Faculty Bibliography

Sampling error during screening and surveillance endoscopy is a well-recognized problem. Wide-area transepithelial sampling with three-dimensional computer-assisted analysis (WATS3D), used adjunctively to forceps biopsy (FB), has been shown to increase the detection of Barrett's esophagus (BE) and BE-associated neoplasia. We evaluated the clinical utility of WATS3D and its impact on the management of patients with BE and dysplasia. Between 2013 and 2018, 432 consecutive patients who had a WATS3D positive and an accompanying FB negative result were identified. Physicians were contacted to determine if the WATS3D result impacted their decision to enroll patients in surveillance or increase the frequency of surveillance, recommend ablation, and/or initiate or increase the dose of proton pump inhibitors (PPIs). WATS3D directly impacted the management of 97.8% of 317 BE patients; 96.2% were enrolled in surveillance and 60.2% were started on PPIs or their dose was increased. WATS3D impacted the management of 94.9% and 94.1% of the 98 low-grade dysplasia and 17 high-grade dysplasia patients, respectively. As a result of WATS3D, 33.7% of low-grade dysplasia and 70.6% of high-grade dysplasia patients underwent endoscopic therapy. More than 37% of all dysplasia patients were enrolled in a surveillance program, and nearly 30% were scheduled to be surveilled more frequently. PPIs were either initiated, or the dose was increased in more than 54% of all dysplasia patients. We demonstrate that WATS3D has high clinical utility. By prompting physicians to change their clinical management in patients with negative FB results, WATS3D, used adjunctively to FB, directly impacts patient management, and improves patient outcomes.

Background and study aims  The coronavirus disease 2019 (COVID-19), and measures taken to mitigate its impact, have profoundly affected the clinical care of gastroenterology patients and the work of endoscopy units. We aimed to describe the clinical care delivered by gastroenterologists and the type of procedures performed during the early to peak period of the pandemic. Methods  Endoscopy leaders in the New York region were invited to participate in an electronic survey describing operations and clinical service. Surveys were distributed on April 7, 2020 and responses were collected over the following week. A follow-up survey was distributed on April 20, 2020. Participants were asked to report procedure volumes and patient characteristics, as well protocols for staffing and testing for COVID-19. Results  Eleven large academic endoscopy units in the New York City region responded to the survey, representing every major hospital system. COVID patients occupied an average of 54.5 % (18 - 84 %) of hospital beds at the time of survey completion, with 14.5 % (2 %-23 %) of COVID patients requiring intensive care. Endoscopy procedure volume and the number of physicians performing procedures declined by 90 % (66 %-98 %) and 84.5 % (50 %-97 %) respectively following introduction of restricted practice. During this period the most common procedures were EGDs (7.9/unit/week; 88 % for bleeding; the remainder for foreign body and feeding tube placement); ERCPs (5/unit/week; for cholangitis in 67 % and obstructive jaundice in 20 %); Colonoscopies (4/unit/week for bleeding in 77 % or colitis in 23 %) and least common were EUS (3/unit/week for tumor biopsies). Of the sites, 44 % performed pre-procedure COVID testing and the proportion of COVID-positive patients undergoing procedures was 4.6 % in the first 2 weeks and up to 19.6 % in the subsequent 2 weeks. The majority of COVID-positive patients undergoing procedures underwent EGD (30.6 % COVID +) and ERCP (10.2 % COVID +). Conclusions  COVID-19 has profoundly impacted the operation of endoscopy units in the New York region. Our data show the impact of a restricted emergency practice on endoscopy volumes and the proportion of expected COVID positive cases during the peak time of the pandemic.

INTRODUCTION: Telehealth involves the use of electronic information and telecommunications to promote healthcare. Physician experience is critical in assessing the impact of telehealth on clinical outcomes and utilization. Gastroenterologists' use and attitudes towards telehealth are largely unknown. We aimed to identify gastroenterologists' professional attitudes towards their use of telehealth and its effect on patient care during the COVID-19 pandemic.
METHOD(S): We performed a cross sectional survey of outpatient gastroenterologists and hepatologists at a single tertiary academic medical center in June 2020. Clinicians were invited to participate in an electronic survey. Survey questions involved either single or multiple categorical responses.
RESULT(S): A total of 46 respondents (51 +/- 14 years old) participated, 70% of which were male. 44 (96%) respondents had no telehealth experience prior to the pandemic. Clinicians conducted 19 +/- 13 visits weekly with a mean length of 24 +/- 9 minutes. 88% of providers reported telehealth allowed for increased flexibility, both in patient scheduling and their personal lives. Telehealth was always or usually effective in addressing patients' clinical needs 91% of the time. 29 (63%) respondents estimated that 10% or fewer patients required in-person follow-up. Clinicians estimated 93% of patients desired the continued option of telehealth, and 42 (91%) providers wanted to continue telehealth in some capacity, conditional on reimbursement. Those interested would use telehealth for follow-up visits (28%), on a patient-by-patient basis (23%), or for new visits (20%). While 21 (46%) respondents felt that telehealth and in-person visits required equal effort, 16 (35%) felt telehealth required more effort. Reasons cited for telehealth requiring more effort included coordination of care (30%), technical difficulty for the patient (20%), and more charting (17%).
CONCLUSION(S): While most clinicians had no telehealth experience before the pandemic, a majority were interested in using telehealth in the future, citing increased flexibility for both provider and patient. Physicians felt that telehealth was effective in addressing patients' needs. However, many felt that telehealth required more effort, particularly in regard to coordination of care and technical difficulties. Newer telehealth platforms should address connectivity issues. Future studies should focus on patients' attitudes towards telehealth, and the effect of telehealth on healthcare outcomes, utilization and costs

Artificial intelligence (AI) was first described in 1950; however, several limitations in early models prevented widespread acceptance and application to medicine. In the early 2000s, many of these limitations were overcome by the advent of deep learning. Now AI systems are capable of analyzing complex algorithms and self-learning, we enter a new age in medicine where AI can be applied to clinical practice through risk assessment models, improving diagnostic accuracy and improving workflow efficiency. This article presents a brief historical perspective on the evolution of AI over the last several decades and the introduction and development of AI in medicine in recent years. A brief summary of the major applications of AI in gastroenterology and endoscopy are also presented, which will be reviewed in further detail by several other articles in this issue of GIE.

INTRODUCTION: Lipomas are benign submosal lesions, which can be found throughout the gastrointestinal tract. In most patients, these are incidentals findings and patients are asymptomatic. However, there are instances when lipomas can cause symptoms of obstruction if very large. This case highlights a rare complication of a colonic lipoma. CASE DESCRIPTION/METHODS: The case is of a 31-year-old man, who initially presented for intermittent rectal bleeding. On initial evaluation he had a benign abdominal exam, but a rectal exam was performed suggested hemorrhoids. There was no significant past medical history and no family history of colon cancer. A colonoscopy was performed demonstrating sigmoid diverticulosis, an ascending colon lipoma, and internal hemorrhoids, the likely cause of bleeding. Ten days later the patient calls with intermittent abdominal pain for the last several days. On further questioning, the patient does report occasional episodes of a similar sharp pain for the last few years, but in the last few days the pain has intensified. An outpatient CT scan was performed showing a 6.8 cm lipoma in the transverse colon causing colo-colonic intussusception (image 1). The patient was taken for urgent robotic right hemicolectomy with a side to side ileocolic anastomosis. Final pathology confirmed a large lipoma. The patient fully recovered and symptoms have resolved.
Discussion(s): DISCUSSION: Intussusception is when the bowel telescopes on itself. The most common location is the small bowel, but intussusception can occur in the colon 1. A lipoma is a benign submucosal tumor, which can be found in the colon. In the majority of cases lipomas are incidental finding and cause no symptoms. Based on autopsy reports, the incidence rate of colonic lipomas is 0.2-0.8%. However, clinical symptoms might include abdominal pain, bleeding, and perforation. Clinicians should be aware of this unique presentation, which requires surgical intervention

INTRODUCTION: Endoscopic submucosal dissection (ESD) and endoscopic full-thickness resection (EFTR) are therapeutic alternatives to surgery for resection of colon and rectal lesions. In regards to large colon and rectal polyps and tumors, both ESD and EFTR have high en bloc resection rates and low recurrence rates, but are limited by training, procedure length, stability, and instrumentation. The Robotic System (RS) is a new robot-assisted endoscopic platform with multiple degrees of freedom allowing improved visualization, dexterity, and tissue manipulation with traction. This is the first U.S. experience assessing the feasibility and safety of robot-assisted ESD and EFTR in resection of distal colon and rectal lesions and its implication for polyps and tumors.
METHOD(S): This is a multicenter retrospective study from five institutions. Patients with distal colon or rectal lesions who underwent either ESD or EFTR with the RS were included. Each patient's clinical history, endoscopic findings, procedural records, and pathology records were reviewed.
RESULT(S): Forty-one patients underwent either ESD or EFTR with the RS for distal colon or rectal lesions, with an average total resection time of 135.0 minutes (s 62.8, n = 24). On average, lesions were 9.3 cm from the anal verge (range: 2 cm to 17 cm, n = 35) and were 30.0 mm in max diameter (range: 9 to 77 mm, n = 28). There were 13 (31.7%) neoplasms and 23 (56.1%) adenomatous polyps; other lesions included inflammatory polyps, diffuse nodular lymphoid hyperplasia, and granulation tissue-all were suspicious for malignancy. Neoplasms included 11 adenocarcinomas and 2 GISTs. Adenomatous polyps included 11 tubular adenomas and 11 tubulovillous adenomas. Twenty-nine out of 34 patients (85.3%) with either adenomatous polyps or adenocarcinoma were successfully removed with the RS alone. Of these, 23 (79.3%) demonstrated clean margins on pathology. Post-endoscopic complications included rectal pain and bleeding.
CONCLUSION(S): This report demonstrates a role of robotic endoscopy for the safe and effective treatment of natural orifice endoscopic surgical resection, with its benefits including traction and triangulation. As endoscopic surgery in the form of ESD evolves, refinement of the tools and techniques of the robotic platform will allow endoscopists to have shorter learning curves and resection of distal colon and rectal polyps and tumors to have higher negative margin rates, potentially allowing more endoscopists the ability to perform ESD

BACKGROUND AND AIMS/OBJECTIVE:Artificial intelligence (AI), specifically deep learning, offers the potential to enhance the field of gastrointestinal endoscopy in areas ranging from lesion detection and classification, to quality metrics and documentation. Progress in this field will be measured by whether AI implementation can lead to improved patient outcomes and more-efficient clinical workflow for GI endoscopists. The aims of this article are to report the findings of a multidisciplinary group of experts focusing on issues in artificial intelligence research and applications related to gastroenterology and endoscopy, to review the current status of the field, and to produce recommendations for investigators developing and studying new AI technologies for gastroenterology. METHODS:A multidisciplinary meeting was held on September 28, 2019, bringing together academic, industry, and regulatory experts in diverse fields including gastroenterology, computer and imaging sciences, machine learning, and computer vision, Food and Drug Administration (FDA) and National Institutes of Health (NIH). Recent and ongoing studies in gastroenterology and current technology in AI were presented and discussed, key gaps in knowledge were identified, and recommendations were made for research that would have the highest impact in making advances and implementation in the field of AI to gastroenterology. RESULTS:There was a consensus that AI will transform the field of gastroenterology, particularly endoscopy and image interpretation. Powered by advanced machine learning algorithms, the use of computer vision to endoscopy has the potential to result in better prediction and treatment outcomes for patients with gastroenterology disorders and cancer. Large libraries of endoscopic images, "EndoNet," will be important to facilitate development and application of AI systems. The regulatory environment for implementation of AI systems is evolving, but common outcomes such as colon polyp detection have been highlighted as potential clinical trial endpoints. Other threshold outcomes will be important, as well as clarity on iterative improvement of clinical systems. CONCLUSIONS:Gastroenterology is a prime candidate for early adoption of AI. AI is rapidly moving from an experimental phase to a clinical implementation phase in gastroenterology. It is anticipated that the implementation of AI in gastroenterology over the next decade will have a significant and positive impact on patient care and clinical workflows. Ongoing collaboration among gastroenterologists, industry experts, and regulatory agencies will be important to ensure that progress is rapid and clinically meaningful. However, there are several constraints and areas that will benefit from further exploration, including potential clinical applications, implementation, structure and governance, role of gastroenterologists, and potential impact of AI in gastroenterology.

INTRODUCTION: Colorectal cancer (CRC) can be prevented by removal of polyps during colo-noscopy. Colonoscopy barriers include invasiveness and need of bowel cleansing preparation. Non-invasive CRC stool based tests may increase CRC screening adherence, but are not designed as a tool to identify pre-cancerous polyps. We present data from a novel prep-free colon cancer screening technology for the detection of pre-cancerous polyps.
METHOD(S): An ingestible capsule descends through the gastrointestinal tract via natural motility and scans the colon for structural abnormalities using an ultra-low-dose X-ray source. The data is transmitted to a recorder unit attached to the patient. The test requires no preparation or sedation, allowing patients to continue their daily routine. A 187 patients were performed in the U.S. and Israel designed to assess the safety and effectiveness of the technology in detecting polyps. All sites received EC/IRB approvals. Patients ingested the capsule with a contrast agent and underwent a colonoscopy performed by independent gastroenterologists, who were blinded to the test's results.
RESULT(S): Sensitivity of the capsule in detecting clinically significant polyps (>10 mm) was 76% and specificity was 82% with no severe or serious adverse events reported. Some patients reported mild abdominal pain and nausea. Patient characteristics are shown in Table 1. A survey questionnaire resulted with a score of 4.18 compared to a 2.91 for colonoscopy (P = 0.0011) using a scoring system of 1 (strongly disagree) to 5 (strongly agree) in response to the phrase: "I would recommend the test for colonic screening".
CONCLUSION(S): The reported patient satisfaction, sensitivity, specificity and safety highlights the potential of the capsule technology as a tool for CRC prevention. Further studies are needed to make this technology part of our routine colon cancer prevention armamentarium