AGA Clinical Practice Update on Appropriate and Tailored Polypectomy: Expert Review.

DESCRIPTION: In this Clinical Practice Update (CPU), we provide guidance on the appropriate use of different polypectomy techniques. We focus on polyps <2 cm in size that are most commonly encountered by the practicing endoscopist, including use of classification systems to characterize polyps and various polypectomy methods. We review characteristics of polyps that require complex polypectomy techniques and provide guidance on which types of polyps require more advanced management by a therapeutic endoscopist or surgeon. This CPU does not provide a detailed review of complex polypectomy techniques, such as endoscopic submucosal dissection, which should only be performed by endoscopists with advanced training. METHODS: This expert review was commissioned and approved by the American Gastroenterological Association (AGA) Institute CPU Committee 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 CPU Committee and external peer review through standard procedures of Clinical Gastroenterology and Hepatology. These Best Practice Advice statements were drawn from a review of the published literature and from expert opinion. Because systematic reviews were not performed, these Best Practice Advice statements do not carry formal ratings regarding the quality of evidence or strength of the presented considerations. BEST PRACTICE ADVICE 1: A structured visual assessment using high-definition white light and/or electronic chromoendoscopy and with photodocumentation should be conducted for all polyps found during routine colonoscopy. Closely inspect colorectal polyps for features of submucosally invasive cancer. BEST PRACTICE ADVICE 2: Use cold snare polypectomy for polyps <10 mm in size. Cold forceps polypectomy can alternatively be used for 1- to 3-mm polyps where cold snare polypectomy is technically difficult. BEST PRACTICE ADVICE 3: Do not use hot forceps polypectomy. BEST PRACTICE ADVICE 4: Clinicians should be familiar with various techniques, such as cold and hot snare polypectomy and endoscopic mucosal resection, to ensure effective, safe, and optimal resection of intermediate-size polyps (10-19 mm). BEST PRACTICE ADVICE 5: Consider using lifting agents or underwater endoscopic mucosal resection for removal of sessile polyps 10-19 mm in size. BEST PRACTICE ADVICE 6: Serrated polyps should be resected using cold resection techniques. Submucosal injection may be helpful for polyps >10 mm if margins cannot be well delineated. BEST PRACTICE ADVICE 7: Use hot snare polypectomy to remove pedunculated lesions >10 mm in size. BEST PRACTICE ADVICE 8: Do not routinely use clips to close resection sites for polyps <20 mm. BEST PRACTICE ADVICE 9: Refer patients with polyps to endoscopic referral centers in the context of size ≥20 mm, challenging polypectomy location, or recurrent polyp at a prior polypectomy site. BEST PRACTICE ADVICE 10: Tattoo lesions that may need future localization at endoscopy or surgery. Tattoos should be placed in a location that will not interfere with subsequent attempts at endoscopic resection. BEST PRACTICE ADVICE 11: Refer patients with nonpedunculated polyps with clear evidence of submucosally invasive cancer for surgical evaluation. BEST PRACTICE ADVICE 12: Understand the endoscopy suite's electrosurgical generator settings appropriate for polypectomy or postpolypectomy thermal techniques.

The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning.

Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. Methods: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. Results: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. Discussion: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved.

Devices for esophageal function testing.

BACKGROUND AND AIMS: Esophageal function testing is an integral component of the evaluation of refractory GERD and esophageal motility disorders. This review summarizes the current technologies available for esophageal function testing, including the functional luminal imaging probe (FLIP), high-resolution esophageal manometry (HRM), and multichannel intraluminal impedance (MII) and pH monitoring. METHODS: We performed a MEDLINE, PubMed, and MAUDE database literature search to identify pertinent clinical studies through March 2021 using the following key words: esophageal manometry, HRM, esophageal impedance, FLIP, MII, and esophageal pH testing. Technical data were gathered from traditional and web-based publications, proprietary publications, and informal communications with pertinent vendors. The report was drafted, reviewed, and edited by the American Society for Gastrointestinal Endoscopy Technology Committee and approved by the Governing Board of the American Society for Gastrointestinal Endoscopy. RESULTS: FLIP is a high-resolution impedance planimetry system used for pressure and dimension measurement in the esophagus, pylorus, and anal sphincter. FLIP provides complementary information to HRM for esophageal motility disorders, especially achalasia. The Chicago classification, based on HRM data, is a widely adopted algorithmic scheme used to diagnose esophageal motility disorders. MII detects intraluminal bolus movement and, combined with pH measurement or manometry, provides information on acid and non-acid gastroesophageal reflux and bolus transit in patients with refractory GERD and for preoperative evaluation for anti-reflux procedures. CONCLUSIONS: Esophageal function testing techniques (FLIP, HRM, and MII-pH) have diagnostic and prognostic value in the evaluation of esophageal motility disorders and refractory GERD. Newer technologies and classification systems have enabled an increased understanding of these diseases.

Deep Learning Methods for Anatomical Landmark Detection in Video Capsule Endoscopy Images.

Video capsule endoscope (VCE) is an emerging technology that allows examination of the entire gastrointestinal (GI) tract with minimal invasion. While traditional endoscopy with biopsy procedures are the gold standard for diagnosis of most GI diseases, they are limited by how far the scope can be advanced in the tract and are also invasive. VCE allows gastroenterologists to investigate GI tract abnormalities in detail with visualization of all parts of the GI tract. It captures continuous real time images as it is propelled in the GI tract by gut motility. Even though VCE allows for thorough examination, reviewing and analyzing up to eight hours of images (compiled as videos) is tedious and not cost effective. In order to pave way for automation of VCE-based GI disease diagnosis, detecting the location of the capsule would allow for a more focused analysis as well as abnormality detection in each region of the GI tract. In this paper, we compared four deep Convolutional Neural Network models for feature extraction and detection of the anatomical part within the GI tract captured by VCE images. Our results showed that VGG-Net has superior performance with the highest average accuracy, precision, recall and, F1-score compared to other state of the art architectures: GoogLeNet, AlexNet and, ResNet.

Endoscopic therapies for gallbladder drainage.

BACKGROUND AND AIMS: Endoscopic management of acute cholecystitis has expanded in patients who are considered nonoperative candidates. Traditionally managed with percutaneous cholecystostomy (PC), improvement in techniques and devices has led to increased use of endoscopic methods for gallbladder drainage. This document reviews technical aspects of endoscopic transpapillary gallbladder drainage (ET-GBD) and EUS-guided GBD (EUS-GBD) as well as their respective technical/clinical success and adverse event rates. Available comparative data are also reviewed among nonsurgical gallbladder drainage techniques (PC, ET-GBD, and EUS-GBD). METHODS: The MEDLINE database was searched through March 2021 for relevant articles by using keywords including "acute cholecystitis," "interventional EUS," "percutaneous cholecystostomy," "transpapillary gallbladder drainage," "EUS-guided gallbladder drainage," "lumen-apposing metal stent," "gallbladder stenting," and "endoscopic gallbladder drainage." The manuscript was drafted by 2 authors and reviewed by members of the American Society for Gastrointestinal Endoscopy Technology Committee and subsequently by the American Society for Gastrointestinal Endoscopy Governing Board. RESULTS: Multiple studies have demonstrated acceptable outcomes comparing PC and both endoscopic gallbladder drainage techniques, ET-GBD and EUS-GBD. Published data suggest that endoscopic gallbladder drainage techniques may be associated with lower rates of adverse events and improved quality of life. However, there are important clinical considerations for choosing among these treatment options, requiring a multidisciplinary and collaborative approach to therapeutic decision-making in these patients. CONCLUSIONS: The implementation of EUS-GBD and ET-GBD in high-risk surgical patients with acute cholecystitis may result in favorable outcomes when compared with PC. Further improvements in techniques and training should lead to more widespread acceptance and dissemination of these treatment options.

Lumen-apposing metal stents (with videos).

BACKGROUND AND AIMS: Lumen-apposing metal stents (LAMSs) are a novel class of devices that have expanded the spectrum of endoscopic GI interventions. LAMSs with their dumbbell configuration, short saddle length, and large inner luminal diameter provide favorable stent characteristics to facilitate anastomosis formation between the gut lumen and adjacent structures. METHODS: The MEDLINE database was searched through April 2021 for articles related to LAMSs by using additional relevant keywords such as "walled-off pancreatic necrosis," "pseudocysts," "pancreatic fluid collection," "cholecystitis," "gastroenterostomy," in addition to "endoscopic treatment" and "endoscopic management," among others. RESULTS: This technology review describes the full spectrum of LAMS designs and delivery systems, techniques for deployment, procedural outcomes, safety, training issues, and financial considerations. CONCLUSIONS: Although LAMSs were initially introduced for drainage of pancreatic pseudocysts and walled-off necrosis, the versatility of these devices has led to a variety of off-label uses including gallbladder drainage, enteric bypass with the creation of gastroenterostomies, and treatment of luminal GI strictures.

Single-use duodenoscopes and duodenoscopes with disposable end caps.

BACKGROUND AND AIMS: Multidrug-resistant infectious outbreaks associated with duodenoscopes have been documented internationally. Single-use duodenoscopes, disposable distal ends, or distal end cap sealants could eliminate or reduce exogenous patient-to-patient infection associated with ERCP. METHODS: This document reviews technologies that have been developed to help reduce or eliminate exogenous infections because of duodenoscopes. RESULTS: Four duodenoscopes with disposable end caps, 1 end sheath, and 2 disposable duodenoscopes are reviewed in this document. The evidence regarding their efficacy in procedural success rates, reduction of duodenoscope bacterial contamination, clinical outcomes associated with these devices, safety, and the financial considerations are discussed. CONCLUSIONS: Several technologies discussed in this document are anticipated to eliminate or reduce exogenous infections during endoscopy requiring a duodenoscope. Although disposable duodenoscopes can eliminate exogenous ERCP-related risk of infection, data regarding effectiveness are needed outside of expert centers. Additionally, with more widespread adoption of these new technologies, more data regarding functionality, medical economics, and environmental impact will accrue. Disposable distal end caps facilitate duodenoscope reprocessing; postmarketing surveillance culture studies and real-life patient infection analyses are important areas of future research.

Association for Bariatric Endoscopy systematic review and meta-analysis assessing the American Society for Gastrointestinal Endoscopy Preservation and Incorporation of Valuable Endoscopic Innovations thresholds for aspiration therapy.

A subcommittee of the Association for Bariatric Endoscopy, a division of the American Society for Gastrointestinal Endoscopy (ASGE) comprising experts in the subject area, performed this systematic review and meta-analysis. The systematic review and meta-analysis was reviewed by the ASGE Technology Committee and was ultimately submitted to the ASGE Governing Board for approval. The systematic review and meta-analysis underwent peer review by outside experts in statistics and meta-analysis before receiving final ASGE Governing Board approval. The Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) initiative is an ASGE program whose objectives are to identify important clinical questions related to endoscopy and to establish a priori diagnostic and/or therapeutic thresholds for endoscopic technologies designed to resolve these clinical questions. Once endoscopic technologies meet an established PIVI threshold, those technologies are appropriate to incorporate into clinical practice, presuming the appropriate training in that endoscopic technology has been achieved. ASGE encourages and supports the appropriate use of technologies that meet its established PIVI thresholds.

Single-Dose Linaclotide Is Equal in Efficacy to Polyethylene Glycol for Bowel Preparation Prior to Capsule Endoscopy.

BACKGROUND: Video capsule endoscopy provides noninvasive visualization of the small bowel, but yield is often limited by debris. At our institution, preparation with polyethylene glycol (PEG) and simethicone is used to improve visualization. AIMS: We hypothesized that linaclotide and simethicone would yield equal to better results. METHODS: We enrolled 29 subjects for the experimental regimen of linaclotide and simethicone. We maintained standard NPO status, clear liquid period, and simethicone dose. Subjects received 290 µg of linaclotide 1 h prior to capsule. We randomly selected 30 historical PEG controls. Two blinded gastroenterologists graded visualization as ideal/excellent, good, fair, or poor and measured small bowel transit time. RESULTS: Thirteen men and 16 women were enrolled with an average age of 61. There was no significant difference in exam quality between linaclotide and control. Preparation was rated as ideal/excellent or good in 19 of 28 of linaclotide and 18 of 28 PEG subjects when recorder entered the small bowel (p = 0.78, chi-square). Median small bowel transit was 192 min (linaclotide) versus 202 min (PEG), respectively (p = 0.93, t test). Three studies (1 linaclotide and 2 PEG) failed to leave the stomach; 1 linaclotide subject had recorder failure. Diagnostic yield was similar (18/29 for linaclotide and 16/30 for PEG, p = 0.50, chi-square). There were no serious side effects. No differences in age, sex, BMI, or frequency of diabetes, GERD, or gastroparesis were measured between the groups. CONCLUSIONS: Single-dose linaclotide 1 h before capsule endoscopy was equally effective when compared to PEG in terms of visualization and transit time. This trial was registered at ClincialTrials.gov, number NCT02465385.

Bowel Obstruction and Hydronephrosis Due to an Over-the-Scope Clip.

An over-the-scope clip is a type of endoscopically placed clip used to treat gastrointestinal perforation, bleeding, or fistula. After the defect heals, the clip usually passes uneventfully through the gastrointestinal tract. An uncommon complication of over-the-scope clip placement is intestinal obstruction caused by luminal stenosis at the site of clip placement. Intestinal obstruction can rarely cause other downstream complications such as hydronephrosis from extrinsic compression of the urinary tract. We report a rare case of bilateral hydronephrosis caused by bowel obstruction from a migrated endoscopically placed clip.

The Esophageal Microbiome in Health and Disease.

PURPOSE OF REVIEW: Investigation of the esophageal microbiome is a relatively new field. This review will outline data characterizing the esophageal microbiome in both health and disease states, including gastroesophageal reflux disease (GERD), Barrett's esophagus, esophageal cancer, eosinophilic esophagitis, and motility disorders. RECENT FINDINGS: While the esophagus was previously considered devoid of a significant bacterial population, development of culture-independent techniques, specifically 16S rRNA gene sequencing, as well as novel, minimally invasive microbial sampling modalities, has facilitated characterization of the esophageal microbiome in both health and several disease states. Although limited, there is evidence that the esophagus contains a diverse microbial population, with Gram-positive bacteria, specifically Streptococcus, dominating in health, while Gram-negative bacteria prevail in reflux disorders including GERD and Barrett's esophagus. The microbiome is altered with other esophageal disorders as well, including eosinophilic esophagitis and esophageal motility disorders, though these changes have been less well characterized. Characterization of the gut microbiome has advanced significantly; however, further investigation is essential. Understanding changes in the esophageal microbiome could affect our understanding of the natural history of diseases of the esophagus and present potential therapeutic approaches.

A comparison of CMV detection in gastrointestinal mucosal biopsies using immunohistochemistry and PCR performed on formalin-fixed, paraffin-embedded tissue.

Cytomegalovirus (CMV) can precipitate and exacerbate gastrointestinal (GI) mucosal injury. The gold standard for CMV detection in formalin-fixed, paraffin-embedded (FFPE) tissue is immunohistochemistry (IHC). Although CMV polymerase chain reaction (PCR) on fresh tissue may be a valuable adjunct to IHC, its utility is unknown for FFPE tissues. We therefore evaluated quantitative, real-time CMV PCR in a total of 102 FFPE GI biopsy specimens from 74 patients with a history of hematopoietic stem cell or solid organ transplant, inflammatory bowel disease, human immunodeficiency virus infection, or unspecified colitis. CMV DNA was detected by PCR in 90.9% (30/33) of IHC-positive, 14.5% (8/55) of IHC-negative, and 20.0% (1/5) of IHC-equivocal FFPE tissues. Quantitation of CMV DNA copies normalized to ß-globin demonstrated a wide range of values (median 0.276; range, 0.0004 to 144.50). Importantly, 93.3% (14/15) of patients with IHC-positive, active colitis showed no evidence of CMV in matched concurrent, histologically normal biopsies tested by PCR. These results suggest that CMV PCR on FFPE GI biopsies complements IHC and has the potential to identify additional patients who may benefit from anti-CMV therapy.

Flash mob research: a single-day, multicenter, resident-directed study of respiratory rate.

BACKGROUND: Vital signs are critical data in the care of hospitalized patients, but the accuracy with which respiratory rates are recorded in this population remains uncertain. We used a novel flash mob research approach to evaluate the accuracy of recorded respiratory rates in inpatients. METHODS: This was a single-day, resident-led, prospective observational study of recorded vs directly observed vital signs in nonventilated patients not in the ICU on internal medicine teaching services at six large tertiary-care centers across the United States. RESULTS: Among the 368 inpatients included, the median respiratory rate was 16 breaths/min for the directly observed values and 18 breaths/min for the recorded values, with a median difference of 2 breaths/min (P < .001). Respiratory rates of 18 or 20 breaths/min accounted for 71.8% (95% CI, 67.1%-76.4%) of the recorded values compared with 13.0% (95% CI, 9.5%-16.5%) of the directly observed measurements. For individual patients, there was less agreement between the recorded and the directly observed respiratory rate compared with pulse rate. CONCLUSIONS: Among hospitalized patients across the United States, recorded respiratory rates are higher than directly observed measurements and are significantly more likely to be 18 or 20 breaths/min.

A tandem colonoscopy study of adenoma miss rates during endoscopic training: a venture into uncharted territory.

BACKGROUND: Tandem colonoscopy is regarded as the reference standard for the evaluation of the adenoma detection rate (ADR) and adenoma miss rate (AMR) during colonoscopy. Pooled results from previous tandem studies yield AMRs of 22%. The AMR of trainees is important to estimate the number of colonoscopies required to develop competence in screening for colorectal neoplasms. OBJECTIVE: To measure the ADR and AMR of trainees as a function of experience. METHODS: Prospective tandem colonoscopy study at an academic VA medical center. A trainee initially attempted colonoscopy. If the trainee was able to intubate the cecum, the trainee performed the withdrawal, and the colonoscopy was then repeated by the attending physician to assess the AMR. RESULTS: Twelve trainee endoscopists were included in the study. Trainees had between 0 and 33 months of previous endoscopic experience and had done between 0 and 605 previous colonoscopies. A total of 230 patients were evaluated for the study, and 218 patients were enrolled. Complete tandem colonoscopy was performed in 147 patients. There was a 54% ADR. The mean (standard deviation) size of the adenomas in the cohort was 5.9 (5.3) mm. Significant variables in multivariate logistic regression analysis for missed adenomas were trainee experience (P = .011) and patient age (P < .001). The AMR decreased with increasing experience, and it is estimated that 450 colonoscopies are required to attain AMRs of less than 25% in a 60-year-old patient. LIMITATIONS: Single-center study; the attending physician performing the second pass was not blinded to the first pass. The AMR was only analyzed for cases in which the trainee was able to reach the cecum with no or minimal assistance. CONCLUSIONS: Our tandem colonoscopy study demonstrates that the AMR decreases as the experience of trainees increases and is a late competency attained during training. Future training may need to incorporate these findings to serve as a basis for determining appropriate training guidelines.