Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement.

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.

Erratum: Cold snare polypectomy of colorectal polyps ≤ 10 mm on clopidogrel: Australian and New Zealand randomized controlled trial.

[This corrects the article DOI: 10.1055/a-1813-1019.].

Risk of Delayed Bleeding after Cold Snare Polypectomy in Patients with Antithrombotic Therapy.

BACKGROUND: Cold snare polypectomy is being increasingly adopted; however, there are few reports of cold snare polypectomy regarding antithrombotic therapy. AIMS: This study aimed to investigate the real-world safety of cold snare polypectomy during antithrombotic therapy. METHODS: We collected data from consecutive patients undergoing cold snare polypectomy in a single hospital between 2013 and 2017. Indications for cold snare polypectomy were any ≤ 10 mm polyp. The primary outcome was delayed bleeding. We compared rates of delayed bleeding between patients with and without antithrombotic therapy and analyzed risk factors for delayed bleeding using binary logistic regression model with firth procedure. RESULTS: In 2152 patients (mean age 67.6 years; male 1411), 4433 colorectal polyps (mean diameter 5.0 mm) underwent cold snare polypectomy. Clipping during the procedure was performed for 5.8%. Delayed bleeding occurred in 0.51% (11/2152) of patients and 0.25% (11/4433) of polyps, but no major delayed bleeding occurred. A total of 244 (11%) patients received antithrombotic therapy. Patients on antithrombotic therapy were older (p < 0.001), more likely male (p < 0.001) and had cold snare polypectomy in the proximal colon (p = 0.011). The rate of delayed bleeding was higher in patients on antithrombotic therapy (1.64% vs. non-antithrombotic therapy 0.37%, p = 0.009). Larger polyp size (> 5 mm), use of clips, and antithrombotic therapy were significant risk factors for delayed bleeding. There was no clear association between specific antithrombotic agents and delayed bleeding. CONCLUSIONS: Delayed bleeding after cold snare polypectomy was rare even in patients with antithrombotic therapy, and no major delayed bleeding occurred.

Piecemeal cold snare polypectomy versus conventional endoscopic mucosal resection for large sessile serrated lesions: a retrospective comparison across two successive periods.

OBJECTIVE: Large (≥20 mm) sessile serrated lesions (L-SSL) are premalignant lesions that require endoscopic removal. Endoscopic mucosal resection (EMR) is the existing standard of care but carries some risk of adverse events including clinically significant post-EMR bleeding and deep mural injury (DMI). The respective risk-effectiveness ratio of piecemeal cold snare polypectomy (p-CSP) in L-SSL management is not fully known. DESIGN: Consecutive patients referred for L-SSL management were treated by p-CSP from April 2016 to January 2020 or by conventional EMR in the preceding period between July 2008 and March 2016 at four Australian tertiary centres. Surveillance colonoscopies were conducted at 6 months (SC1) and 18 months (SC2). Outcomes on technical success, adverse events and recurrence were documented prospectively and then compared retrospectively between the subsequent time periods. RESULTS: A total of 562 L-SSL in 474 patients were evaluated of which 156 L-SSL in 121 patients were treated by p-CSP and 406 L-SSL in 353 patients by EMR. Technical success was equal in both periods (100.0% (n=156) vs 99.0% (n=402)). No adverse events occurred in p-CSP, whereas delayed bleeding and DMI were encountered in 5.1% (n=18) and 3.4% (n=12) of L-SSL treated by EMR, respectively. Recurrence rates following p-CSP were similar to EMR at 4.3% (n=4) versus 4.6% (n=14) and 2.0% (n=1) versus 1.2% (n=3) for surveillance colonoscopy (SC)1 and SC2, respectively. CONCLUSIONS: In a historical comparison on the endoscopic management of L-SSL, p-CSP is technically equally efficacious to EMR but virtually eliminates the risk of delayed bleeding and perforation. p-CSP should therefore be considered as the new standard of care for L-SSL treatment.

Practice of endoscopy during COVID-19 pandemic: position statements of the Asian Pacific Society for Digestive Endoscopy (APSDE-COVID statements).

Coronavirus-19 (COVID-19) caused by SARS-CoV-2 has become a global pandemic. Risk of transmission may occur during endoscopy and the goal is to prevent infection among healthcare professionals while providing essential services to patients. Asia was the first continent to have a COVID-19 outbreak, and this position statement of the Asian Pacific Society for Digestive Endoscopy shares our successful experience in maintaining safe and high-quality endoscopy practice at a time when resources are limited. Sixteen experts from key societies of digestive endoscopy in Asia were invited to develop position statements, including patient triage and risk assessment before endoscopy, resource prioritisation and allocation, regular monitoring of personal protective equipment, infection control measures, protective device training and implementation of a strategy for stepwise resumption of endoscopy services after control of the COVID-19 outbreak.

The Cold Revolution: How Far Can It Go?

Cold resection for small colonic polyps, and larger lesions, is being rapidly and widely adopted. Driven by an impressive safety and cost profile compared with conventional polypectomy, these advantages are offset by the limitations of smaller and shallower resection, and absent thermal effects that may permit persistence of residual neoplasia. To overcome this, optimal cold snare technique requires inclusion of a margin of normal mucosa and a piecemeal resection technique for larger polyps. This article examines the fundamentals of cold snare resection and evidence for its application, theorizes on limits to its application, and identifies areas for further research.

Improved laparoscopic skills in gynaecology trainees following a simulation-training program using take-home box trainers.

BACKGROUND: Lack of time and access to equipment are recognised barriers to simulation training. AIM: To investigate the effect of a take-home laparoscopic simulator training program on the laparoscopic skills of gynaecology trainees. METHOD: Participants (n = 17 in 2015, n = 16 in 2016) were supplied with a box trainer, associated equipment and instructions on self-directed training. A program was designed and implemented in 2015 comprising of ten weekly laparoscopic skills tasks and modified in 2016 to eight monthly tasks. Half of the participants were randomly allocated a supervisor. Participants performed baseline and post-training assessments of laparoscopic skills in a box trainer task (thread transfer) and virtual reality simulator tasks (laparoscopic tubal ligation and bilateral oophorectomy). RESULTS: Trainees in 2015 demonstrated an improvement in the median time to complete the laparoscopic tubal ligation task (baseline 124 s vs post-training 91 s, P = 0.041). There was no difference in the number of tubal ligation bleeding incidents, or in the time taken to complete the box trainer thread transfer task. In 2016 trainees demonstrated improvement in tubal ligation time (baseline 251 vs 71 post-training, P = 0.021) and bilateral oophorectomy time (baseline 891 s vs 504 post-training, P = 0.025). There was no significant difference in other outcome measures. There was no difference found in performance when groups were compared by supervisor allocation. CONCLUSION: A take-home box trainer simulation-training program was associated with improvement in laparoscopic skills. This type of program may improve trainee access to simulation training.

Inhibitory effect of lidocaine on colonic spasm during colonoscopy: A multicenter double-blind, randomized controlled trial.

OBJECTIVES: Colonic spasm can interfere with colonoscopy, but antispasmodic agents can cause complications. This study aimed to assess the inhibitory effect of topical lidocaine compared with a placebo control. METHODS: In five tertiary-care hospitals in Japan, 128 patients requiring endoscopic resection of a colorectal lesion were enrolled and randomly and double-blindly allocated to colonoscopy with topical administration of 2% lidocaine solution 20mL (LID, n = 64) or normal saline 20mL (control, n = 64). During colonoscopy, the assigned solution was applied with a spray catheter near the lesion and the area was observed for three minutes. primary endpoint was the inhibitory effect at three time-points (1, 2 and 3 minutes after dispersion), using a three-point scale (excellent, fair, poor). Secondary endpoints were rebound spasm and adverse events. All endpoints were scored in real time. Serum lidocaine levels were measured in 32 patients (LID 16, control 16). RESULTS: There were no significant differences between groups in patient demographics. At all time-points, the proportion of patients with "excellent" scores was greater in LID group than control group, with significant differences observed at 2 minutes (p = 0.02) and 3 minutes (p = 0.02). In LID group, the rate of "excellent" scores increased by 12.5% at 2 minutes and was maintained at 3 minutes. Rebound spasm did not occur in LID group, compared with 15.6% of control group (p = 0.001). There were no adverse events in LID group. All serum lidocaine levels were below detectable levels. CONCLUSIONS: Topical lidocaine is an effective and safe method for suppressing colorectal spasm during colonoscopy (UMIN000024733).

Trainee Performance in Loop Electrosurgical Excision Procedure (LEEP) After Simulation Training.

OBJECTIVE: The aim of the study was to review the performance of trainees in loop electrosurgical excision procedure (LEEP) procedures after the introduction of a simulation training program. MATERIALS AND METHOD: A simulation training program was introduced in September 2016 for gynecology trainees at the study institution. Trainees were encouraged to perform at least 3 simulated LEEP procedures before operating. For a 12-month period after the introduction of training, data on operating time and specimen quality measures of clear margin status, adequate depth, and absence of fragmentation were reviewed. This was compared with a 12-month period before simulation training (from September 2014-September 2015). Trainees were surveyed for feedback on the training. RESULTS: In total, 135 LEEP procedures were reviewed: 68 before and 67 after simulator training. Trainee specimens after training were more likely to be nonfragmented (89.2% vs 55.9%, p = .003), have clear margins (72.2% vs 41.9%, p = .015), and meet "all criteria" (46% vs 20.6%, p = .043) than trainee specimens before training. There was no change in depth adequacy (70.3% vs 67.7%, p = .99). Median trainee procedure time reduced from 18 minutes (interquartile range = 11-24) before training to 8 minutes after training (interquartile range = 6-11) (p = <0.001). There was no significant change in operating time or specimen quality from LEEP procedures performed by attendings (who did not use the simulator). Trainee and attending procedural outcomes were similar after training. Trainees had mostly positive views on the training, though reported time constraints as a barrier to simulation. CONCLUSIONS: After the introduction of an LEEP simulation training program, operative time and specimen quality from trainee procedures seemed to improve.

Standards of diagnostic colonoscopy for early-stage neoplasia: Recommendations by an Asian private group.

BACKGROUND AND AIM: In recent years, the incidence of colorectal cancer has been increasing, and it is now becoming the major cause of cancer death in Asian countries. The aim of the present study was to develop Asian expert-based consensus to standardize the preparation, detection and characterization for the diagnosis of early-stage colorectal neoplasia. METHODS: A professional group was formed by 36 experts of the Asian Novel Bio-Imaging and Intervention Group (ANBI2 G) members. Representatives from 12 Asia-Pacific countries participated in the meeting. The group organized three consensus meetings focusing on diagnostic endoscopy for gastrointestinal neoplasia. The Delphi method was used to develop the consensus statements. RESULTS: Through the three consensus meetings with debating, reviewing the literature and regional data, a consensus was reached at third meeting in 2016. The consensus was reached on a total of 10 statements. Summary of statements is as follows: (i) Adequate bowel preparation for high-quality colonoscopy; (ii) Antispasmodic agents for lesion detection; (iii) Image-enhanced endoscopy (IEE) for polyp detection; (iv) Adenoma detection rate for quality indicators; (v) Good documentation of colonoscopy findings; (vi) Complication rates; (vii) Cecal intubation rate; (viii) Cap-assisted colonoscopy (CAC) for polyp detection; (ix) Macroscopic classification using indigocarmine spray for characterization of colorectal lesions; and (x) IEE and/or magnifying endoscopy for prediction of histology. CONCLUSION: This consensus provides guidance for carrying out endoscopic diagnosis and characterization for early-stage colorectal neoplasia based on the evidence. This will enhance the quality of endoscopic diagnosis and improve detection of early-stage colorectal neoplasia.

Is that realistic? The development of a realism assessment questionnaire and its application in appraising three simulators for a gynaecology procedure.

INTRODUCTION: There is no standard approach to determining the realism of a simulator, valuable information when planning simulation training. The aim of this research was to design a generic simulator realism questionnaire and investigate the contributions of different elements of simulator design to a user's impression of simulator realism and performance. METHODS: A questionnaire was designed with procedure-specific and non-procedure-specific (global) questions, grouped in subscales related to simulator structure and function. Three intrauterine contraceptive device (IUCD) simulators were selected for comparison. Participants were doctors of varying experience, who performed an IUCD insertion on each of the three models and used the questionnaire to rate the realism and importance of each aspect of the simulators. The questionnaire was evaluated by correlation between procedure-specific and global items and the correlation of these items to overall realism scores. Realism scores for each simulator were compared by Kruskal-Wallis and subsequent between-simulator comparison by Dunn's test. RESULTS: Global question scores were highly related to procedure-specific scores. Comparison revealed global item subscale scores were significantly different across models on each of the nine subscales (P < 0.001). Function items were rated of higher importance than structure items (mean function item importance 5.36 versus mean structure item importance 5.02; P = 0.009). CONCLUSIONS: The designed questionnaire was able to discriminate between the models for perceived simulator realism. Findings from this study may assist simulator design and inform future development of a generic questionnaire for assessing user perceptions of simulator realism.

Cold EMR of large sessile serrated polyps at colonoscopy (with video).

BACKGROUND AND AIMS: The optimal technique for the resection of sessile serrated polyps (SSPs) is unknown, with established limitations and risks with conventional polypectomy. Although cold snare polypectomy is safe, the efficacy of piecemeal resection for large lesions is untested. In this study we evaluate the safety and efficacy of cold EMR for large SSPs. METHODS: Patients presenting for elective colonoscopy at an academic endoscopy center with 1 or more SSPs ≥10 mm in size were enrolled, excluding those on anticoagulant or antiplatelet therapy other than aspirin. Lesions were resected with a cold EMR technique comprising submucosal injection of succinylated gelatin and dilute methylene blue before piecemeal cold snare resection of all visible polyp with a margin of normal tissue. Outcomes were the presence of residual serrated neoplasia in biopsy specimens from the defect margin and findings on surveillance colonoscopy. RESULTS: Cold EMR was performed on 163 SSPs during 105 procedures in 99 patients (97% women; median age, 57 years). The mean size was 17.5 mm: 61 SSPs were ≥20 mm and 13 SSPs ≥30 mm, and 97.5% were in the proximal colon. Cytologic dysplasia was present in 2 (1.2%). Margin biopsy specimens were positive in 2 lesions (1.2%). Surveillance colonoscopy for 82% of lesions (median, 5 months) showed residual serrated tissue in 1, treated with cold snare, but no evidence of recurrence in the remainder. Minor adverse events were seen in 3 patients; no delayed bleeding was observed. CONCLUSIONS: Cold EMR is a safe and effective method for the removal of large SSPs.

Measurement Bias of Polyp Size at Colonoscopy.

BACKGROUND: The success of current and proposed strategies to reduce colorectal cancer (CRC) incidence and mortality rates are fundamentally based on measurement accuracy. OBJECTIVE: The aim of this study was to evaluate the densities of colorectal polyps individually measured at colonoscopy and whether measurement bias is a systemic phenomenon among colonoscopists. DESIGN: A population-wide, observational study. SETTING: All hospitals of the government-funded health system in Brisbane, Australia. PATIENTS: Our study investigated measurement bias at colonoscopy through systematic analysis of 8,591 individual polyp measurements recorded from 12,597 colonoscopies. All colonoscopies performed over a 12-month period between December 1, 2014, and November 30, 2015, were included. RESULTS: A total of 12,597 electronic colonoscopy reports were individually reviewed, hospital-by-hospital, and 8,591 individual size measurements from 18,276 detected polyps (47%) were obtained. LIMITATIONS: Our study is limited because the true size of unresected polyps was unknown. We chose not to compare pathologic and histologic sizes as resection specimens sent to pathologists are morphologically different and are measured differently to the pre-resection polyp images seen by endoscopists. CONCLUSIONS: Colonoscopists may be inaccurate in the measurement of polyp size and appear biased towards and against certain size measurements. These findings cast doubt over the validity of international post-polypectomy surveillance guidelines and the safety of optical diagnosis as a potential management paradigm for diminutive colorectal polyps. They also question the historical accuracy of polyp size data and risk estimates upon which these strategies were based.