Introduction

Stent placement by endoscopic retrograde cholangiopancreatography (ERCP) is one of the preferred methods for biliary drainage in unresectable malignant biliary obstruction. Nevertheless, clinical success of palliative drainage is not easy to predict, especially at the time of ERCP.

Aims & Methods

We conducted a multicentre retrospective cohort study in 3 centres in Portugal, involving patients with unresectable malignant biliary obstruction (UMBO) submitted to palliative ERCP-guided biliary stenting between 2015 and 2022. This study aimed to evaluate clinical success of biliary drainage in our population, as well as to evaluate the performance of two recently developed and internally validated risk scores for predicting successful biliary drainage after ERCP-guided endobiliary stenting in UMBO, created by the group of Pausawasdi N. et al. This group developed a first score for predicting early clinical success of biliary drainage (decrease ≥50% in total bilirubin (TB) levels within 2 weeks after stenting), using as variables the presence/absence of extrahepatic biliary obstruction, peritoneal carcinomatosis, the type of biliary stent (plastic or metallic) and pre-endoscopic alkaline phosphatase level. The second score was developed to predict complete clinical success of biliary drainage (normalization of TB levels within 6 weeks after stenting) including pre-endoscopic TB levels, presence/absence of extrahepatic biliary obstruction and type of stent as variables. We included 217 patients for this study. However, due to the limitations of a retrospective analysis, we could not evaluate the performance of these scores for all the patients of our cohort. Statistical analysis was performed using SPSS v.29.

Results

In our cohort, a decrease in total bilirubin (TB) levels ≥50% within 2 weeks after biliary stenting was reached in 81.9%(N=113) of the patients of a subpopulation of 138 patients in which these TB levels were available. TB normalization in 6 weeks after stenting occurred in 55%(N=72) of the cases from a subpopulation of 131 patients in which this TB level was measured. In our population, the predictive scores for early and complete clinical success had an AUROC of 0.597 (95% CI, 0.471-0.723; p = 0.13) and of 0.737 (95% CI, 0.650-0.825; p <0.001), respectively.

Conclusion

In our cohort, the predictive score for complete clinical success of biliary stenting in UMBO (at 6 weeks) had a good accuracy (AUROC 0.74), similar to the AUROC reported by this study group (AUROC 0.76 in the validation cohort). The main advantage of this score relies on the fact that it can be applied before ERCP, since its variables can all be determined pre-endoscopically or, at the most, by the time of ERCP (type of stent), possibly allowing the definition of a better strategy for the management and follow-up of these patients.

References

Pausawasdi, N., Termsinsuk, P., Charatcharoenwitthaya, P., Limsrivilai, J., & Kaosombatwattana, U. (2022). Development and validation of a risk score for predicting clinical success after endobiliary stenting for malignant biliary obstruction. PloS one, 17(8), e0272918. https://doi.org/10.1371/journal.pone.0272918

Introduction

Although Endoscopic Retrograde Cholangiopancreatography (ERCP) has played an important role in the diagnosis and treatment of biliary and pancreatic diseases since its inception, the gallbladder is still considered a “blind spot” or inaccessible area for ERCP.

Aims & Methods

This study was intended to evaluate the technical success rate, safety, and clinical application value of per-oral cholangioscopy-guided transpapillary cystic duct approach for Gb-NOEES, and to explore the feasibility of Natural Orifice Endoluminal Endoscopic Surgery (NOEES) in the diagnosis and treatment of gallbladder diseases.
Patients with gallbladder diseases who received Gb-NOEES treatment from January 2023 to November 2024 were retrospectively included in a single-center study. Inclusion criteria: Patients are preoperatively diagnosed with gallstones, gallstones combined with common bile duct stones, gallstones combined with intrahepatic stones, acute cholecystitis, and gallbladder polyps. Exclusion criteria: patients with asymptomatic gallstones, patients with gallbladder cancer, and patients at risk of gallbladder cancer. All procedures were performed by experts with ≥10 years of experience in digestive endoscopy, and postoperative follow-up period ranged from 2 to 26 months.

Results

A total of 100 patients were included (58 males and 42 females, with an average age of 47±15.1). The disease distribution is shown in Table 1. The technical success rate of Gb-NOEES was 99% (99/100), and the average operative time was 130±59 minutes. The complication rate was 4%: 3 cases of gallbladder perforation (1 case of successful conservative treatment, and 2 cases of conversion to laparoscopic surgery), and 1 case of postoperative bleeding (successful conservative treatment). No severe pancreatitis or death occurred. Treatment outcomes: Gallstone clearance rate was 98% (78/80), with the largest stone measuring 4.0 cm, and up to 52 stones removed in a single operation. Complete excision rate of gallbladder polyps was achieved in 100% (15/15), with long diameter of polyps ranging from 4 mm to 15 mm, and up to 8 polyps excised in a single operation. Drainage success rate for acute cholecystitis was 100% (4/4). One case of early-stage gallbladder cancer was incidentally detected. During the follow-up period, the recurrence rate of stones was 2.5% (2/80), and there was no recurrence of polyps.

Conclusion

Gb-NOEES demonstrated favorable safety profile (complication rate was 4%) and high efficacy (overall success rate was 98%) in the diagnosis and treatment of gallbladder diseases. This technique has advantages of both lesion removal and organ preservation, offering a new minimally-invasive treatment option for gallbladder diseases. However, its clinical application value requires further validation through multi-center studies.

Table 1. Disease Distribution of Patients

Disclosure

There is no conflict of interest.

Introduction

Colon Capsule Endoscopy (CCE) offers a non-invasive alternative to colonoscopy for lower gastrointestinal (GI) investigations. However, its adoption is limited by lengthy reading times, reader fatigue, and variable diagnostic accuracy. These factors are often influenced by bowel preparation quality and completion rates. Artificial intelligence (AI) has shown the potential to improve diagnostic accuracy of polyp detection and reduce reading times in capsule endoscopy.

Aims & Methods

Objective(s): The primary aim is to assess the diagnostic accuracy of Computer-Aided Detection (CADe) system (AiSPEED™) assisted CCE reading using full-video analysis in a real-world clinical setting. Secondary outcome was to assess a) non-inferiority compared to standard clinician reading in detecting polypoid lesions and b) mean reading time.
Methods: CESCAIL study is a multi-centre study of 14 UK centres recruited 720 participants between November 2021 and September 2024. Participants (prospectively and retrospectively enrolled ) included those ≥18 years referred for CCE under the urgent cancer pathway or for post-polypectomy surveillance. CCEs were performed using PillCam™ COLON 2 and analysed using AiSPEED™. CCE videos were evaluated by separate clinicians who provided standard readings, while AI-assisted reading included an AI-assisted pre-reader review and subsequent clinician validation.

Results

720 patients were enrolled, with 673 included in the final analysis. The capsule excretion rate before battery depletion was 77.1%, with adequate bowel preparation achieved at 78.1% (with standard) and 74.0% (with AI-assisted reading) (McNemar p=0.108). In the per-patient analysis, the diagnostic yield for detecting polyps was 63.6% (428/673) for standard reading and 70.6% (475/673) for AI-assisted reading, using the expert panel as the reference standard. These findings confirmed both non-inferiority (p<0.001) and superiority (p<0.001) of the AI-assisted reading. The diagnostic accuracy for detecting polyps requiring follow-up procedure (flexible sigmoidoscopy/colonoscopy) was 0.96 (95% CI: 0.95–0.98) for AI-assisted reading, compared to 0.91 (95% CI: 0.89–0.93) for standard reading (p<0.0001) (see Table 1). The mean reading time per video was 8.7 minutes for AI-assisted reading compared to 47.3 minutes for standard reading, representing a 5.4-fold reduction.

Conclusion

AI-assisted reading with AiSPEED™ offers the potential for greater accuracy in polyp detection and significantly reduced clinician reading times during CCE examination compared to standard reading methods.

References

1. Moen S, Vuik FER, Kuipers EJ, Spaander MCW. Artificial Intelligence in Colon Capsule Endoscopy-A Systematic Review. Diagnostics (Basel). 2022;12(8).
2. Mota J, Joao Almeida M, Mendes F, Martins M, Ribeiro T, Afonso J, et al. A Comprehensive Review of Artificial Intelligence and Colon Capsule Endoscopy: Opportunities and Challenges. Diagnostics (Basel). 2024;14(18).
3. Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, et al. AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. Lancet Digit Health. 2024;6(5):e345-e53.
4. Spada C, Hassan C, Galmiche JP, Neuhaus H, Dumonceau JM, Adler S, et al. Colon capsule endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy. 2012;44(5):527-36.
5. PillCam COLON 2 for investigation of the colon through direct visualisation [Internet]. NATIONAL INSTITUTE FOR HEALTH AND CARE EXCELLENCE. August 2024. Available from: https://www.nice.org.uk/guidance/gid-dg10083/documents/final-scope-2.

Disclosure

Hagen Wenzek serves as the CEO, and Elizabeth White is the Project Manager at Corporate Health International which owns the ​intellectual property of AiSPEED^TM