Application of machine-learning model to optimize colonic adenoma detection in India.

AIMS: There is limited data on the prevalence and risk factors of colonic adenoma from the Indian sub-continent. We aimed at developing a machine-learning model to optimize colonic adenoma detection in a prospective cohort. METHODS: All consecutive adult patients undergoing diagnostic colonoscopy were enrolled between October 2020 and November 2022. Patients with a high risk of colonic adenoma were excluded. The predictive model was developed using the gradient-boosting machine (GBM)-learning method. The GBM model was optimized further by adjusting the learning rate and the number of trees and 10-fold cross-validation. RESULTS: Total 10,320 patients (mean age 45.18 ± 14.82 years; 69% men) were included in the study. In the overall population, 1152 (11.2%) patients had at least one adenoma. In patients with age > 50 years, hospital-based adenoma prevalence was 19.5% (808/4144). The area under the receiver operating curve (AUC) (SD) of the logistic regression model was 72.55% (4.91), while the AUCs for deep learning, decision tree, random forest and gradient-boosted tree model were 76.25% (4.22%), 65.95% (4.01%), 79.38% (4.91%) and 84.76% (2.86%), respectively. After model optimization and cross-validation, the AUC of the gradient-boosted tree model has increased to 92.2% (1.1%). CONCLUSIONS: Machine-learning models may predict colorectal adenoma more accurately than logistic regression. A machine-learning model may help optimize the use of colonoscopy to prevent colorectal cancers. TRIAL REGISTRATION: ClinicalTrials.gov (ID: NCT04512729).

Role of Novel Motorized Enteroscopy in the Evaluation of Small Bowel Diseases: A Systematic Review and Meta-analysis.

BACKGROUND AND AIM: Motorized spiral enteroscopy (MSE) has recently been introduced for small bowel evaluation. In this systematic review and meta-analysis, we aim to evaluate the safety and efficacy of MSE for evaluation of small bowel diseases. METHODS: A literature search was performed in Embase, PubMed, Medline databases for studies evaluating MSE between January -2010 and October-2022. The primary outcome of the study was diagnostic yield with MSE. Secondary outcomes included technical success, procedure duration, depth of maximum insertion (DMI), rate of pan-enteroscopy and adverse events. RESULTS: 10 studies with 961 patients [581 (60.5%) males] were included in the analysis. 1068 MSE procedures were performed by antegrade route in 698, retrograde route in 215 and bidirectional in 155 patients. Technical success was achieved in 94.9% (95% CI 92.9% to 96.4%) procedures. The pooled diagnostic yield of MSE was 73.7% (95% CI 70.7% to 76.4%). Pooled rate of pan-enteroscopy by antegrade route was 21.9% (95% CI 18.1% to 26.1%), retrograde route was 6.9% (95% CI 2.4% to 18.3%) and combined route was 61.2% (95% CI 52.4% to 69.3%). Pooled rate of major adverse events was 1.9% (95% CI 1.2% to 3.2%). CONCLUSIONS: MSE is a safe and effective tool for evaluating small bowel disorders. High diagnostic yield and low rate of adverse events make it a potential alternative to balloon enteroscopy. However, comparative trials are required in the future.

Pancreatitis from posterior gastric wall perforation by ingested metallic wire-case report and review of literature.

Gastric and duodenal perforation from ingested organic and inorganic foreign bodies, such as sewing needles, toothpick, metallic wires, fish and chicken bone, are uncommon incidents as most foreign bodies pass in the faeces. The perforated foreign body can at times migrate and either penetrate causing traumatic injury or incite inflammation with formation of abscesses or pseudo-tumours in the adjacent organs such as the liver and pancreas. We report one such case of pancreatitis in a child resulting from a metallic wire perforating the posterior gastric wall and penetrating the pancreas. The findings were detected on CT and the foreign body was extracted endoscopically. We also present review of literature on similar case reports.

A Randomized, Controlled Trial Comparing the Total Enteroscopy Rate and Diagnostic Efficacy of Novel Motorized Spiral Enteroscopy and Single-Balloon Enteroscopy in Patients With Small-Bowel Disorders: The Motor Trial (NCT 05548140).

INTRODUCTION: Device-assisted enteroscopy has revolutionized the management of small-bowel disorders (SBD). No study to date has compared both novel motorized spiral enteroscopy (NMSE) and single-balloon enteroscopy (SBE) as a randomized controlled trial. Hence, this study was planned to include patients having SBD with the primary aim to compare the total enteroscopy rate (TER). METHODS: This study was conducted at the Asian Institute of Gastroenterology (AIG Hospitals), Hyderabad, India, from September 20, 2022, to December 15, 2022. All consecutive patients, older than 18 years with suspected SBD, and planned for total enteroscopy were screened for inclusion. The primary outcome was to compare the TER, and secondary outcomes were to compare the technical success, time taken to reach the depth of maximal insertion, withdrawal time, total procedure time, diagnostic yield, therapeutic success, and adverse events (AE). RESULTS: Seventy-two patients of the 110 patients screened were randomized in either NMSE (n = 35) or SBE (n = 37) group. The most common indication for the procedures was obscure gastrointestinal bleed (48%), others being unexplained abdominal pain with indeterminate radiologic findings (32%) and chronic diarrhea (20%). In NMSE group, the TER was 71.4%, whereas in the SBE group, it was 10.8% ( P < 0.0001). The total procedure time (minutes) was much lesser with NMSE (58.17 ± 21.5 minutes) vs SBE (114.2 ± 33.5 minutes) ( P < 0.0001). The diagnostic yield of NMSE (80%) was comparatively higher than SBE (62.1%) ( P = 0.096). Minor AE (grade I) were observed in both the groups: NMSE 8.5% (3/35) and SBE 5.4% (2/37). DISCUSSION: This randomized controlled trial shows that with NMSE higher TER can be achieved in shorter duration with minimal AE, compared with SBE.

Technical performance and diagnostic yield of motorised spiral enteroscopy compared with single-balloon enteroscopy in suspected Crohn's disease: a randomised controlled, open-label study (the MOTOR-CD trial).

OBJECTIVE: Recent studies have shown that motorised spiral enteroscopy (MSE) enables deeper and total small bowel evaluation compared with single-balloon enteroscopy (SBE) in suspected Crohn's disease (CD) when analysed per procedure. However, no randomised controlled study has compared bidirectional MSE with bidirectional SBE in suspected CD. DESIGN: Patients with suspected CD requiring small bowel enteroscopy were randomly assigned to either SBE or MSE between May 2022 and September 2022 in a high volume tertiary centre. Bidirectional enteroscopy was done if intended lesion could not be reached on unidirectional study. Comparison was made with regard to technical success (ability to reach lesion), diagnostic yield, depth of maximal insertion (DMI), procedure time and total enteroscopy rates. Depth:time ratio was calculated to avoid confounding for the location of lesion. RESULTS: Among 125 suspected patients with CD (28% female, 18-65 years, median 41 years), 62 and 63 underwent MSE and SBE, respectively. The overall technical success (98.4 %: MSE, 90.5 %: SBE; p=0.11), diagnostic yield (95.2%: MSE; 87.3%: SBE, p=0.2) and procedure time were not significantly different. However, MSE appeared to have higher technical success (96.8% vs 80.7%, p=0.08) in deeper small bowel (distal jejunum/proximal ileum) with higher DMI, higher depth:time ratio and total enteroscopy rates when attempted (77.8% vs 11.1%, p=0.0007). Both the modalities were safe although minor adverse events were more common with MSE. CONCLUSION: MSE and SBE have comparable technical success and diagnostic yield for small bowel evaluation in suspected CD. MSE scores over SBE with regard to deeper small bowel evaluation with complete small bowel coverage and higher depth of insertion in a shorter time. TRIAL REGISTRATION NUMBER: NCT05363930.

Artificial Intelligence in Hepatology- Ready for the Primetime.

Artificial Intelligence (AI) is a mathematical process of computer mediating designing of algorithms to support human intelligence. AI in hepatology has shown tremendous promise to plan appropriate management and hence improve treatment outcomes. The field of AI is in a very early phase with limited clinical use. AI tools such as machine learning, deep learning, and 'big data' are in a continuous phase of evolution, presently being applied for clinical and basic research. In this review, we have summarized various AI applications in hepatology, the pitfalls and AI's future implications. Different AI models and algorithms are under study using clinical, laboratory, endoscopic and imaging parameters to diagnose and manage liver diseases and mass lesions. AI has helped to reduce human errors and improve treatment protocols. Further research and validation are required for future use of AI in hepatology.

Diagnostic yield and technical performance of the novel motorized spiral enteroscopy compared with single-balloon enteroscopy in suspected Crohn's disease: a prospective study (with video).

BACKGROUND AND AIMS: Both single-balloon enteroscopy (SBE) and the novel motorized spiral enteroscopy (NMSE) are effective techniques for device-assisted enteroscopy (DAE). To date, no study has prospectively compared both modalities in suspected Crohn's disease (CD). METHODS: Patients with suspected CD undergoing either SBE or NMSE between March 2021 and December 2021 in a high-volume tertiary center were prospectively compared for technical success (ability to reach the lesion), diagnostic yield, depth of maximal insertion (DMI), procedure time, and total enteroscopy rates. RESULTS: One hundred seventy-seven patients (37.2% female; aged 7-75 years) with suspected CD underwent 201 DAEs. Technical success was 83% (SBE 81.5% vs NMSE 87.3%, P = .61) and impacted subsequent management in 92% (SBE 88.5% vs NMSE 97.8%, P = .2). Technical success with antegrade NMSE was significantly higher (81.4%) than antegrade SBE (33.3%, P = .007) for lesions in the proximal ileum and beyond. There was no significant difference in the diagnostic yield (SBE 80.8% vs NMSE 83.6%, P = .65). Median procedure time was significantly lower in both antegrade (NMSE, 40 minutes [range, 10-75]; SBE, 60 minutes [range, 20-180]; P < .0001) and retrograde (NMSE, 25 minutes [range, 20-60]; SBE, 60 minutes [range, 20-180]; P < .0001) NMSE. Median DMI was higher with antegrade NMSE (NMSE, 400 cm [range, 70-600]; SBE, 180 cm [range, 60-430]; P < .0001). The total enteroscopy rate was higher with NMSE (37% vs .7% with SBE, P < .0001). All adverse events were mild. CONCLUSIONS: Both NMSE and SBE are safe and effective for small-bowel evaluation in suspected CD. NMSE is superior to SBE with regard to deeper small-bowel evaluation with complete small-bowel coverage and shorter procedure time.

Application of Deep Learning Models to Improve Ulcerative Colitis Endoscopic Disease Activity Scoring Under Multiple Scoring Systems.

BACKGROUND AND AIMS: Lack of clinical validation and inter-observer variability are two limitations of endoscopic assessment and scoring of disease severity in patients with ulcerative colitis [UC]. We developed a deep learning [DL] model to improve, accelerate and automate UC detection, and predict the Mayo Endoscopic Subscore [MES] and the Ulcerative Colitis Endoscopic Index of Severity [UCEIS]. METHODS: A total of 134 prospective videos [1550 030 frames] were collected and those with poor quality were excluded. The frames were labelled by experts based on MES and UCEIS scores. The scored frames were used to create a preprocessing pipeline and train multiple convolutional neural networks [CNNs] with proprietary algorithms in order to filter, detect and assess all frames. These frames served as the input for the DL model, with the output being continuous scores for MES and UCEIS [and its components]. A graphical user interface was developed to support both labelling video sections and displaying the predicted disease severity assessment by the artificial intelligence from endoscopic recordings. RESULTS: Mean absolute error [MAE] and mean bias were used to evaluate the distance of the continuous model's predictions from ground truth, and its possible tendency to over/under-predict were excellent for MES and UCEIS. The quadratic weighted kappa used to compare the inter-rater agreement between experts' labels and the model's predictions showed strong agreement [0.87, 0.88 at frame-level, 0.88, 0.90 at section-level and 0.90, 0.78 at video-level, for MES and UCEIS, respectively]. CONCLUSIONS: We present the first fully automated tool that improves the accuracy of the MES and UCEIS, reduces the time between video collection and review, and improves subsequent quality assurance and scoring.

Ampullary cyst with papillary orifice distal to bulge: Not always a choledochocele!

Video 1Ampullary cyst with papillary orifice distal to bulge: not always a choledochocele.

To assess the efficacy of safety measures adopted during endoscopy in the Corona Virus Disease-19 era for health care professionals-A single-centre tertiary care hospital experience.

BACKGROUND AND OBJECTIVES: During Corona Virus Disease-19 (COVID-19) pandemic, it has been estimated that approximately 10% of health care professionals (HCPs) have been diagnosed contacting  COVID-19. Aerosol-generating procedures have led to change in safety practices among HCPs. We thus evaluated the efficacy of the endoscopic safety measures among HCPs posted in the endoscopy unit. METHODS: In this retrospective analysis, all endoscopic procedures performed over a period of 4 months, from 1 April to 31 July 2020 were included. We noted indications and number of COVID-positive procedures as well as comprehensive screening of HCPs posted in our endoscopy unit. The aim of the study was to evaluate the incidence and outcome of COVID-19 among HCPs. RESULTS: Three thousand four hundred and sixty procedures were included in the analysis. Indications were divided as urgent (n = 190, 5.49%), semi-urgent (n = 553, 16%) and non-urgent group (n = 2717, 78.52%). Thirty-four procedures (0.98%) were done on diagnosed COVID-19 patients. The most common indications were gastrointestinal bleed (n = 12/34, 35.30%) followed by biliary sepsis (n = 9/34, 26.5%). Among the HCPs, the incidence of symptomatic COVID-19 was 6.58% (n = 5/76). All HCPs recovered with excellent outcomes. A comprehensive screening showed 7.90% (n = 6/76) HCPs having Immunoglobulin G (IgG) antibody in their sera. CONCLUSION: Addition of safety measures in endoscopy leads to low risk of transmission among HCPs.

Diagnostic yield and therapeutic impact of novel motorized spiral enteroscopy in small-bowel disorders: a single-center, real-world experience from a tertiary care hospital (with video).

BACKGROUND AND AIMS: Novel motorized spiral enteroscopy (NMSE) is a recent advancement in the field of enteroscopy and offers multiple features, including self-propulsion, better irrigation, and shorter enteroscope length with a larger channel. The aim of this study was to evaluate the efficacy in terms of diagnostic yield and therapeutic success of NMSE in patients undergoing enteroscopy by antegrade and/or retrograde approaches for suspected small-bowel disease. METHODS: We retrospectively evaluated consecutive patients with symptomatic small-bowel disease who underwent enteroscopy over a 6-month period. Diagnostic yield, therapeutic success, total enteroscopy rate (TER), technical success, total procedural time, depth of maximal insertion, and adverse events related to the NMSE procedure were noted. RESULTS: Of 61 patients (mean age, 45.67 ± 15.37 years; 43 men) included for NMSE, 57 patients underwent successful enteroscopy with a technical success of 93.4%. The overall diagnostic yield was 65.5% (95% confidence interval, 52.31-77.27) and 70.1% (95% confidence interval, 56.60-81.57) in patients who underwent successful NMSE; TER was 60.6%: 31.1% by the antegrade approach and 29.5% by a combined antegrade and retrograde approach. Depth of maximal insertion and procedural time was of 465 cm (range, 100-650) and 40 minutes (range, 25-60), respectively, by the antegrade approach and 140 cm (range, 50-200) and 35 minutes (range, 30-60) by the retrograde route. Lesions were classified as inflammatory (n = 25), vascular (n = 10), and mass (n = 4). Biopsy specimens were obtained in 50.8% subjects, and 23% patients underwent therapeutic procedures. No major adverse events were seen. CONCLUSIONS: NMSE is a promising technology, showing high efficacy as a diagnostic and therapeutic tool in the management of otherwise difficult-to-treat small-bowel disease.