare, syphilitic hepatitis should be considered in patients with liver enzyme elevations and nonspecific symptoms, particularly when no clear alternative diagnosis is found.

References

1) Malvar G, Cardona D, Pezhouh MK, Adeyi OA, Chatterjee D, Deisch JK, Lamps LW, Misdraji J, Stueck AE, Voltaggio L, Gonzalez RS. Hepatic Secondary Syphilis Can Cause a Variety of Histologic Patterns and May Be Negative for Treponeme Immunohistochemistry. Am J Surg Pathol. 2022 Apr 1;46(4):567-575. doi: 10.1097/PAS.0000000000001848. PMID: 34864775.
2)Supronowicz Ł, Rogalska M. Syphilitic hepatitis. Clin Exp Hepatol. 2024 Mar;10(1):9-13. doi: 10.5114/ceh.2024.136235. Epub 2024 Mar 12. PMID: 38765910; PMCID: PMC11100338.
3)Al Dallal HA, Narayanan S, Alley HF, Eiswerth MJ, Arnold FW, Martin BA, Shandiz AE. Case Report: Syphilitic Hepatitis-A Rare and Underrecognized Etiology of Liver Disease With Potential for Misdiagnosis. Front Med (Lausanne). 2021 Nov 29;8:789250. doi: 10.3389/fmed.2021.789250. PMID: 34912834; PMCID: PMC8666961.
Figure 1: Histological images of the liver biopsy
Figure 2: Abdominal CT images
Figure 3: Images of maculopapular rash