Introduction

Computer-aided detection (CADe) systems improve adenoma detection rate (ADR). However, there is some concern that the long-term use of CADe systems might lead to a decline in endoscopists’ independent detection skills, particularly their ability to detect lesions without assistance—a phenomenon referred to as "deskilling".

Aims & Methods

This study aims to evaluate the impact of CADe on the learning curve of endoscopists for ADR. This was a propensity score–matched (PSM), prospective, single-center, observational study conducted at a tertiary care hospital from January 2021 to December 2023. CADe systems were installed in half of the endoscopy units, and patients were equally distributed between the rooms. Patients in CADe-equipped rooms were examined using EndoBRAIN-EYE (Olympus Corp, Tokyo, Japan). Patients aged ≥ 20 years scheduled for colonoscopy were included, excluding those with polyposis, inflammatory bowel disease, known polyps, incomplete colonoscopy, emergency cases, previous colorectal surgery, and examination by novices. Endoscopists were classified as high-detectors (ADR ≥ 25%) or low-detectors (ADR < 25%) based on the ADR recorded before CADe implementation. The primary outcome was to evaluate the learning effect of CADe using cumulative summation (CUSUM) analysis based on ADR during both CADe and non-CADe procedures to assess skill acquisition and transfer. The CUSUM scores were calculated from the acceptable probability of failure and unacceptable probability of failure. Acceptable and unacceptable ADR were defined as 40% and 30% for high detectors, and 35% and 25% for low detectors, respectively. Performance was judged based on the boundary lines (h0 and h1): acceptable if the CUSUM plot fell below h0, unacceptable if it went above h1, and inconclusive requiring further observation if it stayed between these boundaries. The secondary outcomes included ADR, advanced adenoma detection rate (AADR), and sessile serrated lesion detection rate (SSLDR). The study received ethics approval (no.19H072) and complied with the Declaration of Helsinki.

Results

Out of 5,717 patients initially enrolled, 4,712 patients (2,356 in CADe group and 2,356 in non-CADe group) were analyzed after PSM for known factors (age, sex, indication, and bowel preparation). During CADe-assisted procedures, both high-detectors and low-detectors showed patterns below the acceptable performance line (h0), indicating improved adenoma detection performance with AI support. However, during non-CADe procedures, the patterns diverged significantly. For high-detectors, their CUSUM plots consistently fell below the acceptable performance line (h0) over time during non-CADe colonoscopies, indicating that they successfully acquired and maintained improved adenoma detection skills even without AI assistance. In contrast, the CUSUM plots of the low-detectors remained between the acceptable (h0) and unacceptable (h1) limits throughout the study period, showing no significant change in learning trajectory during non-CADe procedures. The CADe group had a significantly higher ADR (40.5% [95% CI: 38.5-42.5%]) compared to non-CADe group (32.4% [95% CI: 30.5-34.4%]; p < 0.001). SSLDR was also significantly higher in the CADe group (6.9% [95% CI: 5.9-8.0%] vs. 4.5% [95% CI: 3.7-5.4%]; p = 0.001), while AADR showed no significant difference (4.1% [95% CI: 3.4-5.0%] vs. 4.7% [95% CI: 3.9-5.6%]; p = 0.39).

Conclusion

The implementation of the CADe system did not result in deskilling regarding adenoma detection.

Disclosure

The conflict of interests were following: Shin-ei Kudo and Masashi Misawa received speaking honoraria from Olympus Corporation and have an ownership interest of the products of Cybernet Systems. Kensaku Mori received research grants from Cybernet Systems, Morita Mfg, Atom Medical Inc, and Asahi Intecc. Additionally, Kensaku Mori serves as a Technical Advisor for Sanyu Industry. Tetsuo Nemoto received a research grant from Olympus Corporation for other studies. Other authors have nothing to declare.

Introduction

Quality assessment is a priority in the field of gastroenterology. However, limited data are available from Greece regarding adherence to quality standards in gastrointestinal endoscopy.

Aims & Methods

This study aims at assessing the knowledge and compliance of Greek gastroenterologists with established quality standards for upper and lower digestive endoscopy, while exploring factors that may influence compliance.
​This prospective study recorded data on the quality of upper and lower digestive endoscopy performed in Greece from October 2024 to January 2025. All members of the Hellenic Society of Gastroenterology (n=668) were invited to participate via an electronic survey. The survey included a questionnaire designed specifically for this study, covering demographic and professional characteristics, as well as quality indicators for gastroscopy and colonoscopy.

Results

A total of 164 gastroenterologists participated (response rate 24.55%), of whom 107(65.24%) were male, and 102(62.2%) working in public or academic hospitals. The duration of gastroscopy was not recorded by 116(70.73%) participants, while 102(62.2%) systematically used photodocumentation. Most participants utilized the Prague and Los Angeles classifications 156(95.12%) and 159(96.95%) respectively. Additionally, 140(85.37%) followed the Seattle protocol, and 158(96.34%) conducted biopsies according to ESGE guidelines for precancerous gastric lesions. However, 83(50.61%) don’t use a registry for patients with Barrett’s esophagus. Complications were systematically recorded after gastroscopy by 103(62.8%) and after colonoscopy by 90(54.88%).
In colonoscopy, 149(90.85%) use the BBPS scale, and 158(96.34%) reported successful cecal intubation. Withdrawal times exceeded six minutes for 151(92.07%) participants. An adenoma detection rate of over 25% was achieved by 117(71.78%), while 103(62.8%) consistently used the Paris classification. Proper polypectomy techniques were employed by 111(67.68%), but 100(60.98%) recommended follow-up intervals shorter than guidelines suggest. Patient experience following gastroscopy and colonoscopy was not recorded by 126(76.83%) and 116(70.73%) participants, respectively. Overall, compliance with quality indicators for upper and lower digestive endoscopy was observed in 87(53.05%) and 75(45.73%) participants, respectively. Multivariate analysis revealed that 5-15 years of experience (p=0.05), the use of video recording (p=0.01) and use of high-resolution endoscopes (p<0.01) were associated with improved compliance with quality indicators of upper endoscopy. Whereas age above 55 (p<0.01), use of high-resolution endoscopes(p<0.01), use of video recording (p=0.02) and attendance of educational seminars relevant with quality in endoscopy (p=0.05) were associated with improved compliance with quality indicators of colonoscopy.

Conclusion

In this study, discrepancies were observed in the compliance of Greek endoscopists with endoscopic quality indicators, highlighting the need for further improvement. The systematic recording of these quality indicators is essential, underlining the important role of scientific societies in this process.

Introduction

Liver elastography is one of the basic diagnostic tools in hepatology practice. The most widely used and most studied tool in the world is transient elastography (Fibroscan), however, this system is unevenly available in Slovakia. Shear-wave elastography is a more accessible method because it is built into standard ultrasound systems. However, the problem of shear-wave elastography remains the interpretation of its results, since the threshold values for significant fibrosis (SF) and advanced fibrosis (AF) are unique for each system.

Aims & Methods

To compare the results of transient elastography (TE) and point shear-wave elastography (pSWE) in a cohort of patients examined simultaneously with both systems and to determine the clinical benefit of pSWE in practice.
We examined all indicated patients over a 15-month period using both TE and pSWE (Hitachi Arietta V70). We recorded liver stiffness values in kPa, and baseline demographic and laboratory parameters. We used TE as the gold standard, with a threshold of >10 kPa for SF and >15 kPa for AF. We evaluated the accuracy of pSWE in predicting the detection of SF and AF. We used three models: the first one containing only pSWE values, and two logit models using pSWE together with common demographic and laboratory parameters. We identified the area under the curve (AUROC) and threshold values for each model and evaluated the probability of SF and AF according to these values.

Results

We examined 500 patients with a median age of 60 (IQR 48-69), male/female 214/286, with a SF rate of 30.8% and AF of 18.4%. The stiffness values according to TE and pSWE showed a highly significant correlation (rho=0.593, P<0.001). We found the accuracy of pSWE alone in predicting SF (AUROC=0.812), and AF (AUROC=0.839) with threshold values of SF>6.34 and AF>8.45 kPa. For values of pSWE<6.34, 6.34-8.45, and >8.45 kPa, the probability of SF was 11.1, 40.9, and 65.4% and AF was 5.0, 14.77, and 48.9%. We created two probability models (for P, range 0 to 1): ASTEL1 (N=369) that included pSWE, GGT, and platelets (AUROC SF=0.856, AUROC AF=0.908), and ASTEL2 (N=467) using pSWE, age, sex, AST/ALT, GGT (AUROC SF=0.857, AUROC AF=0.901). We set a threshold of P<0.33 to exclude SF and P>0.66 to confirm AF. At P<0.33, P=0.33-0.66, and P>0.66, SF was present in 15.6, 62, and 94.2% (ASTEL1) and 13.92, 50.7, and 86.8% (ASTEL2). At P<0.33, P=0.33-0.66 and P>0.66, AF was present in 5.6, 30, and 79.7% (ASTEL1) and in 4.4, 28, 73.68% (ASTEL2).

Conclusion

pSWE alone has an excellent negative predictive value (<6.34 kPa, 88.9-95%) in the diagnosis of SF and AF. Higher accuracy of positive prediction of SF (86.8-94.2%) and AF (73.7-79.7%) can be achieved by using one of two probability models (for P>0.66) combining SWE values with common demographic and laboratory parameters.

Introduction

The cornerstone of acute cholangitis treatment is antibiotic therapy combined with biliary drainage. The Tokyo Guidelines 2018 provide severity grading criteria that help predict prognosis and identify patients requiring early biliary drainage. While mild cholangitis can often be managed initially with antibiotics alone, moderate and severe cases typically require early and emergent drainage, respectively. Our aim is to explore factors influencing the timing of ERCP in acute cholangitis and its impact on clinical outcomes.

Aims & Methods

This retrospective single-center cohort study included patients diagnosed with acute cholangitis who underwent ERCP between March 2022 and March 2023 in a tertiary hospital with ERCP. Diagnosis and severity grading were based on the Tokyo Guidelines 2018. Descriptive and statistical analyses were performed to evaluate patient characteristics, severity classification, timing to ERCP and related clinical outcomes.

Results

A total of 104 patients underwent ERCP for acute cholangitis; 55 were female (52.9%) and the median age was 77 years. Based on the Tokyo 2018 criteria, 28 patients (26.9%) had grade III cholangitis, 52 (50%) grade II and 24 (23%) grade I. Only 5 patients (4.8%) underwent ERCP within 24 hours of admission—2 with grade III, 1 with grade II and 2 with grade I. Within 72 hours, 31 patients (29.8%) had undergone ERCP—9 with grade III, 16 with grade II and 6 with grade I. Notably, 70.8% of grade III cases were submitted to ERCP more than 72 hours after admission, with a median of 3 days of antibiotics before the procedure. There was no statistically significant association between ERCP timing and patient age, cholangitis severity, intensive/intermediate care admission or anticoagulant/antiplatelet use. However, admission on a Friday or Saturday was significantly associated with delayed ERCP (p=0.007), with 91% of these patients undergoing ERCP after 72 hours, compared to 56% for admissions on other days. Cholangitis severity correlated significantly with total hospital stay (grade I: 7 ± 3 days, grade II: 8 ± 3.8 days, grade III: 10.5 ± 9 days; p=0.001). ERCP timing was also associated with total antibiotic duration (<24h: 9 ± 2.6 days, 24–72h: 8 ± 3 days, >72h: 10 ± 4.8 days; p=0.043). The 30-day mortality rate was 4.8%, with no significant association with ERCP timing or severity grade.

Conclusion

In this real-world cohort, ERCP was frequently delayed beyond the recommended window, even in severe acute cholangitis. Weekend admission was a significant contributor to this delay. However, no association was found between ERCP timing and 30-day mortality, likely due to small sample size. These findings highlight the need for optimized access to biliary drainage, particularly during weekends, to better meet guideline recommendations.

Introduction

Hepatic encephalopathy (HE) after Transjugular Intrahepatic Portosystemic Shunt (TIPS) affect 35-50% of patients. The use of prophylactic agents (Lactulose and Rifaximin) to prevent post-TIPS HE remains controversial and currently not recommended by professional guidelines. Our aim was to assess real world practice and identify potential predictors for post-TIPS HE and benefit from post-TIPS prophylaxis.

Aims & Methods

Retrospective cohort study of patients undergoing TIPS at the Tel-Aviv Medical Center (2016-2024). The primary outcome was overt HE, with secondary outcomes of liver transplantation (LT) and mortality.

Results

Seventy-nine patients underwent TIPS, median age was 60 years and 52% were male. Primary liver disease was metabolic dysfunction-associated steatohepatitis (MASH) in 34%, viral (20%), and alcohol-related liver disease (ALD) (16.5%). Indications for TIPS were variceal bleeding (52%) and refractory ascites (38%). Prior to the procedure 31% had ≥ 1 episodes of HE, 21.5% were treated with Lactulose and/or Rifaximin, and 58% were on betablocker treatment. At the time of the procedure, the patient's Child-Pugh score was A/B/C in 19%/66%/11% respectively, with a median MELD-Na of 10.9. Median follow up was 22.75 months. Overall, 22 patients died during follow-up and 8 underwent liver transplantation. 45 patients (57%) developed post-TIPS HE, 60% of them during the first three months. Early post-TIPS HE treatment was given to 49%: 10% Lactulose, 5% Rifaximin, and 34% both. Among those patients, 44% were previously (pre-TIPS) on HE treatment. Development of HE was not predicted by pre-or post-TIPS MELD-Na or Child-Pugh score, TIPS diameter, postTIPS gradient, or post-procedure ammonia levels. Rates of HE also did not differ according to initial prophylaxis treatment (59% with treatment, 56% without, p=1). Pre-TIPS AST and albumin were associated with post-TIPS HE (36.6U/L vs. 60.44 U/L, p=0.03; 34.6g/dl vs. 31.8g/dl, p = 0.05). Prior beta-blocker treatment was associated with post-TIPS HE (14% vs 32%, p = 0.01) but not varices as the indication for TIPS. Mortality rate was not affected by the occurrence of post-TIPS HE (28% among those who developed HE vs. 26% among those who didn't, p = 1).

Conclusion

Early post-TIPS preventive treatment was mostly given to patients previously treated with Lactulose/Rifaximin, however it did not affect the rate of post-TIPS HE. Development of HE did not increase mortality.

References

1. Wolfgang el al. ASSLD practice Guidance, Hepatology (2024)
2. Yao el al.J Gastrointestin Liver Dis (2015)