Artificial Intelligence for Real-Time Prediction of the Histology of Colorectal Polyps by General Endoscopists.

BACKGROUND: Real-time prediction of histologic features of small colorectal polyps may prevent resection and/or pathologic evaluation and therefore decrease colonoscopy costs. Previous studies showed that computer-aided diagnosis (CADx) was highly accurate, though it did not outperform expert endoscopists. OBJECTIVE: To assess the diagnostic performance of histologic predictions by general endoscopists before and after assistance from CADx in a real-life setting. DESIGN: Prospective, multicenter, single-group study. (ClinicalTrials.gov: NCT04437615). SETTING: 6 centers across the United States. PARTICIPANTS: 1252 consecutive patients undergoing colonoscopy and 49 general endoscopists with variable experience in real-time prediction of polyp histologic features. INTERVENTION: Real-time use of CADx during routine colonoscopy. MEASUREMENTS: The primary end points were the sensitivity and specificity of CADx-unassisted and CADx-assisted histologic predictions for adenomas measuring 5 mm or less. For clinical purposes, additional estimates according to location and confidence level were provided. RESULTS: The CADx device made a diagnosis for 2695 polyps measuring 5 mm or less (96%) in 1252 patients. There was no difference in sensitivity between the unassisted and assisted groups (90.7% vs. 90.8%; P = 0.52). Specificity was higher in the CADx-assisted group (59.5% vs. 64.7%; P < 0.001). Among all 2695 polyps measuring 5 mm or less, 88.2% and 86.1% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be resected and discarded without pathologic evaluation. Among 743 rectosigmoid polyps measuring 5 mm or less, 49.5% and 47.9% (P < 0.001) in the CADx-assisted and unassisted groups, respectively, could be left in situ without resection. LIMITATION: Decision making based on CADx might differ outside a clinical trial. CONCLUSION: CADx assistance did not result in increased sensitivity of optical diagnosis. Despite a slight increase, the specificity of CADx-assisted diagnosis remained suboptimal. PRIMARY FUNDING SOURCE: Olympus America Corporation served as the clinical study sponsor.

Use of a Cirrhosis Admission Order Set Improves Adherence to Quality Metrics and May Decrease Hospital Length of Stay.

INTRODUCTION: Quality metrics for inpatient cirrhosis management have been created to improve processes of care. We aimed to improve adherence to quality metrics by creating a novel clinical decision support (CDS) tool in the electronic health record (EHR). METHODS: We developed and piloted an alert system in the EHR that directs providers to a cirrhosis order set for patients who have a known diagnosis of cirrhosis or are likely to have cirrhosis. Adherence to process measures and outcomes when the CDS was used were compared with baseline performance before the implementation of the CDS. RESULTS: The use of the order set resulted in a significant increase in adherence to process measures such as diagnostic paracentesis (29.6%-51.1%), low-sodium diet (34.3%-77.8%), and social work involvement (36.6%-88.9%) ( P < 0.001 for all). There were also significant decreases in both intensive care and hospital lengths of stay ( P < 0.001) as well as in-hospital development of infection ( P = 0.002). There was no difference in hospital readmissions at 30 or 90 days between the groups ( P = 0.897, P = 0.640). DISCUSSION: The use of CDS in EHR-based interventions improves adherence to quality metrics for patients with cirrhosis and could easily be shared by institutions through EHR platforms. Further studies and larger sample sizes are needed to better understand its impact on additional outcome measures.

Virtual Gastroenterology Fellowship Recruitment During COVID-19 and Its Implications for the Future.

BACKGROUND AND AIMS: Amid the COVID-19 pandemic, medical education organizations endorsed a virtual recruitment format, representing a stark change from traditional in-person interviews. We aimed to identify the attitudes and perceptions of Gastroenterology Fellowship Program Directors (PDs) and applicants regarding the virtual interview experience and the role of virtual interviews (VI) in the future. METHODS: We designed separate surveys targeting PDs and applicants using the Qualtrics software. At the end of the interview season, we e-mailed both survey links to all PDs and requested that they forward the applicant survey to their interviewed candidates. Surveys were voluntary and anonymous. Descriptive statistics were used to analyze the data with results presented as percentages. RESULTS: A total of 29.7% of PDs completed the survey. Compared to traditional interviews, VI were viewed by 46.5% of PDs to be very suboptimal or suboptimal. Yet, 69.1% envisioned a role for VI in the future. A total of 14.2% of applicants completed the survey. Compared to traditional interviews, VI were viewed by 42.3% of applicants to be very suboptimal or suboptimal. However, 61.8% saw a future role for VI. While both applicants and PDs reported that establishing an interpersonal connection was a disadvantage with VI, applicants placed more emphasis on this need for connection (p = 0.001). CONCLUSION: Overall, PDs and applicants report mixed views with regard to VI but anticipate that it may continue to have a future role. VI may augment future recruitment cycles with care taken to not disadvantage applicants, who rely heavily on the interview process to create personal connections with programs.

Optical diagnosis of colorectal polyps using novel blue light imaging classification among trainee endoscopists.

BACKGROUND: Blue light imaging (BLI) has been shown to improve the characterization of colorectal polyps among the endoscopy experts. We aimed to determine if this technology could be taught to endoscopy trainees while maintaining high accuracy and interobserver agreement. METHODS: Twenty-one gastroenterology trainees (fellows) from two academic institutions participated in this prospective study. Each trainee completed a web-based learning comprising four modules: pre-test, didactic videos explaining the BLI Adenoma Serrated International Classification (BASIC), interactive examples, and post-test assessment. The pre- and post-test modules consisted of reviewing video images of colon polyps in high definition white light imaging and BLI and then applying the BASIC classification to determine if the polyps were likely to be adenomatous. Confidence in adenoma identification (rated '1' to '5'), accuracy in polyp (adenoma vs. non-adenoma) identification, and agreement in characterization per BASIC criteria were derived. RESULTS: Trainee accuracy in the adenoma diagnosis improved from 74.7% (pre-test) to 85.4% (post-test) (P < 0.01). There was a trend towards higher accuracy in polyp characterization with subsequent years of training (1st year fellows 77.4%, 2nd year 88.5%, and final year 94.0%) with consistent improvements after the e-learning across years of trainees. Overall, trainees were able to identify adenoma with a high sensitivity of 86.9%, specificity 83.9%, positive predictive value of 84.4%, and negative predictive value of 86.5%. However, their interobserver agreement in adenoma diagnosis was moderate (k = 0.52). CONCLUSION: The novel BLI classification can be easily taught to gastroenterology trainees using an online module and accuracy improves with years of training reaching >90% for colorectal polyp characterization.

Impact of the COVID-19 Pandemic on the Clinical Learning Environment: Addressing Identified Gaps and Seizing Opportunities.

The clinical learning environment (CLE) encompasses the learner's personal characteristics and experiences, social relationships, organizational culture, and the institution's physical and virtual infrastructure. During the COVID-19 pandemic, all 4 of these parts of the CLE have undergone a massive and rapid disruption. Personal and social communications have been limited to virtual interactions or shifted to unfamiliar clinical spaces because of redeployment. Rapid changes to the organizational culture required prompt adaptations from learners and educators in their complex organizational systems yet caused increased confusion and anxiety among them. A traditional reliance on a physical infrastructure for classical educational practices in the CLE was challenged when all institutions had to undergo a major transition to a virtual learning environment. However, disruptions spurred exciting innovations in the CLE. An entire cohort of physicians and learners underwent swift adjustments in their personal and professional development and identity as they rose to meet the clinical and educational challenges they faced due to COVID-19. Social networks and collaborations were expanded beyond traditional institutional walls and previously held international boundaries within multiple specialties. Specific aspects of the organizational and educational culture, including epidemiology, public health, and medical ethics, were brought to the forefront in health professions education, while the physical learning environment underwent a rapid transition to a virtual learning space. As health professions education continues in the era of COVID-19 and into a new era, educators must take advantage of these dynamic systems to identify additional gaps and implement meaningful change. In this article, health professions educators and learners from multiple institutions and specialties discuss the gaps and weaknesses exposed, opportunities revealed, and strategies developed for optimizing the CLE in the post-COVID-19 world.

Review article: the role of nutrition in alcohol-associated liver disease.

BACKGROUND: Malnutrition is a commonly encountered issue in patients with alcohol-associated liver disease. The role of nutritional supplementation in the management of alcohol-associated liver disease is integral to patient outcomes-it has been shown to decrease rates of hepatic encephalopathy, improve outcomes post-liver transplant, reduce 90-day hospital readmissions and lower mortality. Despite these benefits, many studies have shown nutritional support to be an underutilised tool in the care of patients with alcohol-associated liver disease. AIMS: To review the epidemiology, pathophysiology, recommendations for nutritional assessment and supplementation, as well as future directions for research of the relationship between nutrition and alcohol-associated liver disease. METHODS: A literature search was conducted via PubMed using MeSH terms to inform this narrative review. RESULTS: Decreased dietary intake, socioeconomic status, impaired absorption of nutrients and increased free radical species are implicated in the pathophysiology of malnutrition in alcohol-associated liver disease. CONCLUSIONS: Malnutrition is common in alcohol-associated liver disease, and physicians should be aware of its association with poor clinical outcomes. Routine nutritional assessment, involvement of a dietician and nutritional supplementation are recommended to improve clinical outcomes in patients with alcohol-associated liver disease.