Physician perceptions on the current and future impact of artificial intelligence to the field of gastroenterology

BACKGROUND AND AIMS

The use of artificial intelligence (AI) has transformative implications to the practice of gastroenterology and endoscopy. The aims of this study were to understand the perceptions of the gastroenterology community toward AI and to identify potential barriers for adoption.

METHODS

A 16-question online survey exploring perceptions on the current and future implications of AI to the field of gastroenterology was developed by the American Society for Gastrointestinal Endoscopy AI Task Force and distributed to national and international society members. Participant demographic information including age, sex, experience level, and practice setting was collected. Descriptive statistics were used to summarize survey findings, and a Pearson χ2 analysis was performed to determine the association between participant demographic information and perceptions of AI.

RESULTS

Of 10,162 invited gastroenterologists, 374 completed the survey. The mean age of participants was 46 years (standard deviation, 12), and 299 participants (80.0%) were men. One hundred seventy-nine participants (47.9%) had >10 years of practice experience, with nearly half working in the community setting. Only 25 participants (6.7%) reported the current use of AI in their clinical practice. Most participants (95.5%) believed that AI solutions will have a positive impact in their practice. One hundred seventy-six participants (47.1%) believed that AI will make clinical duties more technical but will also ease the burden of the electronic medical record (54.0%). The top 3 areas where AI was predicted to be most influential were endoscopic lesion detection (65.3%), endoscopic lesion characterization (65.8%), and quality metrics (32.6%). Participants voiced a desire for education on topics such as the clinical use of AI applications (64.4%), the advantages and limitations of AI applications (57.0%), and the technical methodology of AI (44.7%). Most participants (42.8%) expressed that the cost of AI implementation should be covered by their hospital. Demographic characteristics significantly associated with this perception included participants' years in practice and practice setting.

CONCLUSIONS

Gastroenterologists have an overall positive perception regarding the use of AI in clinical practice but voiced concerns regarding its technical aspects and coverage of costs associated with implementation. Further education on the clinical use of AI applications with understanding of the advantages and limitations appears to be valuable in promoting adoption.

Comparative Risks of Post-ERCP Adverse Events in Patients with Asymptomatic and Symptomatic Choledocholithiasis: A Systematic Review and Meta-Analysis

BACKGROUND AND AIMS

Endoscopic retrograde cholangiopancreatography (ERCP) is the standard of care for the management of choledocholithiasis but carries risk of complications which may result in significant morbidity and mortality. While currently available guidelines endorse the use of ERCP for the management of symptomatic common bile duct stones, the need for ERCP in incidentally found asymptomatic choledocholithiasis is more controversial, and practice varies on a geographic and institutional level. This systematic review and meta-analysis is conducted to compare post-ERCP adverse events between asymptomatic and symptomatic choledocholithiasis patients.

METHODS

We searched PubMed/Embase/Web of Science databases to include all studies comparing post-ERCP outcomes between asymptomatic and symptomatic choledocholithiasis patients. The primary outcome was post-ERCP pancreatitis (PEP), while secondary outcomes included post-ERCP cholangitis, bleeding, and perforation. We calculated pooled risk ratios (RR) and 95% confidence intervals (CIs) using the Mantel-Haenszel method within a random-effect model.

RESULTS

Our analysis included six observational studies, totaling 2,178 choledocholithiasis patients (392 asymptomatic and 1786 symptomatic); 53% were female. Asymptomatic patients exhibited a higher risk of PEP compared with symptomatic patients (11.7% versus 4.8%; RR 2.59, 95% CI 1.56-4.31, p ≤ 0.001). No significant difference was observed in post-ERCP cholangitis, bleeding, or perforation rates between the two groups.

CONCLUSIONS

Asymptomatic patients with choledocholithiasis appear to have a higher risk of PEP than symptomatic patients, while the risk of other post-ERCP adverse events is similar between the two groups. Interventional endoscopists should thoroughly discuss potential adverse events (particularly PEP) with asymptomatic patients before performing ERCP and utilize PEP-prevention measures more liberally in this subgroup of patients.

Multiloculated Liver Abscess: A Complication of Endoscopic Ultrasound-Guided Liver Biopsy

Endoscopic ultrasound (EUS)-guided liver biopsy is gaining popularity for liver parenchymal sampling due to its detailed visualization of liver anatomy, precision in sampling, and the ability to combine liver biopsy with other endoscopic goals. In this study, we present a case involving an anatomically complex, immunocompromised patient who underwent EUS-guided liver biopsy. While the samples were sufficient and progressed the management of her autoimmune hepatitis, her course was complicated by a multiloculated liver abscess. EUS liver biopsy has an excellent safety profile, but a small risk of infection remains, especially in immunocompromised patients or those with preexisting biliary obstruction.

The Bethesda ERCP Skills Assessment Tool (BESAT) can reliably differentiate endoscopists of different experience levels

Background and study aims The Bethesda ERCP Skill Assessment Tool (BESAT) is a video-based assessment tool of technical endoscopic retrograde cholangiopancreatography (ERCP) skill with previously established validity evidence. We aimed to assess the discriminative validity of the BESAT in differentiating ERCP skill levels. Methods Twelve experienced ERCP practitioners from tertiary academic centers were asked to blindly rate 43 ERCP videos using the BESAT. ERCP videos consisted of native biliary cannulation and sphincterotomy and were recorded from 10 unique endoscopists of various ERCP experience (from advanced endoscopy fellow to > 10 years of ERCP experience). Inter-rater reliability, discriminative validity, and internal structure validity were subsequently assessed. Results The BESAT was found to reliably differentiate between endoscopists of varying levels of ERCP experience with experienced ERCPists scoring higher than novice ERCPists in 11 of 13 (85%) instrument items. Inter-rater reliability for BESAT items ranged from good to excellent (intraclass correlation range: 0.86 to 0.93). Internal structure validity was assessed with item-total correlations ranging from 0.53 to 0.83. Conclusions Study findings demonstrate that the BESAT, a video-based ERCP skill assessment tool, has high inter-rater reliability and has discriminative validity in differentiating novice from expert ERCP skill. Further investigations are needed to determine the role of video-based assessment in improving trainee learning curves and patient outcomes.

Efficacy, Feasibility, and Safety of the X-Tack Endoscopic HeliX Tacking System: A Multicenter Experience

BACKGROUND AND AIMS

The application of endoscopic suturing has revolutionized defect closures. Conventional over-the-scope suturing necessitates removal of the scope, placement of the device, and reinsertion. A single channel, single sequence, through-the-scope suturing device has been developed to improve this process. This study aims to describe the efficacy, feasibility, and safety of a through-the-scope suturing device for gastrointestinal defect closure.

METHODS

This was a retrospective multicenter study involving 9 centers of consecutive adult patients who underwent suturing using the X-Tack Endoscopic HeliX Tacking System (Apollo Endosurgery). The primary outcomes were technical success and long-term clinical success. Secondary outcomes included adverse events, recurrence, and reintervention rates.

RESULTS

In all, 56 patients (mean age 53.8, 33 women) were included. Suturing indications included fistula repair (n=22), leak repair (n=7), polypectomy defect closure (n=12), peroral endoscopic myotomy (POEM) site closure (n=7), perforation repair (n=6), and ulcers (n=2). Patients were followed at a mean duration of 74 days. Overall technical and long-term clinical success rates were 92.9% and 75%, respectively. Both technical and clinical success rates were 100% for polypectomies, POEM-site closures, and ulcers. Success rates were lower for the repair of fistulas (95.5% technical, 54.5% clinical), leaks (57.1%, 28.6%), and perforations (100%, 66.7%). No immediate adverse events were noted.

CONCLUSION

This novel, through-the-scope endoscopic suturing system, is a safe and feasible method to repair defects that are ≤3 cm. The efficacy of this device may be better suited for superficial defects as opposed to full-thickness defects. Larger defects will need more sutures and probably a double closure technique to provide a reinforcement layer.

Gastrointestinal Kaposi Sarcoma: A Rare Case of an Isolated Rectal Lesion in an Immunocompetent HIV-Negative Patient

Kaposi sarcoma (KS) is a pathological endothelial growth associated with human herpes virus-8 which primarily affects the skin. In HIV-negative men who have sex with men, the clinical presentation of KS resembles the classic form limited to cutaneous or multifocal disease. In this report, we present a unique case of a healthy 61-year-old man who has sex with men with an isolated gastrointestinal KS who does not meet criteria for any of the typical KS clinical variants. Proper follow-up and regular HIV screenings are needed to evaluate the potential progression course of the disease in these patients.

AGA Clinical Practice Update on the Role of Artificial Intelligence in Colon Polyp Diagnosis and Management: Commentary

DESCRIPTION

The purpose of this American Gastroenterological Association (AGA) Institute Clinical Practice Update (CPU) is to review the available evidence and provide expert commentary on the current landscape of artificial intelligence in the evaluation and management of colorectal polyps.

METHODS

This CPU was commissioned and approved by the AGA Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPUC and external peer review through standard procedures of Gastroenterology. This Expert Commentary incorporates important as well as recently published studies in this field, and it reflects the experiences of the authors who are experienced endoscopists with expertise in the field of artificial intelligence and colorectal polyps.

Pyloric Gastric Adenoma: Endoscopic Detection, Removal, and Echoendosonographic Characterization

Pyloric gland adenomas (PGAs) are rare neoplasms found not only in the gastrointestinal tract but also in other extragastrointestinal organs. They have potential for malignant conversion, and early detection and removal is imperative to prevent invasive disease. PGAs prove difficult in management and surveillance given their rarity. However, increasing familiarity with histological appearance and use of advanced tools such as echoendosonography can bring greater understanding of their clinical history. We describe a unique case of a PGA detected within a hiatal hernia sac characterized with echoendosonography and highlight the need to develop surveillance protocols for these types of lesions.

Novel technique for management of Bouveret syndrome

Video 1Endoscopic treatment of a Bouveret syndrome showing and describing the techniques and procedures involved.

Enhanced suction for removal of esophageal food impaction

Video 1Enhanced suction for removal of esophageal food impaction.

Natural orifice transendoscopic surgery as a rescue for a dislodged lumen-apposing metal stent in the peritoneum after successful EUS-directed transgastric ERCP

Video 1Natural orifice transendoscopic surgery as a rescue for a dislodged lumen-apposing metal stent after EUS-directed transgastric ERCP.

Novel through-the-scope suture closure of colonic EMR defects (with video)

BACKGROUND AND AIMS

Large colon polyps removed by EMR can be complicated by delayed bleeding. Prophylactic defect clip closure can reduce post-EMR bleeding. Larger defects can be challenging to close using through-the-scope clips (TTSCs), and proximal defects are difficult to reach using over-the-scope techniques. A novel, through-the-scope suturing (TTSS) device allows direct closure of mucosal defects without scope withdrawal. The goal of this study was to evaluate the rate of delayed bleeding after the closure of large colon polyp EMR sites with TTSS.

METHODS

A multicenter retrospective cohort study was performed involving 13 centers. All defect closure by TTSS after EMR of colon polyps ≥2 cm from January 2021 to February 2022 were included. The primary outcome was rate of delayed bleeding.

RESULTS

A total of 94 patients (52% female; mean age, 65 years) underwent EMR of predominantly right-sided (n = 62 [66%]) colon polyps (median size, 35 mm; interquartile range, 30-40 mm) followed by defect closure with TTSS during the study period. All defects were successfully closed with TTSS alone (n = 62 [66%]) or with TTSS and TTSCs (n = 32 [34%]), using a median of 1 (interquartile range, 1-1) TTSS system. Delayed bleeding occurred in 3 patients (3.2%), with 2 requiring repeated endoscopic evaluation/treatment (moderate).

CONCLUSION

TTSS alone or with TTSCs was effective in achieving complete closure of all post-EMR defects, despite a large lesion size. After TTSS closure with or without adjunctive devices, delayed bleeding was seen in 3.2% of cases. Further prospective studies are needed to validate these findings before wider adoption of TTSS for large polypectomy closure.

Deploying automated machine learning for computer vision projects: a brief introduction for endoscopists

Video 1Deploying automated machine learning for computer vision projects: a brief introduction for endoscopists.

Prospective assessment of the accuracy of ASGE and ESGE guidelines for choledocholithiasis

Background and study aims American Society of Gastrointestinal Endoscopy (ASGE) and European Society of Gastrointestinal Endoscopy (ESGE) guidelines recommend categorizing patients by risk for choledocholithiasis to determine management. The goal of our study was to compare the accuracy of criteria proposed in these guidelines. Patients and methods All patients with suspected choledocholithiasis at our institution were prospectively identified. Based upon initial test results, patients were categorized as low, intermediate, and high risk for choledocholithiasis per ASGE 2010 and 2019, and ESGE criteria. Patients were followed until 30 days post-discharge. Results of endoscopic retrograde cholangiography (ERCP), endoscopic ultrasound, and magnetic resonance cholangiopancreatography were used as criteria standard for choledocholithiasis. The accuracy of each criterion for choledocholithiasis was computed. Results During the study period, 359 consecutive patients with suspected choledocholithiasis were identified, of whom 225 had choledocholithiasis. Median patient age was 69 years and 55.3% were women. ESGE criteria categorized 47.9% as high-risk, lower than ASGE 2010 (62.7%, P <0.01), and 2019 criteria (54.6%, P =0.07). In high-risk patients, choledocholithiasis was noted in 83.1% for ESGE criteria, similar for ASGE 2019 (81.6%, P =0.7) and 2010 criteria (79.1%, P =0.3). The percentage of patients who underwent unnecessary ERCP was 8.1% per ESGE criteria, lower than ASGE 2010 (13.1%, P =0.03), but similar to 2019 criteria (10%, P =0.4). No difference in accuracy for choledocholithiasis was noted among the three criteria. No 30-day readmissions for choledocholithiasis were noted in the low-risk category. Conclusions ESGE and ASGE guidelines have similar accuracy for diagnosis of choledocholithiasis. However, ESGE criteria result in more patients needing additional testing, but also a smaller proportion of patients undergoing unnecessary ERCP.

Consensus guidelines for the perioperative management of patients undergoing endoscopic retrograde cholangiopancreatography

Deep sedation without tracheal intubation (monitored anaesthesia care) and general anaesthesia with tracheal intubation are commonly used anaesthesia techniques for endoscopic retrograde cholangiopancreatography (ERCP). There are distinct pathophysiological differences between monitored anaesthesia care and general anaesthesia that need to be considered depending on the nature and severity of the patient's underlying disease, comorbidities, and procedural risks. An international group of expert anaesthesiologists and gastroenterologists created clinically relevant questions regarding the merits and risks of monitored anaesthesia care vs general anaesthesia in specific clinical scenarios for planning optimal anaesthetic approaches for ERCP. Using a modified Delphi approach, the group created practical recommendations for anaesthesiologists, with the aim of reducing the incidence of perioperative adverse outcomes while maximising healthcare resource utilisation. In the majority of clinical scenarios analysed, our expert recommendations favour monitored anaesthesia care over general anaesthesia. Patients with increased risk of pulmonary aspiration and those undergoing prolonged procedures of high complexity were thought to benefit from general anaesthesia with tracheal intubation. Patient age and ASA physical status were not considered to be factors for choosing between monitored anaesthesia care and general anaesthesia. Monitored anaesthesia care is the favoured anaesthesia plan for ERCP. An individual risk-benefit analysis that takes into account provider and institutional experience, patient comorbidities, and procedural risks is also needed.

Speedometer for withdrawal time monitoring during colonoscopy: a clinical implementation trial

OBJECTIVES

Meticulous inspection of the mucosa during colonoscopy, represents a lengthier withdrawal time, but has been shown to increase adenoma detection rate (ADR). We investigated if artificial intelligence-aided speed monitoring can improve suboptimal withdrawal time.

METHODS

We evaluated the implementation of a computer-aided speed monitoring device during colonoscopy at a large academic endoscopy center. After informed consent, patients ≥18 years undergoing colonoscopy between 5 March and 29 April 2021 were examined without the use of the speedometer, and with the speedometer between 29 April and 30 June 2021. All colonoscopies were recorded, and withdrawal time was assessed based on the recordings in a blinded fashion. We compared mean withdrawal time, percentage of withdrawal time ≥6 min, and ADR with and without the speedometer.

RESULTS

One hundred sixty-six patients in each group were eligible for analyses. Mean withdrawal time was 9 min and 6.6 s (95% CI: 8 min and 34.8 s to 9 min and 39 s) without the use of the speedometer, and 9 min and 9 s (95% CI: 8 min and 45 s to 9 min and 33.6 s) with the speedometer; difference 2.3 s (95% CI: -42.3-37.7, p = 0.91). The ADRs were 45.2% (95% CI: 37.6-52.8) without the speedometer as compared to 45.8% (95% CI: 38.2-53.4) with the speedometer (p = 0.91). The proportion of colonoscopies with withdrawal time ≥6 min without the speedometer was 85.5% (95% CI: 80.2-90.9) versus 86.7% (95% CI: 81.6-91.9) with the speedometer (p = 0.75).

CONCLUSIONS

Use of speed monitoring during withdrawal did not increase withdrawal time or ADR in colonoscopy.

CLINICALTRIALS.GOV IDENTIFIER

NCT04710251.

Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials

BACKGROUND AND AIMS

Artificial intelligence (AI) tools aimed at improving polyp detection have been shown to increase the adenoma detection rate during colonoscopy. However, it is unknown how increased polyp detection rates by AI affect the burden of patient surveillance after polyp removal.

METHODS

We conducted a pooled analysis of 9 randomized controlled trials (5 in China, 2 in Italy, 1 in Japan, and 1 in the United States) comparing colonoscopy with or without AI detection aids. The primary outcome was the proportion of patients recommended to undergo intensive surveillance (ie, 3-year interval). We analyzed intervals for AI and non-AI colonoscopies for the U.S. and European recommendations separately. We estimated proportions by calculating relative risks using the Mantel-Haenszel method.

RESULTS

A total of 5796 patients (51% male, mean 53 years of age) were included; 2894 underwent AI-assisted colonoscopy and 2902 non-AI colonoscopy. When following U.S. guidelines, the proportion of patients recommended intensive surveillance increased from 8.4% (95% CI, 7.4%-9.5%) in the non-AI group to 11.3% (95% CI, 10.2%-12.6%) in the AI group (absolute difference, 2.9% [95% CI, 1.4%-4.4%]; risk ratio, 1.35 [95% CI, 1.16-1.57]). When following European guidelines, it increased from 6.1% (95% CI, 5.3%-7.0%) to 7.4% (95% CI, 6.5%-8.4%) (absolute difference, 1.3% [95% CI, 0.01%-2.6%]; risk ratio, 1.22 [95% CI, 1.01-1.47]).

CONCLUSIONS

The use of AI during colonoscopy increased the proportion of patients requiring intensive colonoscopy surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively). While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs.

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.

Use of a novel articulation arm device for endoscopic submucosal dissection of a rectal laterally spreading tumor

Video 1.

In vivo detection of bile duct pre-cancer with endoscopic light scattering spectroscopy

Bile duct cancer is the second most common primary liver cancer, with most diagnoses occurring in the advanced stages. This leads to a poor survival rate, which means a technique capable of reliably detecting pre-cancer in the bile duct is urgently required. Unfortunately, radiological imaging lacks adequate accuracy for distinguishing dysplastic and benign biliary ducts, while endoscopic techniques, which can directly assess the bile duct lining, often suffer from insufficient sampling. Here, we report an endoscopic optical light scattering technique for clinical evaluation of the malignant potential of the bile duct. This technique employs an ultraminiature spatial gating fiber optic probe compatible with cholangioscopes and endoscopic retrograde cholangiopancreatography (ERCP) catheters. The probe allowed us to investigate the internal cellular composition of the bile duct epithelium with light scattering spectroscopy (LSS) and phenotypic properties of the underlying connective tissue with diffuse reflectance spectroscopy (DRS). In a pilot in vivo double-blind prospective study involving 29 patients undergoing routine ERCP procedures, the technique detected malignant transformation with 97% accuracy, showing that biliary duct pre-cancer can be reliably identified in vivo non-invasively.

Validating the Simplified Endoscopic Mucosal Assessment for Crohn's Disease: A Novel Method for Assessing Disease Activity

BACKGROUND

To demonstrate treatment efficacy in Crohn's disease (CD), regulatory authorities require that trials include an endoscopic remission/response end point; however, standardized endoscopic assessment of disease activity, such as the Simple Endoscopic Score for Crohn's Disease (SES-CD), is not typically recorded by clinicians in practice or outside of clinical trials. The novel Simplified Endoscopic Mucosal Assessment for Crohn's Disease (SEMA-CD) was developed to be easy to use in routine clinical practice and as a trial end point. We conducted a study to assess and validate the reliability and feasibility of SEMA-CD as a measure of endoscopic disease activity.

METHODS

Pre- and post-treatment ileocolonoscopy videos of pediatric (n = 36) and adult (n = 74) CD patients from 2 ustekinumab clinical trials were each scored with SEMA-CD by 2 to 3 professional central readers, blinded to clinical history and other video scorings; the correlation between SEMA-CD and SES-CD previously completed during the trials was assessed. Sensitivity to change, inter- and intrarater reliability, and comparative ease of scoring were also assessed.

RESULTS

The SEMA-CD strongly correlated with SES-CD (Spearman ρ = 0.89; 95% confidence interval, 0.86-0.92). Pre- to post-treatment changes in SEMA-CD vs in SES-CD were strongly correlated, and the correlation remained strong between the scores when compared by study population (pediatric, adult), disease severity, and video quality. Intra- and inter-rater reliability were good, and SEMA-CD was rated easier than SES-CD to score 63.0% of the time, although slightly more difficult than SES-CD to score <1.0% of the time.

CONCLUSIONS

The SEMA-CD is reliable, reproducible, sensitive to change, and easy to use in both pediatric and adult patients with CD.

Artificial intelligence in gastroenterology and hepatology: how to advance clinical practice while ensuring health equity

Artificial intelligence (AI) and machine learning (ML) systems are increasingly used in medicine to improve clinical decision-making and healthcare delivery. In gastroenterology and hepatology, studies have explored a myriad of opportunities for AI/ML applications which are already making the transition to bedside. Despite these advances, there is a risk that biases and health inequities can be introduced or exacerbated by these technologies. If unrecognised, these technologies could generate or worsen systematic racial, ethnic and sex disparities when deployed on a large scale. There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of oesophageal cancer, management of inflammatory bowel disease (IBD), liver transplantation, colorectal cancer screening and many others. This review adapts a framework for ethical AI/ML development and application to gastroenterology and hepatology such that clinical practice is advanced while minimising bias and optimising health equity.

Deep Learning Computer-aided Polyp Detection Reduces Adenoma Miss Rate: A United States Multi-center Randomized Tandem Colonoscopy Study (CADeT-CS Trial)

BACKGROUND & AIMS

Artificial intelligence-based computer-aided polyp detection (CADe) systems are intended to address the issue of missed polyps during colonoscopy. The effect of CADe during screening and surveillance colonoscopy has not previously been studied in a United States (U.S.) population.

METHODS

We conducted a prospective, multi-center, single-blind randomized tandem colonoscopy study to evaluate a deep-learning based CADe system (EndoScreener, Shanghai Wision AI, China). Patients were enrolled across 4 U.S. academic medical centers from 2019 through 2020. Patients presenting for colorectal cancer screening or surveillance were randomized to CADe colonoscopy first or high-definition white light (HDWL) colonoscopy first, followed immediately by the other procedure in tandem fashion by the same endoscopist. The primary outcome was adenoma miss rate (AMR), and secondary outcomes included sessile serrated lesion (SSL) miss rate and adenomas per colonoscopy (APC).

RESULTS

A total of 232 patients entered the study, with 116 patients randomized to undergo CADe colonoscopy first and 116 patients randomized to undergo HDWL colonoscopy first. After the exclusion of 9 patients, the study cohort included 223 patients. AMR was lower in the CADe-first group compared with the HDWL-first group (20.12% [34/169] vs 31.25% [45/144]; odds ratio [OR], 1.8048; 95% confidence interval [CI], 1.0780-3.0217; P = .0247). SSL miss rate was lower in the CADe-first group (7.14% [1/14]) vs the HDWL-first group (42.11% [8/19]; P = .0482). First-pass APC was higher in the CADe-first group (1.19 [standard deviation (SD), 2.03] vs 0.90 [SD, 1.55]; P = .0323). First-pass ADR was 50.44% in the CADe-first group and 43.64 % in the HDWL-first group (P = .3091).

CONCLUSION

In this U.S. multicenter tandem colonoscopy randomized controlled trial, we demonstrate a decrease in AMR and SSL miss rate and an increase in first-pass APC with the use of a CADe-system when compared with HDWL colonoscopy alone.

EUS imaging for the diagnosis of nonalcoholic fatty liver disease

BACKGROUND AND AIMS

EUS is increasingly used to evaluate patients with liver disease, but its role in assessing hepatic steatosis has not been reported. The goal of our study was to assess the accuracy of EUS for diagnosing hepatic steatosis.

METHODS

We identified all patients who underwent EUS-guided liver biopsy sampling at our institution. All digitally stored EUS liver images were reviewed by a single radiologist, who rated the severity of liver echogenicity using a 4-point US scale. Liver biopsy specimens for all study patients were reviewed by a single liver pathologist, who rated them for steatosis and fibrosis using Nonalcoholic Steatohepatitis Clinical Research Network criteria. Receiver operator characteristic curves were used to assess the diagnostic accuracy of EUS for hepatic steatosis for all patients and in a subgroup analysis for obese and nonobese patients.

RESULTS

During the study period, 76 patients underwent EUS-guided liver biopsy sampling. The average age of study patients was 56.5 years, 50% were women, and 43.2% were obese. The accuracy for EUS for the diagnosis of hepatic steatosis was .8 (95% confidence interval [CI], .7-.89). The accuracy of EUS for the diagnosis of hepatic steatosis in obese patients was .93 (95% CI, .8-.99) and in nonobese patients was .69 (95% CI, .54-.83). For obese patients, EUS had a positive predictive value of 89.7% and a negative predictive value of 75%. The finding of course echotexture on EUS had an accuracy of 79% for the diagnosis of grade 3 fibrosis or cirrhosis.

CONCLUSIONS

EUS is a useful tool for the diagnosis of hepatic steatosis, particularly in obese patients in whom abdominal US has modest accuracy.

Charting a path forward for clinical research in artificial intelligence and gastroenterology

Gastroenterology has been an early leader in bridging the gap between artificial intelligence (AI) model development and clinical trial validation, and in recent years we have seen the publication of several randomized clinical trials examining the role of AI in gastroenterology. As AI applications for clinical medicine advance rapidly, there is a clear need for guidance surrounding AI-specific study design, evaluation, comparison, analysis and reporting of results. Several initiatives are in the publication or pre-publication phase including AI-specific amendments to minimum reporting guidelines for clinical trials, society task force initiatives aimed at priority use cases and research priorities, and minimum reporting guidelines that guide the reporting of clinical prediction models. In this paper, we examine applications of AI in clinical trials and discuss elements of newly published AI-specific extensions to the Consolidated Standards of Reporting Trials and Standard Protocol Items: Recommendations for Interventional Trials statements that guide clinical trial reporting and development. We then review AI applications at the pre-trial level in both endoscopy and other subfields of gastroenterology and explore areas where further guidance is needed to supplement the current guidance available at the pre-trial level.

Organoid Sensitivity Correlates with Therapeutic Response in Patients with Pancreatic Cancer

PURPOSE

Pancreatic ductal adenocarcinoma (PDAC) remains a significant health issue. For most patients there are no options for targeted therapy and existing treatments are limited by toxicity. The HOPE trial (Harnessing Organoids for PErsonalized Therapy) was a pilot feasibility trial aiming to prospectively generate patient derived organoids (PDOs) from patients with PDAC and test their drug sensitivity and correlation with clinical outcomes.

EXPERIMENTAL DESIGN

PDOs were established from a heterogeneous population of patients with PDAC including both basal and classical PDAC subtypes.

RESULTS

A method for classifying PDOs as sensitive or resistant to chemotherapy regimens was developed to predict the clinical outcome of study subjects. Drug sensitivity testing on PDOs correlated with clinical responses to treatment in individual patients.

CONCLUSION

These data support the investigation of PDOs to guide treatment in prospective interventional trials in PDAC.

Preloaded 22-gauge fine-needle system facilitates placement of a higher number of fiducials for image-guided radiation therapy compared with traditional backloaded 19-gauge approach

BACKGROUND AND AIMS

Image-guided radiation therapy (IGRT) often relies on EUS-guided fiducial markers. Previously used manually backloaded fiducial needles have multiple potential limitations including safety and efficiency concerns. Our aim was to evaluate the efficacy, feasibility, and safety of EUS-guided placement of gold fiducials using a novel preloaded 22-gauge needle compared with a traditional, backloaded 19-gauge needle.

METHODS

This was a single-center comparative cohort study. Patients with pancreatic and hepatobiliary malignancy who underwent EUS-guided fiducial placement (EUS-FP) between October 2014 and February 2018 were included. The main outcome was the technical success of fiducial placement. Secondary outcomes were mean procedure time, fiducial visibility during IGRT, technical success of IGRT delivery, and adverse events.

RESULTS

One hundred fourteen patients underwent EUS-FP during the study period. Of these, 111 patients had successful placement of a minimum of 2 fiducials. Fifty-six patients underwent placement using a backloaded 19-gauge needle and 58 patients underwent placement using a 22-gauge preloaded needle. The mean number of fiducials placed successfully at the target site was significantly higher in the 22-gauge group compared with the 19-gauge group (3.53 ± .96 vs 3.11 ± .61, respectively; P = .006). In the 22-gauge group, the clinical goal of placing 4 fiducials was achieved in 78%, compared with 23% in the 19-gauge group (P < .001). In univariate analyses, gender, age, procedure time, tumor size, and location did not influence the number of successfully placed fiducials. Technical success of IGRT with fiducial tracking was high in both the 19-gauge (51/56, 91%) and the 22-gauge group (47/58, 81%; P = .12).

CONCLUSIONS

EUS-FP using a preloaded 22-gauge needle is feasible, effective, and safe and allows for a higher number of fiducials placed when compared with the traditional backloaded 19-gauge needle.

A Polyp Worth Removing: A Paradigm for Measuring Colonoscopy Quality and Performance of Novel Technologies for Polyp Detection

Leaving no significant polyp behind while avoiding risks due to unnecessary resections is a commonsense strategy to safely and effectively prevent colorectal cancer (CRC) with colonoscopy. It also alludes to polyps worth removing and, therefore, worth finding. The majority of "worthy" precancerous polyps are adenomas, which for over 2 decades, have received the most attention in performance research and metrics. Consequently, the detection rate of adenomas is currently the only validated, outcome-based measure of colonoscopy demonstrated to correlate with reduced risk of postcolonoscopy CRC. However, a third or more of postcolonoscopy CRCs originate from sessile serrated polyps (SSPs), which are notoriously difficult to find, diagnose and completely resect. Among serrated polyps, the agreement among pathologists differentiating SSPs from non-neoplastic hyperplastic polyps is moderate at best. This lack of ground truth precludes SSPs from consideration in primary metrics of colonoscopy quality or performance of novel polyp detection technologies. By instead leveraging the distinct endoscopic and clinical features of serrated polyps, including those considered important due to proximal location and larger size, clinically significant serrated polyps represent serrated polyps worth removing, enriched with subtle precancerous SSPs. With the explosion of technologies to assist polyp detection, now is the time to broaden benchmarks to include clinically significant serrated polypss alongside adenomas, a measure that is relevant both for assessing the performance of endoscopists, and for assessing new polyp detection technologies.

Adoption of New Technologies: Artificial Intelligence

Over the past decade, artificial intelligence (AI) has been broadly applied to many aspects of human life, with recent groundbreaking successes in facial recognition, natural language processing, autonomous driving, and medical imaging. Gastroenterology has applied AI to a vast array of clinical problems, and some of the earliest prospective trials examining AI in medicine have been in computer vision applied to endoscopy. Evidence is mounting for 2 broad areas of AI as applied to gastroenterology: computer-aided detection and computer-aided diagnosis.

Benchmarking definitions of false-positive alerts during computer-aided polyp detection in colonoscopy

BACKGROUND

The occurrence of false-positive alerts is an important outcome measure in computer-aided colon polyp detection (CADe) studies. However, there is no consensus definition of a false positive in clinical trials evaluating CADe in colonoscopy. We aimed to study the diagnostic performance of CADe based on different threshold definitions for false-positive alerts.

METHODS

A previously validated CADe system was applied to screening/surveillance colonoscopy videos. Different thresholds for false-positive alerts were defined based on the time an alert box was continuously traced by the system. Primary outcomes were false-positive results and specificity using different threshold definitions of false positive.

RESULTS

62 colonoscopies were analyzed. CADe specificity and accuracy were 93.2 % and 97.8 %, respectively, for a threshold definition of ≥ 0.5 seconds, 98.6 % and 99.5 % for a threshold definition of ≥ 1 second, and 99.8 % and 99.9 % for a threshold definition of ≥ 2 seconds.

CONCLUSION

Our analysis demonstrated how different threshold definitions of false positive can impact the reported diagnostic performance of CADe for colon polyp detection.

Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method

BACKGROUND : Artificial intelligence (AI) research in colonoscopy is progressing rapidly but widespread clinical implementation is not yet a reality. We aimed to identify the top implementation research priorities. METHODS : An established modified Delphi approach for research priority setting was used. Fifteen international experts, including endoscopists and translational computer scientists/engineers, from nine countries participated in an online survey over 9 months. Questions related to AI implementation in colonoscopy were generated as a long-list in the first round, and then scored in two subsequent rounds to identify the top 10 research questions. RESULTS : The top 10 ranked questions were categorized into five themes. Theme 1: clinical trial design/end points (4 questions), related to optimum trial designs for polyp detection and characterization, determining the optimal end points for evaluation of AI, and demonstrating impact on interval cancer rates. Theme 2: technological developments (3 questions), including improving detection of more challenging and advanced lesions, reduction of false-positive rates, and minimizing latency. Theme 3: clinical adoption/integration (1 question), concerning the effective combination of detection and characterization into one workflow. Theme 4: data access/annotation (1 question), concerning more efficient or automated data annotation methods to reduce the burden on human experts. Theme 5: regulatory approval (1 question), related to making regulatory approval processes more efficient. CONCLUSIONS : This is the first reported international research priority setting exercise for AI in colonoscopy. The study findings should be used as a framework to guide future research with key stakeholders to accelerate the clinical implementation of AI in endoscopy.

Two-photon polymerization nanofabrication of ultracompact light scattering spectroscopic probe for detection of pre-cancer in pancreatic cyst

Pancreatic cancer has one of the worst survival rates of all major cancers, with pancreatic cystic lesions accounting for one in three pancreatic surgeries. The current gold-standard for diagnosis of pancreatic cyst malignancy is based on the endoscopic ultrasound guided fine-needle aspiration (EUS-FNA) procedure, which suffers from a low accuracy in detecting malignancy. Here we present the design and two-photon polymerization based fabrication of refractive and reflective non-contact probes, capable of rapid surveillance of the entire internal cyst surface-an advance over the contact probe we recently developed that allowed, for the first time, reliable evaluation of pancreatic cyst malignant potential in vivo. We employed a novel two-photon polymerization technique, which allows direct laser-writing to an accuracy of tens of nanometers, to fit the probe within the 540 micrometer internal diameter EUS-FNA needle. The newly constructed probes show excellent separation of the illumination and collection beams, essential for proper operation of the spatial gating method. These probes can be used clinically to perform rapid "optical biopsy", ultimately eliminating unnecessary pancreatic surgeries on benign cysts and dangerous delays in surgical removal of malignant cysts, improving patient prognosis and quality of life.

How Would You Manage This Patient With Nonvariceal Upper Gastrointestinal Bleeding? : Grand Rounds Discussion From Beth Israel Deaconess Medical Center

Nonvariceal upper gastrointestinal bleeding is common, morbid, and potentially fatal. Cornerstones of inpatient management include fluid resuscitation; blood transfusion; endoscopy; and initiation of proton-pump inhibitor therapy, which continues in an individualized manner based on risk factors for recurrent bleeding in the outpatient setting. The International Consensus Group released guidelines on the management of nonvariceal upper gastrointestinal bleeding in 2019. These guidelines provide a helpful, evidence-based roadmap for management of gastrointestinal bleeding but leave certain management details to the discretion of the treating physician. Here, 2 gastroenterologists consider the care of a patient with nonvariceal upper gastrointestinal bleeding from a peptic ulcer, specifically debating approaches to blood transfusion and endoscopy timing in the hospital, as well as the recommended duration of proton-pump inhibitor therapy after discharge.

Patient Perspective on Safety of Elective Gastrointestinal Endoscopy During the COVID-19 Pandemic

Background

Patients' perception regarding the risks of COVID-19 infection with gastrointestinal (GI) and the preventive measures taken in GI endoscopy units to mitigate infection risk remains unclear. We aimed to assess patients' perception regarding risks of COVID-19 with GI endoscopy and the changes in the endoscopy unit as a result of the ongoing pandemic.

Methods

Outpatients undergoing GI endoscopy at our institution were categorized into those scheduled to undergo GI endoscopy (preprocedure) and those who had recently undergone GI endoscopy during the pandemic (postprocedure). Two separate but similar survey instruments were designed. Patients were asked to respond on a 5-point Likert scale. Responses were stratified as "low," "neutral," and "high" for analysis.

Results

A total of 150 and 355 respondents completed the preprocedure and postprocedure surveys, with a combined response rate of 82.5%. Non-white ethnicity was associated with reporting a "high" level of concern for endoscopy related COVID-19 exposure in both the preprocedure (OR 4.09, 95% CI 1.54-10.82) and postprocedure cohorts (OR 2.11, 95% CI 1.04-4.29). 42% of patients in the preprocedure cohort and 11.8% in the postprocedure cohort reported their level of concern for COVID exposure as "high." Among the postprocedure cohort, 88% of the patients were likely to undergo repeat endoscopy during the pandemic if recommended.

Conclusion

Patients are willing to undergo GI endoscopy during the COVID-19 pandemic. Non-white and older patients, and those undergoing screening examinations were more concerned with the GI endoscopy related COVID-19 transmission risk.

Use of fully covered self-expanding metal biliary stents for managing endoscopic biliary sphincterotomy related bleeding

Background and study aims  Endoscopic biliary sphincterotomy (EBS) related-bleeding is a common adverse event related to endoscopic retrograde cholangiopancreatography (ERCP). Traditionally, endoscopic modalities such as epinephrine injection, cauterization, and balloon tamponade have been used for management. Recently, use of a fully covered self-expandable metal stent (FCSEMS) to manage EBS-related bleeding has gained popularity. However, data regarding its use are limited to small case series. Therefore, we aimed to evaluate the safety and efficacy of FCSEMS placement for the treatment of EBS-related bleeding. Patients and methods  All patients referred to our center from October 2014 to November 2019 who had an FCSEMS placed for EBS-related bleeding were included. FCSEMS was placed either for primary control of bleeding or after failure of other traditional endoscopic hemostasis techniques at the discretion of the endoscopist. Data was collected regarding patient demographics, procedural characteristics, clinical and technical success rates of FCSEMS, as well as adverse events. Results  A total of 97 patients underwent placement of FCSEMS for EBS-related bleeding, of which 76.3 % had immediate bleeding and 23.7 % had delayed bleeding. Mean age was 67.2 years and 47.4 % were males. Seven patients who had immediate EBS-related bleeding at index ERCP underwent other endoscopic therapies prior to placement of FCSEMS for rebleeding. The technical success rate for FCSEMS placement was 100 % and the rebleeding rate was 6.2 %. Four patients with FCSEMS placement developed pancreatitis and four had stent migration. Conclusions  Our findings suggest that FCSEMS is a highly effective treatment modality for managing EBS-related bleeding and has an acceptable safety profile.

Gender disparities in advanced endoscopy fellowship

Background and study aims  Women remain underrepresented in gastroenterology, especially advanced endoscopy. Women represent 30 % of general gastroenterology fellows; yet in 2019, only 12.8 % of fellows who matched into advanced endoscopy fellowship (AEF) programs were women. Methods  We administered a web-based survey to the program directors (PDs) of AEF programs that participated in the 2018-2019 American Society for Gastroenterology (ASGE) match. We assessed PD and program characteristics, in addition to perceived barriers and facilitators (scale 1-5, 5 = most important) influencing women pursuing AEF training. Results  We received 38 (59.3 %) responses from 64 PDs. 15.8 % (6/38) of AEF PDs and 13.2 % (5/38) of endoscopy chiefs were women. By program, women represented 14.8 % (mean) ± 17.0 % (SD) of AEF faculty and 12.0 % (mean) ± 11.1 % (SD) of AEF trainees over the past 10 years. 47.4 % (18/38) programs reported no female advanced endoscopy faculty and 31.6 % (12/38) of programs have never had a female fellow. Percentage of female fellows was strongly associated with percentage of female AEF faculty (ß = 0.43, P  < 0.001). Inflexible hours and call (mean rank 3.3 ± 1.1), exposure to fluoroscopy (2.9 ± 1.1), lack of women endoscopists at national conferences/courses (2.9 ± 1.1) and lack of female mentorship (2.9 ± 1.0) were cited as the most important barriers to recruitment. Conclusion  We utilized a survey of AEF PDs participating in the ASGE match to determine program characteristics and identify contributors to gender disparity. Women represent a minority of AEF PDs, endoscopy chiefs, advanced endoscopy faculty and AEF trainees. Our study highlights perceived barriers and facilitators to recruitment, and emphasizes the importance of having female representation in faculty, and leadership positions in endoscopy.

Lumen-apposing covered self-expanding metallic stent for symptomatic pancreatic fluid collections: assessment of outcomes and complications with CT and MRI

PURPOSE

To assess technical and clinical outcomes following lumen-apposing covered self-expanding metallic stent (LAMS) placement for symptomatic pancreatic fluid collections (PFC) with CT and MRI.

METHODS

In this retrospective study, patients with PFC who underwent LAMS placement between March 2015 and June 2018 were included. Primary outcomes included technical success, defined as successful stent placement with resolution of PFC, and clinical success, defined as lack of fluid recurrence after stent removal. Secondary outcomes included time duration from stent placement to removal, complications, and re-intervention need.

RESULTS

28 consecutive patients (20 men, mean age: 53 years ± 17; range 21-75) who underwent endoscopic drainage of symptomatic walled-off necrosis (WON, 21/28, 75%), pseudocyst (PC, 5/28, 18%) or acute necrotic collection (ANC, 2/28, 7%) were included. LAMS were placed successfully in 27/28 (96%) patients. On follow-up imaging after at least one month (n = 24), the volume of the PFC decreased by 99.9% from 425 cm³ [IQR 214 - 636] to 0.6 cm³ [IQR 0-43.9]. After stent removal, 26/27 (96%) patients remained collection free. The median time duration from stent placement to removal was 42 days [IQR 34-71]. Complications (10/28; 36%) included stent occlusion (n = 1), stent migration (n = 3), intraprocedural bleeding (n = 2), postprocedural bleeding (n = 2), and pseudoaneurysm formation (n = 2). Re-intervention was required in 7/27 (26%).

CONCLUSION

Following LAMS placement in patients with symptomatic PFC, high technical and clinical success rates of 96% and 96%, respectively, are achieved. Awareness of common complications seen on cross-sectional imaging might help radiologists and gastroenterologist in the patients' management.

Luminal-apposing stents for benign intraluminal strictures: a large United States multicenter study of clinical outcomes

Background

The use of fully covered lumen-apposing metal stents (LAMS) for benign short gastrointestinal (GI) strictures has been reported. This study aimed to evaluate the safety and efficacy of LAMS for refractory GI strictures.

Methods

A retrospective analysis was performed of patients who underwent LAMS placement for benign GI strictures in 8 United States centers. The primary outcomes were technical success and initial clinical response. Secondary outcomes were reintervention rate and adverse events.

Results

A total of 51 patients underwent 61 LAMS placement procedures; 33 (64.7%) had failed previous treatments. The most common stricture location was the pylorus (n=17 patients). Various sizes of stents were used, with 15-mm LAMS placed in 45 procedures, 20-mm LAMS in 14 procedures, and 10-mm LAMS in 2 procedures. The overall technical success, short-term clinical response and reintervention rate after stent removal were 100%, 91.8% and 31.1%, respectively. Adverse events were reported in 17 (27.9%) procedures, with stent migration being the most common (13.1%). In subgroup analysis, both 15 mm and 20 mm stents had comparable short-term clinical response and adverse event rates. However, stent migration (15.6%) was the most common adverse event with 15-mm LAMS while pain (14.3%) was the most common with 20-mm LAMS. The reintervention rate was 80% at 200-day follow up after stent removal.

Conclusions

Using LAMS for treatment of short benign GI strictures is safe and effective. Larger LAMS, such as the new 20 mm in diameter, may have a lower stent migration rate compared to smaller diameter LAMS.

Triage of General Gastrointestinal Endoscopic Procedures During the COVID-19 Pandemic: Results From a National Delphi Consensus Panel

Background and Aims

As the COVID-19 pandemic moves into the postpeak period, the focus has now shifted to resuming endoscopy services to meet the needs of patients who were deferred. By using a modified Delphi process, we sought to develop a structured framework to provide guidance regarding procedure indications and procedure time intervals.

Methods

A national panel of 14 expert gastroenterologists from throughout the US used a modified Delphi process, to achieve consensus regarding: (1) common indications for general endoscopy, (2) critical patient-important outcomes for endoscopy, (3) defining time-sensitive intervals, (4) assigning time-sensitive intervals to procedure indications. Two anonymous rounds of voting were allowed before attempts at consensus were abandoned.

Results

Expert panel reached consensus that procedures should be allocated to one of three timing categories: (1) time-sensitive emergent = scheduled within 1 week, (2) time-sensitive urgent = scheduled within 1-8 weeks, (3) nontime sensitive = defer to > 8 weeks and reassess timing then. The panel identified 62 common general endoscopy indications (33 for EGD, 21 for colonoscopy, 5 for sigmoidoscopy). Consensus was reached on patient-important outcomes for each procedure indication, and consensus regarding timing of the procedure indication was achieved for 74% of indications. Panelists also identified adequate personal-protective-equipment, rapid point-of-care testing, and staff training as critical preconditions before endoscopy services could be resumed.

Conclusion

We used the validated Delphi methodology, while prioritized patient-important outcomes, to provide consensus recommendations regarding triaging a comprehensive list of general endoscopic procedures.

The single-monitor trial: an embedded CADe system increased adenoma detection during colonoscopy: a prospective randomized study

BACKGROUND

Computer-aided detection (CADe) of colon polyps has been demonstrated to improve colon polyp and adenoma detection during colonoscopy by indicating the location of a given polyp on a parallel monitor. The aim of this study was to investigate whether embedding the CADe system into the primary colonoscopy monitor may serve to increase polyp and adenoma detection, without increasing physician fatigue level.

METHODS

Consecutive patients presenting for colonoscopies were prospectively randomized to undergo routine colonoscopy with or without the assistance of a real-time polyp detection CADe system. Fatigue level was evaluated from score 0 to 10 by the performing endoscopists after each colonoscopy procedure. The main outcome was adenoma detection rate (ADR).

RESULTS

Out of 790 patients analyzed, 397 were randomized to routine colonoscopy (control group), and 393 to a colonoscopy with computer-aided diagnosis (CADe group). The ADRs were 20.91% and 29.01%, respectively (OR = 1.546, 95% CI 1.116-2.141, p = 0.009). The average number of adenomas per colonoscopy (APC) was 0.29 and 0.48, respectively (Change Folds = 1.64, 95% CI 1.299-2.063, p < 0.001). The improvement in polyp detection was mainly due to increased detection of non-advanced diminutive adenomas, serrated adenoma and hyperplastic polyps. The fatigue score for each procedure was 3.28 versus 3.40 for routine and CADe group, p = 0.357.

CONCLUSIONS

A real-time CADe system employed on the primary endoscopy monitor may lead to improvements in ADR and polyp detection rate without increasing fatigue level during colonoscopy. The integration of a low-latency and high-performance CADe systems may serve as an effective quality assurance tool during colonoscopy. www.chictr.org.cn number, ChiCTR1800018058.

Outcomes after endoscopic retrograde cholangiopancreatography with general anaesthesia versus sedation

BACKGROUND

We tested the primary hypothesis that use of general anaesthesia vs sedation increases vulnerability to adverse discharge (in-hospital mortality or new discharge to a nursing facility) after endoscopic retrograde cholangiopancreatography (ERCP).

METHODS

In this retrospective cohort study, adult patients undergoing ERCP with general anaesthesia or sedation at a tertiary care hospital were included. We calculated adjusted absolute risk differences between patients receiving general anaesthesia vs sedation using provider preference-based instrumental variable analysis. We also used mediation analysis to determine whether intraoperative hypotension during general anaesthesia mediated its effect on adverse discharge.

RESULTS

Among 17 538 patients undergoing ERCP from 2007 through 2018, 16 238 received sedation and 1300 received GA. Rates of adverse discharge were 5.8% (n=938) after sedation and 16.2% (n=210) after general anaesthesia. Providers' adjusted mean predicted probabilities of using general anaesthesia for ERCP ranged from 0.2% to 63.2% of individual caseloads. Utilising provider-related variability in the use of general anaesthesia for instrumental variable analysis resulted in an 8.6% risk increase (95% confidence interval, 4.5-12.6%; P<0.001) in adverse discharge among patients receiving general anaesthesia vs sedation. Intraoperative hypotensive events occurred more often during general anaesthesia and mediated 23.8% (95% confidence interval, 3.9-43.7%: P=0.019) of the primary association.

CONCLUSIONS

These results suggest that use of sedation during ERCP facilitates reduced adverse discharge for patients for whom general anaesthesia is not clearly indicated. Intraoperative hypotension during general anaesthesia for ERCP partly mediates the increased vulnerability to adverse discharge.