Introduction

Videocolonoscopy (VCC) remains the gold standard in the diagnosis of colorectal carcinoma (CRC) and premalignant lesions. Around 26% of polyps are missed during conventional colonoscopy due to operator (e.g., expertise, fatigue, etc.), and technical (e.g., suboptimal bowel preparation and withdrawal time) dependent-factors. Artificial intelligence (AI) aids in adenoma and polyp detection, thus increasing adenoma and polyp detection rates (ADR and PDR, respectively).

Aims & Methods

We aim to evaluate the real-world effectiveness of an AI-assisted colonoscopy (AI-VCC) and compare the results among experts and non-experts endoscopists. Consecutive patients ≥45 years old who underwent VCC (Nov/2020-Mar/2021) were invited to participate. Patients with BBPS≤6, history of inflammatory bowel disease, familial polyposis syndrome, colorectal carcinoma, colorectal surgery, or uncontrolled coagulopathy were not considered. The study protocol was conducted according to the declaration of Helsinki and approved by the local Institutional Review Board (IRB). All patients signed an informed written consent. First, a standard HD-VCC was performed. Then, an AI-VCC was performed by a second operator blinded to previous findings. We determined the adenoma detection rate (ADR) as a quality indicator of the procedure. The polyp detection rate (PDR), and the adenoma and polyp miss rates (AMR and PMR, respectively) were also calculated. The results were compared between experts and non-experts endoscopists. Data was analyzed in R v4.0.

Results

A total of 115 patients were included. Median age was 57.0 (51.0 - 67.5) years, 82/115 (71.3%) were females. 58/115 (50.4%) patients had a total of 205 polyps/adenoma, with a PDR and ADR of 132/205 (64.3%) and 73/205 (35.6%) with VCC, respectively: 19/205 (9.3%) NICE II, 7/205 (3.4%) >10 mm. With AI-assistance, the ADR and PDR increased from 16.5% to 18.2% and from 50.4% to 60%, respectively. According to the level of expertise, the ADR increased from 10.8% to 16.2% in the junior group with the AI-VCC, whereas no difference in ADR was observed in the senior cohort (Table 1). The calculated PMR was 43.13% while the AMR was 5.19%. Sensitivity among different colon segments ranged from 56.25% (rectum) to 78.26% (ascending colon). Meanwhile, capability of AI for appropriate polyp and adenoma presence discharging (negative predictive value, NPV) ranged from 61.54% (sigmoid) to 89.09% (cecum). However, lower rates for specificity (8.42-49.49%) and positive predictive value (PPV, 9.89-19.78%) were observed due to high false positives. (Table 2).

Table 1. ADR and PDR during HD-VCC and AI-VCC in senior and junior endoscopists.

Conclusion

The AI-assisted polyp detector is a feasible tool to aid endoscopists during screening colonoscopy. Additionally, with AI-assistance, junior endoscopists can achieve an ADR comparable to that of senior endoscopists. NCT04915833.

References

1. Wang P, Berzin TM, Glissen Brown JR, Bharadwaj S, et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomized controlled study. Gut. 2019 Oct;68(10):1813-1819.
2. Zhao S, Wang S, Pan P, Xia T, Chang X, et al. Magnitude, Risk Factors, and Factors Associated with Adenoma Miss Rate of Tandem Colonoscopy: A Systematic Review and Meta-analysis. Gastroenterology. 2019;156 (6):1661–1674e11.
3. Mahmud N, Cohen J, Tsourides K, Berzin TM. Computer vision and augmented reality in gastrointestinal endoscopy. Gastroenterol Rep (Oxf). 2015 Aug;3(3):179-84.
4. Kröner PT, Engels MM, Glicksberg BS, Johnson KW, et al. Artificial intelligence in gastroenterology: A state-of-the-art review. World J Gastroenterol 2021; 27(40): 6794-6824.
5. Taghiakbari M, Mori Y, von Renteln D. Artificial intelligence-assisted colonoscopy: A review of current state of practice and research. World J Gastroenterol. 2021 Dec 21;27(47):8103-8122.

Disclosure

Carlos Robles-Medranda is a key opinion leader and consultant for Pentax Medical, Boston Scientific, Steris, Medtronic, Motus, Micro-tech, G-Tech Medical Supply, CREO Medical, EndoSound, and Mdconsgroup. The other authors declare no conflicts of interest.

Introduction

Acute kidney injury (AKI) in cirrhosis manifests as pre-renal azotemia (PRA), hepatorenal syndrome (HRS), or acute tubular necrosis (ATN), each with distinct prognosis ⁽¹⁾. Early subtype classification and outcome prediction are critical. In Decompensated Cirrhosis patients with AKI, urine NGAL (UNGAL) and urine IL-18 (UIL-18) have been evaluated for differentiating between ATN and non-ATN AKI (PRA and HRS) with conflicting results ^(2,3). The present study compared the diagnostic accuracy of UNGAL and UIL-18 for predicting ATN AKI, AKI resolution and in-hospital mortality.

Aims & Methods

Present study was conducted at a tertiary care hospital (GIPMER, India) from July 1, 2023 to December 31, 2024. Patients with Decompensated Cirrhosis having AKI stage IB or higher were included, while advanced chronic kidney disease, Hepatocellular carcinoma prior liver transplant were excluded. The AKI was diagnosed as per International Club of Ascites Consensus (2015) and classified as per clinical adjudication after volume expansion with injection Human Albumin (20%, 1 g/kg body weight) on day 3 ⁽⁴⁾. Urine NGAL (sandwich ELISA) and IL-18 (sandwich ELISA) were measured after 48 hours of volume expansion, that is on day 3 of AKI diagnosis. The primary outcome was prediction of ATN-AKI on day 3 and secondary outcomes were prediction of AKI resolution at discharge and in-hospital mortality. The Receiver-operator curve (ROC) and multivariate logistic regression were used for analysis and p value <0.05 considered statistically significant.

Results

Total of 81 Decompensated Cirrhosis patients with AKI were enrolled in study. The aetiology of AKI was 24 (29.5%) PRA, 37 (45.7%) HRS and 20 (24.7%) ATN respectively. Mean MELD Na score was 28.4+7.3 and majority (82.7%) were CTP-C. Mean Serum Creatinine was 2.85+0.95 mg/dl. Mean UNGAL was 109.7 (PRA), 206.6 (HRS) and 396.4 (ATN) ug/g Creatinine (p<0.001). Mean UIL-18 was 39.8 (PRA), 85.6 (HRS) and 139.3 (ATN) pg/ml (p<0.001). AUROC for differentiation of ATN from non-ATN for urine NGAL was 0.9 (best cut-off 236.3 ug/g Creat) and urine IL-18 was 0.88 (best cut-off 108.75 pg/ml). AKI resolution occurred in 95.8% (PRA), 81% (HRS), and 40% (ATN). Mortality was highest in ATN (50%), vs PRA (16.7%) and HRS (8.1%). AUROC of UNGAL was 0.211 and UIL-18 was 0.185 for predicting AKI resolution. AUROC of UNGAL was 0.654 and UIL-18 was 0.641 for predicting in-hospital mortality (AUROC: NGAL 0.654, IL-18 0.641). Urine NGAL ( and urine IL-18 failed to predict AKI resolution (p 0.14 and 0.27) and in-hospital mortality (p 0.06 and 0.07) in multivariate regression analysis.

Conclusion

Urine NGAL and IL-18 had good diagnostic accuracy in predicting ATN-AKI in patients with Decompensated Cirrhosis, however do not independently predict resolution of AKI and in-hospital mortality.

References

1. Tariq R, Hadi Y, Chahal K, Reddy S, Salameh H, Singal AK. Incidence, mortality and predictors of acute kidney injury in patients with cirrhosis: A systematic review and meta-analysis. J Clin Transl Hepatol. 2020;8(2):135.
2. Puthumana J, Ariza X, Belcher JM, Graupera I, Ginès P, Parikh CR. Urine interleukin 18 and lipocalin 2 are biomarkers of acute tubular necrosis in patients with cirrhosis: a systematic review and meta-analysis. Clinical Gastroenterology and Hepatology. 2017;15(7):1003-13.
3. Huelin P, Solà E, Elia C, Solé C, Risso A, Moreira R, et al. Neutrophil gelatinase-associated lipocalin for assessment of acute kidney injury in cirrhosis: a prospective study. Hepatology.2019;70(1):319–33.
4. Angeli P, Ginès P, Wong F, Bernardi M, Boyer TD, Gerbes A, et al. Diagnosis and
management of acute kidney injury in patients with cirrhosis: revised consensus recommendations of the International Club of Ascites. Gut. 2015;64(4):531–7.

Introduction

Serrated lesions in the colon, that can contribute to up to 20% of colon cancers, are often difficult to detect during standard white light colonoscopy (SC). Artificial intelligence specifically Computer-aided Detection (CADe) has been shown to positively impact the adenoma detection rate (ADR) and adenomas per colonoscopy, but data on SSLs are scarce. We aimed to evaluate the effect of CADe on detecting SSLs byperforming a meta-analysis of all the randomized controlled trials.

Aims & Methods

PubMed, Embase, and Cochrane databases were searched (upto November 2022) to identify randomized controlled studies comparing CADe and SC. Our primary outcome was the comparison of pooled estimates of SSL-detection rate (SSLDR) between those undergoing CADe and SC. The secondary outcome was the mean number of SSL per colonoscopy (SSLPC). Subgroup analyses were performed for studies only including screening or surveillance colonoscopy. Risk ratios (RR) and mean differences (MD) with 95% confidence intervals (CI) were calculated for dichotomous and continuous variables, respectively, using the random effects model. Study heterogeneity was assessed using i² statistics and prediction intervals

Results

12 RCTs were eligible with a total of 9237 patients: CADe group-4595 patients (mean age 58.5 years; 53.5% men) and SC group- 4642 (mean age 58.4 years; 52.1% men). There was no significant difference in SSLDR between CADe (4.6%) vs. SC (4%) with a Risk Ratio of 1.15 (95% CI 0.95-1.39, i²= 0%) (Table 1a). Similarly, for SSLPC, there was no significant difference between CADe and SC (MD 0.01, 95% CI -0.02 –0.03, i²= 98%). When our analysis was limited to studies including only screening or surveillance colonoscopy, again, there were no significant differences between CADe and SC in terms of SSLDR (5.7% vs 4.9%, RR 1.15, 95% CI 0.92-1.45) and SSLPC (MD -0.02, 95% CI -0.07 – 0.030).

Table 1. Comparison of SSLDR between CADe and Standard Colonoscopy

Conclusion

Compared with standard colonoscopy, currently evaluated AI systems do not show improved sessile serrated lesion detection rate or mean sessile serrated lesions per colonoscopy, even when including only screening or surveillance colonoscopy. Further RCTs should be designed with SSL as one of the primary outcomes using highly trained AI systems.

Disclosure

No Relevant Financial Disclosure

Introduction

Difficult bile stones (DBS) accounts for 10 to 15% of choledocholithiasis cases. In this setting different endoscopic techniques are available to obtain bile duct clearance. Of them endoscopic papillary large balloon dilation (EPLBD) demonstrated high rate of efficacy and is usually performed as a first step when DBS are encountered. However, EPLBD alters the anatomy and the functional role of major papilla potentially exposing patients to cholangitis. To date, few data are available in literature on the long-term consequence of EPLBD.

Aims & Methods

Aim of the study is to explore the long-term complications of EPLBD in terms of cholangitis and biliary recurrence. This is a multicenter retrospective study conducted within 33 centers. Adult patients who underwent to EPLBD (balloon diameter ≥12 mm) and obtained complete bile duct clearance in one or more endoscopic sessions were included in the study. Patients with surgical altered anatomy and those with orthotopic liver transplantation were excluded from the study. Primary outcome of the study was the rate of cholangitis; secondary outcome was endoscopic reintervention after EPLBD.

Results

1221 patients (654 female) with a median age of 77 yo (IQR 68-84) were included in the study. EPLBD was performed after previous failed ERCP standard treatments in 43.7% of cases. Indication for EPLBD was a single or double large stone in 51.8% of patients or multiple stones in 48.2% of patients with a median common bile duct (CBD) diameter of 15 mm (IQR 12-18). Large balloon dilation was performed at a median diameter of 13 mm (IQR 12-15) and CBD clearance was obtained with only one EPLBD session in 81.3% of patients. Assessment of CBD clearance was evaluated in 93% of cases with cholangiography and in the remaining of cases with cholangioscopy or cross-sectional imaging. Intra-procedural and short-term adverse events (AEs) were recorded in 3.9% and 8% of patients respectively. During a median follow-up time of 921 days (IQR 513-1644) 143 patients (11.7%) experienced at least one episode of cholangitis that have occurred after a median time of 293 days from EPLBD (IQR 133-553 days). Cholangitis was caused by stones recurrence in 76% of cases. Cholangitis was managed in the majority of cases (83.5%) with ERCP and in the remaining with conservative antibiotic therapy. Global rate of biliary recurrence with need of ERCP was recorded in 16% of patients. At Kaplan-Meier analysis the risk of cholangitis or biliary recurrence was homogeneous during follow-up time and was not affected by dilator balloon diameter (more or less than 15 mm). At multivariate Cox regression analysis, risk factors for cholangitis were a previous ERCP before EPLBD (HR 95%CI 1.65; 1.16 to 2.34), presence of multiple biliary stones (HR 95%CI 1.67;1.18 to 2.36) and stone recurrence during follow-up (HR 95%CI, 2.86; 1.61 to 5.08) whereas cholecystectomy status was not associated to long-term complications.

Conclusion

Cholangitis is not an uncommon long-term complication of EPLBD. The risk of cholangitis is homogeneous during follow-up time and the major determinants of cholangitis are previous ERCP before EPLBD, the presence of multiple biliary stones and the occurrence of stone recurrence during follow-up.