Introduction

Preoperative biliary drainage (PBD) is commonly used in patients with malignant distal biliary obstruction (MDBO) to maintain performance status, prevent cholangitis and allow subsequent surgical or neoadjuvant treatment. Endoscopic retrograde cholangiopancreatography (ERCP) is the first-line approach, but in cases of failure, percutaneous transhepatic biliary drainage (PTBD) or endoscopic ultrasound-guided biliary drainage (EUS-BD) are considered. While EUS-BD has shown favourable outcomes compared to PTBD in the palliative setting, evidence comparing these modalities in the preoperative setting is limited.

Aims & Methods

The aim of this study was to compare the efficacy, safety, and surgical outcomes of PTBD and EUS-BD in patients with MDBO after failed ERCP. This retrospective multicenter study included patients who underwent PTBD or EUS-BD followed by pancreaticoduodenectomy (PD) for periampullary cancer at 15 referral centers in Japan between January 2012 and December 2021. Only patients who had failed or were not amenable to ERCP were included. The primary outcome was surgery-related adverse events (AEs), while secondary outcomes included drainage efficacy, recurrence patterns, disease-free survival (DFS), and overall survival (OS). Propensity score matching (PSM) was used to adjust for baseline differences.

Results

In total, 2350 patients received PBD before PD. Of the 79 patients in whom ERCP failed, 65 underwent PTBD and 14 underwent EUS-BD. After PSM, 13 matched pairs were analyzed. Technical and clinical success rates were comparable between groups. However, the EUS-BD group had a significantly higher internalization success rate (100% vs. 46%, P=0.005) and fewer drainage sessions required (median: 1 vs. 2, P=0.015). The EUS-BD group also had a significantly shorter hospital stay for drainage (11 vs. 17 days, P=0.042). Rates of drainage-related AEs tended to be lower in the EUS-BD group, although not statistically significant. Surgery-related outcomes, including operative time, intraoperative blood loss, R0 resection rate, postoperative hospital stay, and surgery-related AEs, were not significantly different between groups. No cases of needle tract seeding were observed. Median DFS and OS were comparable between groups (DFS: 14.2 vs. 16.8 months, P=0.22; OS: 17.9 vs. 27.9 months, P=0.167).

Conclusion

EUS-BD showed comparable surgical outcomes and long-term oncological efficacy to PTBD, while offering superior internalization success, fewer interventions, and a shorter preoperative hospital stay. These advantages make EUS-BD a favorable alternative to PTBD in the preoperative management of MDBO after failed ERCP, particularly in patients scheduled for neoadjuvant therapy.

Disclosure

Kitano M has received grants from Boston Scientific, Zeon Medical Inc., and Medicos Hirata Inc. Takenaka M, Shiomi H, Kitagawa K, Shintani S, Maruyama H, Sagami R, Ikeura T, Ogura T, Ishida Y, Mandai K, Sugimori S, Imamura Y, Masuda A, Ikezawa K,Shimizu A, Nakai A, Nagai M and Nakano R have no conflicts of interest or financial ties to disclose.

Introduction

Colorectal anastomotic dehiscence (CAD) is one of the most severe postoperative complications in colorectal surgery, significantly impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative recording of the anastomosis for CAD prediction.

Aims & Methods

A convolutional neural network (CNN) was trained using a dataset of annotated frames from colorectal surgery videos across three international high-volume centers: IPO Lisboa, Hospital das Clínicas de Ribeirão Preto, São Paulo, Brazil and Royal Liverpool University Hospital. The dataset included a total of 5,356 annotated frames from 25 patients, 2,007 frames classified as CAD-positive and 3,349 as CAD-negative. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. Performance was evaluated using sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key regions influencing predictions.

Results

The best-performing model achieved an accuracy of 99.55%, AUROC of 99.60%, sensitivity of 99.21%, specificity of 100%, PPV of 100%, and NPV of 98.94%. The model reliably identified CAD-positive frames and provided visual explanations through heatmaps.

Conclusion

To our knowledge, this is the first AI model developed to predict CAD using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAD before it occurs, marking a paradigm shift in colorectal surgery.

Introduction

Bowel preparation quality is a key determinant of colonoscopy effectiveness and adenoma detection^1,2. Manual evaluation of free-text colonoscopy reports is labor-intensive and limits quality monitoring³. Developing a natural language processing (NLP) application for measuring colonoscopy quality demonstrates the potential to automate this process by extracting key quality indicators⁴.

Aims & Methods

We aimed to develop and validate a NLP approach to automatically classify bowel cleanliness and to comprehensively structure colonoscopy reports by extracting procedural and pathological variables. A total of 11,374 reports from our institutional endoscopy unit were analyzed. An annotated dataset of 1,018 reports labeled as “good,” “intermediate,” or “poor” preparation was used to train a TF-IDF–based logistic regression classifier. Cross-validation and test performance were evaluated using accuracy, precision, recall, and F1-scores, and the model was applied to the full dataset. Additional variables (cecal intubation, polyp presence, number, size, localization, polypectomy method, and hemostasis application) were extracted using rule-based NLP heuristics. Adenoma detection rate (ADR) was calculated in a predefined subset (January 2023–July 2025) with complete pathology data, and multivariable logistic regression identified independent predictors.

Results

The NLP classifier achieved a cross-validated accuracy of 92%. Precision and recall were highest for “good” preparation (0.98 and 0.99) and acceptable for “intermediate” (0.85 and 0.82) and “poor” (0.85 and 0.87). Application to the full cohort yielded 5,787 (50.9%) good, 2,176 (19.1%) intermediate, and 3,411 (30.0%) poor preparations. Leveraging these structured data, ADR analysis in the subset of 5,420 patients showed an overall rate of 20.4%. Multivariable analysis demonstrated that ADR was independently associated with older age (OR 1.05 per year, 95% CI 1.05–1.06, p<0.001), male sex (OR 1.74, 95% CI 1.51–2.01, p<0.001), adequate bowel preparation (OR 1.46, 95% CI 1.21–1.75, p<0.001), cecal intubation (OR 1.76, 95% CI 1.43–2.16, p<0.001), and procedures performed by specialists compared with trainees (24.0% vs 20.3%; OR 1.25, 95% CI 1.05–1.47, p=0.010).

Variable	Value / N	Precision / Recall	ADR%	Multivariable OR (95% CI)	p-value
Cohort distribution (n=11,374)	Good: 5,787 (50.9%)	0.98 / 0.99	–	–	–
	Intermediate: 2,176 (19.1%)	0.85 / 0.82	–	–	–
	Poor: 3,411 (30.0%)	0.85 / 0.87	–	–	–
ADR analysis subset (n=5,420)
Age (per year)	–	–	–	1.05 (1.05–1.06)	<0.001
Male sex (ref: female)	2,661 vs 2,759	–	23.8 vs 17.1	1.74 (1.51–2.01)	<0.001
Bowel preparation (good/intermediate vs poor)	3,891 vs 1,529	–	22.1 vs 16.0	1.46 (1.21–1.75)	<0.001
Cecal intubation (yes vs no)	4,209 vs 1,211	–	21.0 vs 16.5*	1.76 (1.43–2.16)	<0.001
Operator (specialist vs trainee)	1,045 vs 4,149	–	24.0 vs 20.3	1.25 (1.05–1.47)	0.010

*ADR% for cecal intubation groups calculated from subset.

Conclusion

This large-scale real-world analysis demonstrates the feasibility of NLP-based automated classification of bowel preparation quality and its direct utility in generating structured colonoscopy datasets for quality monitoring. By integrating bowel cleanliness with other performance indicators (age, sex, cecal intubation, operator expertise), our framework not only achieved high classification accuracy but also provided clinically relevant benchmarks for ADR, supporting targeted quality improvement in endoscopy units.

References

1. Clark BT, Protiva P, Nagar A, et al. Quantification of Adequate Bowel Preparation for Screening or Surveillance Colonoscopy in Men. Gastroenterology. 2016;150(2):396-e15. doi:10.1053/j.gastro.2015.09.041
2. Clark BT, Rustagi T, Laine L. What level of bowel prep quality requires early repeat colonoscopy: systematic review and meta-analysis of the impact of preparation quality on adenoma detection rate. Am J Gastroenterol. 2014;109(11):1714-1724. doi:10.1038/ajg.2014.232
3. Raju GS, Lum PJ, Slack RS, et al. Natural language processing as an alternative to manual reporting of colonoscopy quality metrics. Gastrointest Endosc. 2015;82(3):512-519. doi:10.1016/j.gie.2015.01.049
4. Harkema H, Chapman WW, Saul M, Dellon ES, Schoen RE, Mehrotra A. Developing a natural language processing application for measuring the quality of colonoscopy procedures. J Am Med Inform Assoc. 2011;18 Suppl 1(Suppl 1):i150-i156. doi:10.1136/amiajnl-2011-000431

Introduction

We determined the impact of an increased two-stool FIT cutoff on colonoscopy positivity and relative sensitivity and specificity in the randomised controlled screening trial SCREESCO conducted in Sweden.

Aims & Methods

We performed a cross-sectional analysis of participants in the FIT arm that performed FIT between March 2014 and March 2020 within the study registered with ClinicalTrials.gov, NCT02078804, who had a fecal hemoglobin concentration of at least 10 μg/g in at least one of two stool samples and who underwent a colonoscopy (n=3841). For each increase in cutoff, we computed the positive predictive value (PPV), numbers needed to scope (NNS), sensitivity and specificity for finding colorectal cancer (CRC) and advanced neoplasia (AN; advanced adenoma or CRC) relative to cutoff 10 μg/g.

Results

Number of colonoscopies, number with finding of advanced neoplasia (AN), positive predictive value (PPV), numbers needed to scope (NNS), relative sensitivity and relative specificity by FIT-cutoff (maximum of two stool samples).
Cutoff	N colonoscopies (%)	N with advanced neoplasia	PPV	NNS	relative sensitivity	95% CI	relative specificity	95% CI
(μg/g)
10	3841 (100)	882	23	4.4	100		0
20	2319 (60)	667	29	3.5	76	74-77	44	44-46
40	1428 (37)	473	33	3.0	54	52-55	68	67-69
60	1059 (28)	384	36	2.8	44	42-45	77	76-78
80	861 (22)	331	38	2.6	38	36-39	82	81-83
120	653 (17)	272	42	2.4	31	29-32	87	87-88
160	541 (14)	240	44	2.3	27	26-29	90	89-90

The PPV for advanced neoplasia (colorectal cancer, or adenoma with high grade dysplasia or size >10mm or villous component) increased from 23.0% (95% CI: 22.3-23.6%) at cutoff 10 μg/g to 28.8% (95% CI: 27.8-29.7%) and 33.1% (95% CI: 31.9-34.4%) at cutoffs 20 and 40 μg/g respectively while the NNS to find a CRC (not shown in the table) correspondingly decreased from 41 to 27 and 19. The PPV for advanced neoplasia was higher in men than women at each cutoff, e.g. 31.5% (95% CI: 30.1-32.8%) in men and 25.6% (95% CI: 24.3-27.0%) in women at 20 μg/g. The relative sensitivity and relative specificity were similar in men and women at each cutoff.

The table shows the results for for advanced neoplasia with the number of colonoscopies and number of findings with AN for each cutoff. Furthermore for each cutoff the positive predictive value (PPV) and numbers needed to sccope to find one AN is given. The relative sensitivity and specificity (each with 95% CI given) are calculated relative to the cutoff 10 μg/g.

Conclusion

The risk of advanced adenoma and colorectal cancer increased with increasing fecal hemoglobin concentration in both men and women, and a low cutoff around 20 to 40 μg/g for two-stool FIT allows detection and removal of many advanced adenomas and colorectal cancers. The findings suggest that a higher cutoff in women than in men could lead to comparable colonoscopy positivity for advanced adenomas and cancer.

References

Brenner H, Werner S. Selecting a Cut-off for Colorectal Cancer Screening With a Fecal Immunochemical Test. Clin Transl Gastroenterol 2017; 8: e111.
Brenner H, Haug U, Hundt S. Sex differences in performance of fecal occult blood testing. Official journal of the American College of Gastroenterology| ACG 2010; 105: 2457-64.
Meulen MPV, Kapidzic A, Leerdam MEV, et al. Do Men and Women Need to Be Screened Differently with Fecal Immunochemical Testing? A Cost-Effectiveness Analysis. Cancer Epidemiol Biomarkers Prev 2017; 26: 1328-36.
Blom J, Löwbeer C, Elfström KM, Sventelius M, Öhman D, Saraste D, Törnberg S. Gender-specific cut-offs in colorectal cancer screening with FIT: Increased compliance and equal positivity rate. Journal of medical screening 2019; 26: 92-7.
Forsberg A, Westerberg M, Metcalfe C, et al. Once-only colonoscopy or two rounds of faecal immunochemical testing 2 years apart for colorectal cancer screening (SCREESCO): preliminary report of a randomised controlled trial. Lancet Gastroenterol Hepatol 2022; 7: 513-21.
Stromberg U, Bonander C, Westerberg M, et al. Colorectal cancer screening with fecal immunochemical testing or primary colonoscopy: An analysis of health equity based on a randomised trial. EClinicalMedicine 2022; 47: 101398.

Introduction

Colonoscopy is a widely accepted screening test for detecting colorectal cancer. Computer-aided detection (CADe) based on artificial intelligence (AI) may be the way forward to improve its quality. As AI becomes a common upgrade in endoscopic equipment, an increasing number of young endoscopists are trained in an AI environment. However, how AI will impact trainees' future endoscopy outcomes remains unclear.

Aims & Methods

The study aimed to evaluate quality indicators in the first 1000 colonoscopies performed by newly trained endoscopists, comparing those trained in an AI environment to those trained in a non-AI environment. A study included 6,000 patients over 18 years old who underwent a colonoscopy for various reasons. The procedures were carried out by six young endoscopists, of which three were trained without AI and three with the assistance of the AI-powered Olympus Endo-Aid CADe system. The study retrospectively evaluated the first 1,000 procedures performed by each endoscopist after completing training. These procedures were performed without AI enhancement and relied entirely on the endoscopists' detection skills. Quality indicators were assessed in non-AI-training and AI-training groups. The morphology of detected polyps was assessed to determine the influence of AI during training on laterally spreading tumors (LST) detection.

Results

A total of 6,000 participants were included in the analysis. Withdrawal time (WT) was longer in the AI-training group (8 vs 9 min, p<0.05). Adenoma detection rate (ADR; 30.3 vs. 35.5%, p<0.05), advanced adenoma detection rate (AADR; 4.6 vs. 5.1%, p<0.05), and adenoma per colonoscopy score (APC; 0.73 vs. 0.75, p<0.05) were higher in the AI-training group. AI-assisted endoscopy training significantly improved LST-NG detection (p<0.05) for lesions smaller than 20mm.

	non-AI-training	AI-training	p-value
WT, min	8 (5-15)	9 (6-16)	<0.05
ADR, %	30.3	35.5	<0.05
AADR, %	4.6	5.1	<0.05
APC	0.73	0.75	<0.05

Conclusion

Implementing CADe during endoscopy training can positively impact quality indicators in the first 1,000 cases. After AI-enhanced training, the detection of LST-NG may improve. The potential of artificial intelligence in endoscopy training requires further investigation through prospective randomized controlled trials.

References

1. Kaminski MF et al. N Engl J Med. 2010 May 13;362(19):1795-803. doi: 10.1056/NEJMoa0907667. PMID: 20463339.
2. Repici A et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology. 2020 Aug;159(2):512-520.e7. doi: 10.1053/j.gastro.2020.04.062. Epub 2020 May 1. PMID: 32371116.
3. Vilmann AS et al. Computerized feedback during colonoscopy training leads to improved performance: a randomized trial. Gastrointest Endosc. 2018 Nov;88(5):869-876. doi: 10.1016/j.gie.2018.07.008. Epub 2018 Jul 19. PMID: 30031803.
4. Kaminski MF et al. Leadership training to improve adenoma detection rate in screening colonoscopy: a randomised trial. Gut. 2016 Apr;65(4):616-24. doi: 10.1136/gutjnl-2014-307503. Epub 2015 Feb 10. PMID: 25670810; PMCID: PMC4819605.
5. Forbes N et al. Association Between Endoscopist Annual Procedure Volume and Colonoscopy Quality: Systematic Review and Meta-analysis. Clin Gastroenterol Hepatol. 2020 Sep;18(10):2192-2208.e12. doi: 10.1016/j.cgh.2020.03.046. Epub 2020 Mar 30. PMID: 32240836.