Introduction

Artificial intelligence (AI) is playing an increasingly prominent role in gastrointestinal endoscopy, particularly in enhancing real-time lesion detection during colonoscopy. This study evaluates the impact of an advanced AI-assisted detection system on the Adenoma Detection Rate (ADR), Adenomas per Colonoscopy (APC), and predictive performance, comparing outcomes across endoscopists with different levels of experience.

Aims & Methods

Three endoscopists participated in the study: two with limited experience (Physicians A and B) and one expert (Physician C). A total of 720 colonoscopies were analyzed, with 400 procedures performed using AI assistance and 320 without, evenly distributed among the three operators.
Patients included were between 40 and 75 years of age and underwent colonoscopy either as a screening examination or following a positive fecal occult blood test. Exclusion criteria comprised a history of inflammatory bowel disease (IBD), hereditary polyposis syndromes, major colorectal surgery, or inadequate bowel preparation. For each procedure, data were collected on ADR, APC, the predictive accuracy of the AI system, and retraction time (from cecum to anus).

Results

The use of AI resulted in a marked and consistent improvement in all primary performance indicators across all three endoscopists.
In terms of ADR, Physician A improved from 23.8% without AI to 29.7% with AI; Physician B from 26.9% to 31.6%; and Physician C from 34.7% to 36.6%. Similarly, the APC index increased from 0.52 to 0.63 for Physician A, from 0.55 to 0.65 for Physician B, and from 0.64 to 0.73 for Physician C.
The AI system demonstrated high predictive accuracy across all operators, with no false positives recorded for polyps ≥4 mm in size. Prediction rates were 87.9% for Physician A, 89% for Physician B, and 92% for Physician C, confirming the device’s reliability in supporting polyp identification during real-time examination. Retraction times were slightly prolonged with AI usage: 8.3 minutes vs 7.5 for Physician A, 8.7 vs 7.4 for Physician B, and 8.8 vs 8.0 for Physician C. However, these differences did not reach statistical significance, indicating that AI support did not meaningfully affect procedural efficiency.

Conclusion

The integration of AI into colonoscopy workflows significantly improved both ADR and APC, with the most substantial impact observed in less experienced endoscopists. Physicians A and B, who initially showed suboptimal detection metrics, achieved levels of quality comparable to those of the expert operator in the absence of AI, highlighting AI’s value as a tool for bridging the gap in operator performance. The high predictive reliability of the system—particularly for clinically relevant lesions—and the absence of false positives ≥4 mm further support its clinical utility. Although retraction times increased slightly with AI, this change was not statistically significant, suggesting that the diagnostic advantages were not offset by decreased procedural efficiency. Overall, AI proves to be a valuable and scalable solution to enhance adenoma detection, support clinical training, and promote uniform quality standards in colorectal cancer screening.

References

1.Antonelli, G., Gkolfakis, P., Tziatzios, G., Papanikolaou, I. S., Triantafyllou, K., & Hassan, C. (2020). Artificial intelligence-aided colonoscopy: Recent developments and future perspectives. World journal of gastroenterology, 26(47), 7436–7443.
2.Hassan, C., Balsamo, G., Lorenzetti, R., Zullo, A., & Antonelli, G. (2022). Artificial Intelligence Allows Leaving-In-Situ Colorectal Polyps. Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association, 20(11), 2505–2513.e4
3.Houwen, B. B. S. L., Hassan, C., Coupé, V. M. H., Greuter, M. J. E., Hazewinkel, Y., Vleugels, J. L. A., Antonelli, G., Bustamante-Balén, M., Coron, E., Cortas, G. A., Dinis-Ribeiro, M., Dobru, D. E., East, J. E., Iacucci, M., Jover, R., Kuvaev, R., Neumann, H., Pellisé, M., Puig, I., Rutter, M. D., … Dekker, E. (2022). Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy, 54(1), 88–99.

Clinical Case Summary

Acute Esophageal necrosis (AEN) is a rare clinical entity, with fewer than 150 reported cases in literature and endoscopic prevalence ranging from 0.01 to 0.28%(1). First described by Goldenberg and later characterized by Gurvits in 2007, this condition predominantly affects the distal esophagus due to its relatively poor blood supply, resulting in its characteristic black appearance. AEN typically occurs in male patients with predisposing risk factors such as chronic liver disease, chronic kidney disease, alcoholism, malnutrition and cardiovascular comorbidities(2). It is also associated with sepsis and carries a high mortality rate. Upper gastrointestinal endoscopy remains the gold standard (3). Given the rarity of AEN, the standardized management guidelines are not well defined and the primary therapeutic focus remains on optimizing medical condition.
We present the case of an 81-year old female, marking the first documented instance of AEN in Ireland, who presented with septic shock, profound hypoglycemia with hypothermia and workup revealed Acute Esophageal Necrosis. The development of AEN in our patient was multifactorial, with esophageal ischemia secondary to septic shock induced hypotension playing a key role. The condition may have been exacerbated by reduced cardiac output and vasoconstriction of splanchnic blood vessels secondary to hypothermia. Furthermore, gastric reflux likely contributed to additional mucosal injury. The patient was managed successfully with conservative yet aggressive approach with inotropic support, antibiotics and total parenteral nutrition.
We conclude that AEN should be considered in any patient with predisposing risk factors, particularly in presence of critical illness. This case highlights the urgent need for development of standardized guidelines to ensure timely diagnosis and optimal management for this rare but serious condition.
The poster will include pictures of Upper GI endoscopy of the patient

References

1. Goldenberg SP, Wain SL, Marignani P. Acute necrotizing esophagitis. Gastroenterology. 1990 Feb;98(2):493-6. doi: 10.1016/0016-5085(90)90844-q. PMID: 2295407.

2. https://pubmed.ncbi.nlm.nih.gov/17322991/

3. Sina (2023). Acute Esophageal Necrosis: A Rare and Serious Cause of Digestive Bleeding - Clinical Case Reports Journal (ISSN 2767-0007). [online] Clinical Case Reports Journal. Available at: https://clinicalcasereportsjournal.com/article/1000264/acute-esophageal-necrosis-a-rare-and-serious-cause-of-digestive-bleeding [Accessed 28 Feb. 2025].

Introduction

Gastric hyperplastic polyps (GHPs) carry a neoplastic transformation risk of up to 5%, with previous studies indicating an increased risk with larger polyp size. We aimed to evaluate the frequency and risk factors of its malignant transformation in a Portuguese cohort.

Aims & Methods

A multicenter retrospective cohort study was conducted including all patients undergoing endoscopic resection of GHPs ≥10mm from January 2013 to January 2024 in Portuguese tertiary reference centers. Patients with hereditary polyposis syndromes were excluded. Demographic, clinical, endoscopic, and histopathological data were collected.

Results

A total of 782 GHPs from eight centers were evaluated. The median age was 68 years (IQR 60-75), and 58.8% were female. Evidence of advanced gastritis stage (OLGIM≥3) and synchronous gastric neoplasia were present in 57 (10.2%) and 37 (4.7%) cases, respectively. The median lesion size was 15 mm (IQR 12-20), and most presented a polypoid morphology (96.8%). Most GHPs were removed by endoscopic mucosal resection (86.6%), followed by cold snare polypectomy (8.1%) endoscopic submucosal dissection (3.6%), and cold snare EMR (1.7%), achieving en-bloc resection in 677 cases (86.6%). Neoplastic transformation was observed in 33 polyps (4.2%) – 25 (3.2%) low/high-grade dysplasia and 8 (1.0%) adenocarcinoma; the resection was non-curative in 30.3% of cases.
In the multivariate analysis, OLGIM≥3 (OR 4.994, 95%CI 1.036-24.065), lesion size ≥25 mm (OR 7.973, 95%CI 7.973 (1.242-51.180), flat/depressed morphology (OR 9.57, 95%CI 1.096-83.712) and synchronous gastric neoplasia (OR 16.956, 95%CI 2.737-105.045) were independently associated with a higher risk of malignant transformation.

Conclusion

The risk of malignant transformation of GHPs in non-neglectable, with lesion size and morphology and concomitant precancerous gastric conditions/lesions being associated with a higher risk. Nevertheless, the rate of non-curative endoscopic resection is high. The identification of these features may help for optimizing and tailoring the selection of adequate endoscopic resection techniques and surveillance strategies in high-risk patients.

Introduction

The incidence of rectal neuroendocrine neoplasms (R-NENs) has been increasing annually. While most R-NENs are solitary, multiple lesions are relatively rare. Previous studies have suggested that patients with ≥8 lesions are more likely to exhibit lymphatic invasion and metastasis, indicating higher risk. However, the clinical and pathological features, prognosis, and endoscopic treatment outcomes of multiple R-NENs remain poorly understood. This study aimed to clarify the clinical characteristics and endoscopic treatment efficacy of multiple R-NENs through a retrospective analysis of cases from our hospital, providing evidence for clinical management.

Aims & Methods

This retrospective study included 28 patients with multiple R-NENs treated endoscopically at the Cancer Hospital of the Chinese Academy of Medical Sciences between January 2010 and January 2024. Patients were divided into two groups based on lesion count: the "several group" (n < 8) and the "numerous group" (n ≥ 8). All patients underwent preoperative imaging to exclude lymph node metastasis and distant metastases. Data on demographics, lesion characteristics, endoscopic procedures, pathological findings, and follow-up outcomes were collected and analyzed.

Results

We compared endoscopic treatment outcomes between patients with several (＜8, n=24) and numerous (≥8, n=4) rectal neuroendocrine tumors. The numerous group had a larger median maximum diameter (9.50 mm vs. 6.00 mm, p=0.337) and included one G2 case (25.0%) versus none in the several group, though differences were not significant. Notably, endoscopic complete resection was achieved in 100% of patients in both groups. All other parameters, including margin positivity, vascular invasion, neural invasion, and R0 resection rate, showed no significant differences. However, the numerous group had a significantly higher recurrence rate (75.0% vs. 0%, p=0.001). These findings highlight lesion count as a critical prognostic indicator for recurrence after endoscopic treatment.

Conclusion

Patients with ≥8 rectal neuroendocrine tumors exhibited more aggressive disease behavior, characterized by higher recurrence rates. These findings underscore the importance of lesion count as a prognostic indicator and suggest that patients with ≥8 lesions may require more intensive follow-up and management. For patients with <8 lesions, endoscopic treatment is effective when lymph node and distant metastases are excluded preoperatively. Future studies with larger datasets are needed to validate these findings and explore optimized treatment strategies.

Disclosure

The authors declare no conflicts of interest in relation to this study.

Introduction

Emerging experimental and clinical data suggest that the gut microbiome can significantly influence the antitumor efficacy of key chemotherapy agents, including 5-fluorouracil, oxaliplatin, and docetaxel. These agents form the backbone of the neoadjuvant chemotherapy (NAC) regimen, FLOT, which is widely used for the treatment of locally advanced gastric cancer (GC). However, despite growing evidence from preclinical models, clinical studies investigating the direct association between gut microbiome composition and the response to NAC in GC patients remain scarce.

Aims & Methods

This study aims to address this gap in knowledge by exploring the relationship between the gut microbiome and therapeutic outcomes in this clinical context. In this longitudinal observational study, we explored the association between pre-treatment fecal microbiome composition analyzed via 16S rRNA gene sequencing and histological tumor regression, as assessed by the Becker score, in GC patients undergoing NAC with the FLOT regimen, followed by gastrectomy.

Results

Among the 38 enrolled patients, 19 (50%) achieved a Becker score of 1–2 and were classified as ‘Responders,’ while the other 19 (50%) were classified as ‘Non-responders’. Responders exhibited a higher abundance of Parabacteroides distasonis, Alistipes sp. AL-1, and Bacteroides plebeius. A combined biomarker of these species demonstrated robust predictive accuracy for a favorable response to NAC, with sensitivity of 89%, specificity of 63%, and an AUC of 0.8 (95% CI: 0.66–0.94). In contrast, non-responders showed a predominance of bacterial genera, including Ruminococcaceae UCG-014, Ruminococcus 1, Ruminococcaceae UCG-005, and the [Eubacterium] eligens group. The combined biomarker of these genera demonstrated excellent predictive performance for poor NAC response, with sensitivity of 89%, specificity of 95%, and an AUC of 0.93 (95% CI: 0.85–1.0).

Conclusion

The results of our study support the hypothesis that the pre-treatment gut microbiome composition can serve as a reliable biomarker for predicting both positive and negative responses to NAC in GC patients. By identifying specific microbial signatures associated with chemotherapy outcomes, this research provides critical insights into how microbiome-based strategies might enhance personalized treatment regimens for GC. Future studies are needed to validate these findings and explore potential therapeutic interventions targeting the microbiome to improve clinical outcomes in GC patients.

Clinical Case Summary

The patient was a 39-year-old man admitted to the emergency department for sudden onset of diffuse abdominal pain. The patient had a pathological history of chronic smoking. The clinical history dates back 10 hours to the onset of abdominal pain, initially localized to the epigastrium and rapidly generalized to the entire abdomen, unrelieved by usual treatment and without other associated signs. The patient was conscious, normocardiac, normotensive, slightly tachypneic and apyretic. A diffuse abdominal tenderness was noted, with no other particular pathological signs. Biological work-up revealed hyperleukocytosis at 20430/mm3 , C-reactive protein (CRP) at 5.80 mg/L , no hydroelectrolytic disorders, and the rest of the biological work-up returned normal. Abdominal CT revealed pneumo bubbles with infiltration of mesenteric fat, predominantly at the supra-mesocolic level, in favor of a hollow organ perforation. The patient underwent surgery, which revealed a pre-pyloric gastric perforation measuring approximately 1 cm with a clean edge and the presence of 2 hepatic nodules measuring 0.25 and 0.5 cm in segment II. The rest of the exploration was without anomalies, and the gastric perforation was sutured, with biopsy of the edges of the gastric perforation and biopsy of the hepatic nodules. Histopathological examination revealed the presence of subacute and chronic nonspecific inflammatory remodeling in the gastric margin biopsy, whereas the liver biopsy showed epithelial and gigantocellular granulomatous inflammation with caseous necrosis consistent with tuberculosis.The diagnosis of hepatic tuberculosis was made.The patient was put on standard anti-tuberculosis treatment for 6 months.

Clinical Case Summary

A 36-year-old man with a history of chronic diarrhea was admitted with isolated oedemato-ascitic syndrome and general deterioration.On examination,he had conjunctival subicterus bilateral lower limb edema, thoracoabdominal collateral venous circulation and ascites.As part of the etiological work-up of the oedemato-ascitic syndrome,Cardiac and renal causes were ruled out.Chest X-ray showed a hilar opacity with tracheal retraction.GeneXpert test on sputum confirmed pulmonary tuberculosis.Paracentesis showed non-infected transudate ascites with a serum-ascites albumin gradient at 11 g/L.Blood tests showed microcytic hypochromic anemia,normal platelet count,and elevated liver tests with AST at 18 times the upper limit of normal (ULN), ALT at 11× ULN, alkaline phosphatase at 3.3× ULN,normal GGT,prothrombin time at 25%,and a direct hyperbilirubinemia of 24 mg/L.Viral serologies were negative.Serum protein electrophoresis showed a beta-gamma bridging pattern with hypergammaglobulinemia.Antinuclear antibodies were positive, while the remaining autoimmune panel and Wilson's disease screening were negative.Abdominal CT angiography showed hepatomegaly with hypertrophy of the caudate lobe,a “flip-flop” pattern,stenosis of the intrahepatic inferior vena cava, and non visualization of the hepatic veins confirming Budd-Chiari syndrome(BDS).The etiological work-up of the chronic diarrhea revealed negative HIV serology,normal TSH,and elevated IgA anti-transglutaminase antibodies.Ileocolonoscopy showed partial villous atrophy in the ileum,supporting the diagnosis of coeliac disease (CD).Given the radiological features suggestive of BDS,a thrombophilia work-up was performed and was negative.An autoimmune etiology related to CD was retained as the most likely cause of BDS.A gluten-free diet resolved the diarrhea.Anticoagulation was started, but persistent portal hypertension and difficulty maintaining therapeutic anticoagulation led to referral for a portosystemic shunt.

References

An actual image of the thoracoabdominal collateral venous circulation of the patient, and his abdominal CT angiography.