Introduction

The advancement of computer-aided detection systems using artificial intelligence (AI) opened a new scope in endoscopic image analysis. However, the deep-learning-based models developed on closed datasets are susceptible to unknown anomalies in complex clinical environments. In particular, the high false positive rate in polyp detection remains a major challenge in clinical practice. The frequent occurrence of false positives (FPs) leads to endoscopists' fatigue, distraction, and the need for refocusing. It costs additional time and effort to discriminate FPs from true positives (TPs).

Aims & Methods

We propose a generic and practical solution for FP suppression in real-world AI-assisted colonoscopy. We release the FPPD-13 dataset, which includes real-world cases of TPs (1300 samples) and 13 classes of FPs (100 samples/class) with a comprehensive taxonomy. A YOLOv5 polyp detector was trained on a private dataset collected in Zhongshan Hospital. It was employed to analyze real-world colonoscopy videos for the collection of TPs and FPs. Two endoscopists discriminated all the positive predictions into TPs and FPs, and a third senior endoscopist was consulted for controversial images. We further propose EndoBoost, a plug-and-play module for FP suppression during polyp detection. EndoBoost follows the formulation of anomaly detection (AD) and takes FPs as anomalies. Specifically, a normalizing flow is utilized for density estimation in the feature space and rejecting FPs during real-time inference. We develop a learnable image encoder to obtain an informative feature space for the AD task. The image encoder and the normalizing flow are jointly optimized to learn the TP manifold while the FP samples are also exploited through outlier exposure.

Results

	AP	AUC	Accuracy	Precision	Sensitivity	Specificity
EndoBoost	0.788±0.017	0.793±0.020	0.705±0.019	0.655±0.026	0.877±0.061	0.534±0.078
KDE	0.646±0.024	0.610±0.027	0.569±0.021	0.541±0.016	0.928±0.036	0.209±0.076
OC-SVM	0.733±0.011	0.726±0.004	0.627±0.037	0.588±0.036	0.886±0.071	0.368±0.145
MCD	0.700±0.009	0.730±0.004	0.657±0.009	0.604±0.011	0.915±0.036	0.398±0.051
PCA (10)	0.654±0.020	0.677±0.013	0.611±0.017	0.567±0.012	0.948±0.024	0.275±0.047
PCA (100)	0.690±0.013	0.721±0.005	0.657±0.008	0.605±0.008	0.902±0.030	0.412±0.035
AE (128)	0.647±0.031	0.675±0.025	0.605±0.022	0.561±0.014	0.960±0.013	0.249±0.044
VAE (128)	0.718±0.008	0.703±0.008	0.588±0.028	0.557±0.025	0.902±0.062	0.275±0.118
iForest	0.644±0.034	0.634±0.026	0.577±0.015	0.544±0.010	0.953±0.025	0.200±0.046

Extensive experiments demonstrate a promising false positive suppression in both retrospective and prospective validation. EndoBoost was validated and compared to other competitors on the proposed dataset. We first evaluated the performance of different AD models when only TPs were accessible during training. EndoBoost achieved the highest AP and AUC among all the AD models (Table). Data-efficiency experiments were conducted to explore how to make the most use of available FPs during training. EndoBoost reached the equivalent performance (AP: 0.965, AUC: 0.966) with the pervious fully supervised method using only 10% FPs. For robustness to unseen classes of false positives, EndoBoost outperformed others with the highest AP (0.781) and AUC (0.974). In the prospective study, we took three colonoscopic video clips with a total length of about 1 hour as the real-world deployment test set. With the assistance of EndoBoost, FPs were suppressed successfully during the withdrawal of the colonoscopy.

Conclusion

In this work, we present a practical solution of dataset and methodology for reducing FPs during AI-assisted colonoscopy. The FPPD-13 dataset and proposed EndoBoost demonstrate their effectiveness in supressing FPs during real-world colonoscopy. For future work, multi-center clinical trials using EndoBoost are being carried out.

Introduction

Duodenal stump fistula (DSF) represents a significant complication that can arise following gastrectomy, with a prevalence ranging from 1.0% to 2.5%. This condition is characterised by a high mortality risk (12.5% to 28%) and a high morbidity rate (75%). In instances where conservative management has proven ineffective, percutaneous transhepatic biliary drainage (PTBD) emerges as a valuable intervention. This procedure involves the aspiration of bile, thereby reducing duodenal pressure and diminishing fistula output. However, it is important to note that PTBD does necessitate a prolonged healing period and frequently requires subsequent treatments, such as percutaneous or endoscopic injection of glue. The prolonged hospitalization is also to be considered in these patients, in which the resolution of the fistula generally requires a period of between 60 and 240 days.
The objective of this study was to ascertain the viability and effectiveness of a pioneering technique involving percutaneous DFS embolization with ethylene vinyl alcohol copolymer (EVOH) in combination with an occlusion balloon, utilised in the management of DSF following gastrectomy for malignant or benign indications.

Aims & Methods

The present study encompassed patients with a diagnosis of DSF, as determined by the presence of duodenal juice in the surgical drainage or its leakage through the abdominal wall. This diagnosis was confirmed through surgical approach and/or a computerised tomography (CT) scan. A retrospective analysis was conducted on 15 consecutive patients who underwent PTB-A embolization with Ethylene-Vinyl Alcohol Copolymer (EVOH) as a treatment for DSF, following the failure of medical, surgical, or endoscopic interventions.
An analysis was conducted of clinical and technical success, morbidity and mortality.

Results

The population under scrutiny comprised 10 female and 5 male subjects. Furthermore, it is noteworthy that 74% of patients underwent surgery for a malignant lesion. In the present study, a total of 13 patients underwent subtotal gastrectomy. In all cases, technical success was achieved. A positive outcome was achieved in 11 out of 15 patients following a single treatment. In 4 cases, patients required further treatment to achieve complete fistula healing. In the course of treatment, it was observed that a single patient required four treatment sessions to achieve complete healing. No procedure-related complications or mortalities were recorded. No recurrence of the fistula was observed in the population under study. Radiological follow-up was conducted at one or three months following the procedure for a total of 11 patients. 2 patients expired prior to the scheduled follow-up due to unrelated causes, while 2 patients failed to attend the control appointment.

Conclusion

PTB-A embolization with EVOH of duodenal stump fistula seems to be an effective treatment for DSF, with prompt recovery, no mortality and short hospitalization after the procedure.

References

1. Orsenigo E,et al. Duodenal stump fistula after gastric surgery for malignancies: a retrospective analysis of risk factors in a single centre experience. Gastric Cancer. 2014 Oct;17(4):733-44. doi: 10.1007/s10120-013-0327-x.

2. Paik HJ, et al. Duodenal stump fistula after gastrectomy for gastric cancer: risk factors, prevention, and management. Ann Surg Treat Res. 2016 Mar;90(3):157-63. doi: 10.4174/astr.2016.90.3.157.

3. Gu L, et al. Risk Factors for Duodenal Stump Leakage after Laparoscopic Gastrectomy for Gastric Cancer. J Gastric Cancer. 2020 Mar;20(1):81-94. doi: 10.5230/jgc.2020.20.e4.

4. Naito R, et al. Retrograde drainage for duodenal stump leakage using ileal decompression tube guided by double-balloon endoscopy: a novel case report. Surg Case Rep. 2024 Feb 18;10(1):44. doi: 10.1186/s40792-024-01842-9.

5. Aurello P, et al. Management of duodenal stump fistula after gastrectomy for gastric cancer: Systematic review. World J Gastroenterol. 2015 Jun 28;21(24):7571-6. doi: 10.3748/wjg.v21.i24.7571.

6. Zizzo M, et al. Management of duodenal stump fistula after gastrectomy for malignant disease: a systematic review of the literature. BMC Surg. 2019 May 28;19(1):55. doi: 10.1186/s12893-019-0520-x.

7. Cozzaglio L, et al. Percutaneous transhepatic biliary drainage and occlusion balloon in the management of duodenal stump fistula. J Gastrointest Surg. 2011 Nov;15(11):1977-81. doi: 10.1007/s11605-011-1668-6.

Introduction

Anemia is a common and often underdiagnosed condition in the elderly population. Digestive endoscopy plays a pivotal role in the etiological workup, particularly to rule out serious underlying causes such as malignancies or peptic lesions. However, the diagnostic yield of such procedures in routine clinical practice remains variable and underreported, especially in resource-limited settings.

Aims & Methods

To assess the diagnostic yield of digestive endoscopy in the investigation of anemia in elderly patients, with a particular focus on iron deficiency anemia (IDA) and vitamin B12 deficiency, and to identify specific endoscopic findings associated with these etiologies.
We conducted a retrospective descriptive study over a 6-month period. The study included all patients aged 65 years and older who underwent esophagogastroduodenoscopy (EGD) and/or colonoscopy as part of the diagnostic evaluation for anemia. Data collected included demographic information, clinical symptoms, laboratory parameters (including hemoglobin, ferritin, vitamin B12 levels), endoscopic findings, and histopathological results when available.

Results

A total of 252 patients were included in the analysis. Among them, 44 patients (17.5%) with a mean age of 71 years [68-82], had confirmed IDA, and six patients (2.4%) presented with vitamin B12 deficiency anemia, associated in all cases with histologically confirmed fundic atrophy.
In univariate analysis, IDA was statistically correlated with the presence of peptic esophagitis (p=0.04), gastric neoplasia (p=0.001), erosive gastropathy (p=0.02), and Helicobacter pylori gastritis (p=0.04). It was also weakly correlated with the presence of colorectal cancer (p=0.05).
Colonic angiodysplasias and colonic polyps were not associated with IDA in this cohort (p=0.1 and p=0.4, respectively).

Conclusion

Digestive endoscopy, particularly EGD, remains a cornerstone in the diagnostic algorithm of anemia in the elderly. It enables the identification of a wide range of underlying pathologies, from inflammatory lesions to malignancies, and guides appropriate therapeutic interventions. Early endoscopic evaluation should be encouraged in this population to prevent diagnostic delays and improve outcomes.

Introduction

During the COVID-19 pandemic the British Society of Gastroenterology (BSG) introduced interim guidelines supporting a non-biopsy pathway for the diagnosis of coeliac disease. These guidelines reflect the current recommendations of the American Gastroenterological Association (AGA). According to these guidelines, symptomatic or high risk adults with anti-Tissue transglutaminase (TTG) IgA titres ≥10× the upper limit of normal (ULN) and a positive endomysial antibody (EMA) on a repeat sample can be diagnosed without endoscopy and referred directly to a specialist coeliac clinic. Patients who do not meet these criteria should be referred for a gastroscopy (OGD) with biopsy for the confirmation of coeliac, prior to starting a gluten free diet.

Aims & Methods

To assess whether general practitioners (GPs) in the community appropriately referred patients with suspected coeliac disease in line with the AGA and BSG interim non-biopsy diagnostic criteria.
A retrospective review was conducted of all new patients referred to the Coeliac clinic in Galway university hospital between January 2023 and December 2024. Data regarding TTG level at diagnosis, EMA result, and compliance with the diagnostic pathway outlined above was collected for each new referral. This data was collected via Evolve - the hospital's electronic based patient record system.

Results

• There were 119 “new” referrals to our Coeliac Service between January 2023 and December 2024. Of these, 44 cases were known coeliac who were referred by primary care for re-engagement with the clinic, 18 were referred from secondary or tertiary care including GI surgery, Dermatology, Paediatrics, etc. 4 coincidental diagnoses (i.e. OGD performed for indications other than coeliac disease), and 5 outliers (i.e. with incomplete data or incorrectly referred to coeliac clinic) leaving 48 new coeliac cases referred from primary care.
• 18 of these referrals met the non-biopsy criteria for diagnosis (TTG ≥100 + positive EMA)
  • Within this cohort 66% (n=12) were incorrectly referred directly for an OGD which may have delayed the diagnosis of coeliac disease while the remaining 33% (n=6) were correctly referred for direct review at the coeliac clinic.
• The remaining 29 patients all had TTG values less that 10x ULN. 48% (n=14) of these patients were incorrectly referred to clinic prior to endoscopy and of greater concern, 45% (n=13) were recommended by their primary care physician to start a gluten free diet prior to any review or endoscopic procedure.
• Overall, only 44% (n=21) of referrals were compliant with the AGA/BSG guidance.

Conclusion

There is a notable gap in adherence to AGA and BSG non-biopsy coeliac diagnostic guidance in community settings. Half of patients eligible for a non-biopsy diagnosis underwent unnecessary endoscopy, and the majority of ineligible patients were commenced on a gluten free diet prior to, or without, referral for endoscopy. Further GP education is warranted to align referral practices with evidence-based pathways. Dedicated streamlined referral pathways for coeliac disease should ensure a timely diagnosis without mandatory endoscopy in those fulfilling the criteria for a non-biopsy diagnosis and facilitate a timely endoscopy prior to gluten elimination in those who require histological diagnosis.

References

Husby, S., Murray, J.A. and Katzka, D.A. (2019) ‘AGA clinical practice update on diagnosis and monitoring of celiac disease—changing utility of serology and histologic measures: Expert review’, Gastroenterology, 156(4), pp. 885–889. doi:10.1053/j.gastro.2018.12.010.
Tashtoush, L.B. et al. (2021) ‘Letter: The BSG covid‐19 interim coeliac disease guidance no‐biopsy approach is safe in adults’, Alimentary Pharmacology & Therapeutics, 54(8), pp. 1090–1092. doi:10.1111/apt.16553.

Disclosure

No conflict of interest

Clinical Case Summary

A 64-year-old woman with a prior diagnosis of type I achalasia underwent Heller myotomy with Dor fundoplication in 2015, which resulted in the resolution of dysphagia and regurgitation. However, she kept experiencing chest pain, which partially improved with nitro-glycerine. In 2018, due to worsening pain, she underwent high-resolution oesophageal manometry (HROM), which demonstrated absent peristalsis without oesophageal pressurization. Also, upper endoscopy was unremarkable, and timed barium swallow (TBS) revealed some tertiary contractions. By 2019, the patient received botulinum toxin injections with partial improvement. Another TBS performed in 2023 showed tertiary contractions in the distal third of the oesophagus, contributing to mild oesophageal emptying delay but without stasis. In 2024, repeat HROM revealed pan-oesophageal pressurization, except in the distal-most centimetres of the oesophagus. During rapid drink challenge, the patient reported pain. Given these findings, she was proposed for peroral endoscopic myotomy (POEM) to extend the myotomy proximally. In August 2024, she underwent a complete distal oesophageal myotomy, including the lower oesophageal sphincter and cardia. Endoscopic assessment in November showed no evidence of stasis, esophagitis, or resistance at the cardia. Latest clinical evaluation in March 2025 confirmed complete resolution of chest pain.
Conclusion: Non-cardiac chest pain is a less common yet challenging symptom to manage in achalasia. Its persistence after disease-directed treatment has been described in the literature, with its primary risk factor being its presence preoperatively¹. However, comparative data on different therapeutic approaches for achalasia-related chest pain remain limited. To our knowledge, only two similar cases have been reported in which pain persisted after Heller myotomy but improved following POEM, probably linked to the inadequate or incomplete myotomy of the oesophageal muscle layer^2,3.

References

1. Olvera-Prado H, et al. Predictive factors associated with the persistence of chest pain in post-laparoscopic myotomy and fundoplication in patients with achalasia. Front Med (Lausanne). 2022 Oct 14;9:941581.
2. Miftahussurur M, Tandan M, Makmun D, Nabi Z. Peroral Endoscopic Myotomy in a Patient with Achalasia Cardia with Prior Heller's Myotomy. Case Rep Gastroenterol. 2020 Jan 22;14(1):48-55.
3. Sato C, et al. Salvage therapy for postoperative residual chest pain due to esophageal achalasia. SAGES 2017 Annual Meeting in Houston [Abstract], https://www.sages.org/meetings/annual-meeting/abstracts-archive/salvage-therapy-for-postoperative-residual-chest-pain-due-to-esophageal-achalasia/

Introduction

Oesophageal food bolus impaction [OFBI] is a common presentation to emergency room [ER] and often requires endoscopic intervention. We aimed to describe the incidence of OFBI in Canterbury, New Zealand and examine factors predicting the need for endoscopic intervention and complications in the population-based cohort.

Aims & Methods

All ER presentations of OFBI in Canterbury between October 2018 and August 2023 were included. Population data for the Canterbury population was obtained from Statistics NZ. Ethnicity was defined according to hospital records based on patients’ self-identification. Endoscopic intervention was defined as the presence of bolus during the endoscopy requiring any endoscopic manoeuvre for clearance. Complications were defined as unsuccessful attempts requiring a repeat procedure or procedure-related injuries.

	Total (n = 187)
Age (years)	Mean 55 Median 54.9
Gender - Male (%) : Female (%)	113 (60.4) : 74 (39.6)
Ethnicity - European (%) : Non-European (%)	163 (87.2) : 24 (12.8)
Cause of oesophageal impaction (%)	EoE 42 (22.5) Stricture 43 (23)£ Other 15 (8)* Idiopathic/unknown 87 (46.5)¥
Food type (%)	Meat 141 (86.5) Non-meat 46 (24.5)
Spontaneous clearance of food bolus clinically, without endoscopy performed (inpatient or outpatient) (%)	42 (22.5)
Spontaneous clearance of food bolus diagnosed on endoscopy as an inpatient (%)	37 (19.8)
Inpatient endoscopic intervention required (%)	92 (49.2)
Total complications (%)	8 (4.3)

£ cause of impaction from Schatzi ring or benign esophageal stricture
* cause of impaction from severe reflux oesophagitis (Los Angeles Grade C or D), esophageal dysmotility, malignant stricture, or esophageal candidiasis
¥ no cause for impaction found; either no endoscopy performed as an inpatient or outpatient or no pathology found on endoscopy

Results

There were 187 ER presentations of OFBI between October 2018 and August 2023. Clinical characteristics of the population-based cohort are presented in Table 1.
The average annual incidence of ER presentations of OFBI in Canterbury region between 2019 – 2022 was 5.82 per 100,000 population (95% CI 3.96-7.68/100,000). The incidence of ER presentations of OFBI in Europeans and non-Europeans over the same period was 8 per 100,000 European population (95% CI 5.27-10.73/100,000) and 1.94 per 100,000 non-European population (95% CI 0.15-3.73/100,000).
A total of 92 cases (49%) required endoscopic intervention. Factors predicting the need for endoscopic intervention were meat bolus [p= 0.01], stricture [p<0.01], and early endoscopy performed <12hrs [p<0.01]. There were only 8 complications. Predictors with a trend associated with complications were after-hours presentation [p=0.06] and early endoscopy performed <6hrs [p=0.06].

Conclusion

Our population-based cohort showed a significantly higher incidence of ER presentations of OFBI in Europeans than in non-European ethnic groups. Factors predicting the need for endoscopic intervention were meat bolus, stricture and early endoscopy. After-hours presentation and early endoscopy <6hrs showed a trend towards a higher risk of complications. The results suggest that a delayed approach may be associated with a higher chance of spontaneous clearance and a lower risk of complications, although further study is needed.

Disclosure

Not applicable

Introduction

Hepatitis C virus (HCV) infection continues to pose a significant public health challenge, with demographic trends shaped by migration patterns and shifting risk profiles. Gaining insight into these dynamics is essential for optimising treatment approaches and informing effective resource allocation.

Aims & Methods

This retrospective cohort study aimed to analyze demographic patterns, HCV genotype distribution, and cirrhosis prevalence among patients treated for hepatitis C at St. Luke’s Hospital, Ireland, between 2016 and 2024. Statistical analyses included descriptive metrics, Chi-Square tests, one-way ANOVA, and multinomial logistic regression, performed using SPSS.

Results

A total of 202 patients received treatment during the study period, with 67% identifying as male and a median age of 46 years. The majority were born in Ireland (45.5%), Eastern Europe (16.8%), or other European countries (15.3%). No significant differences were observed in age at presentation across years (p = 0.449) or by country of birth (p = 0.367). Gender distribution remained stable over time (p = 0.373) and across birth countries (p = 0.107). Genotype distribution, however, varied significantly by country of birth (p < 0.001): Genotype 1b was more prevalent among patients from Eastern and other European countries, while Genotypes 1a and 3 were more common among Irish-born individuals. Genotypes 3 and 4 were seen more frequently in patients from non-European regions. Cirrhosis prevalence showed no significant association with genotype (p = 0.071) or country of birth (p = 0.064). Although country of origin did not change significantly over time (p = 0.224), descriptive trends indicated an increase in non-Irish-born patients.

Conclusion

This study highlights consistent demographic trends in HCV presentations over time, alongside distinct regional variations in genotype distribution. Continued monitoring of these patterns is essential for guiding service planning and delivering targeted, patient-centered care in a changing population landscape.