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.

Safety and efficacy of direct percutaneous endoscopic jejunostomy tube placement compared with surgical jejunostomy: a tertiary care analysis.

BACKGROUND AND AIMS: Jejunostomy tube placements provides enteral access for feeding in eligible patients who cannot meet their nutritional needs by mouth. They can be surgically placed laparoscopically (lap-J) or with the use of a conventional open laparotomy approach (open-J). Recently, direct percutaneous endoscopic jejunostomy (DPEJ) has emerged as an alternative owing to its low cost and shorter recovery times. We sought to retrospectively compare the procedural success rates and adverse events of these methods. METHODS: Patients were identified by querying our health system patient database and the departmental database of patients who underwent DPEJ. The patients were divided into 3 cohorts based on the procedure: DPEJ, lap-J, or open-J. Patient age and body mass index, procedural success rate, and adverse event rate were compared among the 3 groups. RESULTS: A total of 201 patients met inclusion criteria (65 DPEJ, 111 lap-J, and 25 open-J). Procedural success rates were similar among the 3 groups (DPEJ 96.9%, lap-J 99.1%, open-J 100%; P = .702). Rates of infection and bleeding were also similar among the 3 groups. There were no cases of GI perforation. Tube dysfunction for any reason that required complete removal or replacement within 90 days occurred more often in the surgical groups than in the DPEJ group (DPEJ 0%, lap-J 35.1%, open-J 40.0%; P < .001). This was driven largely by increased rates of tube clogging and tube dislodgement in the surgical groups. CONCLUSIONS: DPEJ is a safe and effective alternative to surgical jejunostomy in eligible patients and may be associated with decreased adverse event rates at 90 days.

Effects of Glucagon-Like Peptide-1 Receptor Agonists on Gastric Mucosal Visibility and Retained Gastric Contents During Esophagogastroduodenoscopy.

BACKGROUND AND AIMS: Glucagon-like peptide-1 receptor agonists (GLP-1RA) are increasingly utilized in diabetes and obesity management. GLP-1RAs delay gastric emptying; however, their impact on visibility during esophagogastroduodenoscopy (EGD) remains uncertain. METHODS: A 1:1 matched case-control study was conducted. Individuals undergoing EGD on GLP-1RAs were matched to non-users based on demographics and diabetes status. A validated scale (POLPREP) was used to determine gastric mucosal visibility scores. RESULTS: A total of 84 pairs (n=168) were included. GLP-1RA users showed significantly lower visibility scores, with a 2.54 times higher likelihood of lower scores compared to non-users. Additionally, GLP-1RA users had a higher incidence of retained gastric contents (13.1% vs. 4.8%, aOR:4.62, p=0.025) and aborted procedures due to this issue. No anesthesia-related adverse events were observed. CONCLUSIONS: GLP-1RA use at the time of endoscopy exhibited higher odds of lower gastric mucosal visibility scores, retained contents and aborted procedures. Further research is warranted.

Bedside Live-View Capsule Endoscopy in Evaluation of Overt Obscure Gastrointestinal Bleeding: A Pilot Point-of-Care Study.

BACKGROUND: Capsule endoscopy (CE) is an emerging tool in the diagnosis and management of occult bleeding and overt obscure gastrointestinal bleeding (OOGIB). Maximizing the efficiency of CE can lead to rapid bleeding localization and shorter time to therapy. We investigated whether a trained registered nurse (RN) can accurately interpret bleeding by observing the CE findings in real time by measuring inter-observer agreement between RN and physician interpretation. METHODS: We conducted a prospective study of patients admitted for OOGIB who underwent live-view capsule endoscopy (LVCE) between December 2016 and November 2017. A matched control group who underwent standard CE was obtained through retrospective review. An RN received a 2-day training program for CE interpretation. RN bedside interpretation for bleeding was followed by interpretation by 2 gastrointestinal physicians blinded to LVCE findings. Outcomes were compared between groups using t-tests and χ2 tests. Cohen's kappa measured the agreement between the physicians and the RN. RESULTS: Ten subjects were in the LVCE group, and 12 subjects were in the standard-of-care group. The agreement between the physicians and the RN was 9/10 (90%), with a kappa of 0.73 (95% CI: 0.26-1.00; p = 0.016). Patients in the LVCE group had shorter duration to physician interpretation (0.6 vs. 0.7 days [p = 0.50]), shorter duration to endoscopy (1.8 days vs. 3 days [p = 0.240]), and shorter length of stay (8.1 vs. 11.4 days [p = 0.26]) compared to the standard-of-care group. CONCLUSION: This study utilizing an RN for LVCE interpretation found inter-observer agreement between RN and physician findings. Larger studies are needed to assess whether this RN-physician team approach can translate to improved outcomes.

Feasibility and Utility of Routine Point-of-Care Gastric Ultrasonography in Patients Undergoing Upper Gastrointestinal Endoscopy Procedures: A Prospective Cohort Study.

OBJECTIVES: Previous studies have indicated that point-of-care ultrasonography (POCUS) of the gastric antrum can predict the adequacy of fasting before surgery and anesthesia. The aim of this study was to evaluate the utility of gastric POCUS in patients undergoing upper gastrointestinal (GI) endoscopy procedures. METHODS: We performed a single-center cohort study in patients undergoing upper GI endoscopy. Consenting patient's gastric antrum was scanned before anesthetic care for endoscopy to determine the cross-sectional area (CSA) and qualitatively determine safe and unsafe contents. Further, an estimate of residual gastric volume was determined using the formula and the nomogram methods. Subsequently, gastric secretions aspirated during endoscopy were quantified and further correlated with nomogram and formula-based assessments. No patient required a change in the primary anesthetic plan except for using rapid sequence induction in those with unsafe contents on POCUS scans. RESULTS: Qualitative ultrasound measurements consistently determined safe and unsafe gastric residual contents in 83 patients enrolled in the study. Unsafe contents were determined by qualitative scans in 4 out of 83 cases (5%) despite adequate fasting status. Quantitatively, only a moderate correlation was demonstrated between measured gastric volumes and nomogram (r = .40, 95% CI: 0.20, 0.57; P = .0002) or formula-based (r = .38, 95% CI: 0.17, 0.55; P = .0004) determinations of residual gastric volumes. CONCLUSION: In daily clinical practice, qualitative POCUS determination of residual gastric content is a feasible and useful technique to identify patients at risk of aspiration before upper GI endoscopy procedures.

Videoconference microscopy is a reliable alternative to conventional microscopy in the evaluation of Barrett's esophagus: Zooming into a new era.

Telepathology, practicing pathology from a distance, allows experts to review cases without the need to transfer glass slides. Due to significant intra- and inter-observer variabilities in the histological evaluation of Barrett's esophagus (BE), current guidelines recommend expert consultation in cases of dysplasia. We aimed to determine whether telepathology using microscope videoconferencing can be reliably used for evaluation of BE. Biopsies from 62 patients with endoscopic findings of salmon colored mucosa extending ≥1 cm proximal to the gastroesophageal junction were randomly selected to represent benign esophagus, non-dysplastic BE, low-grade dysplasia, high-grade dysplasia, and adenocarcinoma. Three gastrointestinal-trained pathologists reviewed the cases via videoconference microscopy followed by conventional microscopy. Intra-observer and pairwise inter-observer agreements between the conventional microscopy and videoconference methodologies were calculated for each of the three pathologists using Fleiss-Cohen weighted kappa (K) analysis. The intra-observer agreement for each pathologist's assessment of videoconference microscopy and glass slide readings showed very good reliability (K = 0.94, 95% confidence interval = 0.89-0.99; 0.88, 95% confidence interval = 0.79-0.98; 0.93, 95% confidence interval = 0.90-0.97). Mean pairwise inter-observer agreement was 0.90 for videoconference and 0.91 for conventional microscopy. Diagnosis and grading of BE using videoconference microscopy show similar reliability as conventional microscopy. Based on our findings, we propose that videoconferencing pathology is a valid instrument for evaluating BE.

Validation of the Orlando Protocol for endoscopic management of pancreatic fluid collections in the era of lumen-apposing metal stents.

OBJECTIVES: Although lumen-apposing metal stents (LAMS) are being increasingly used in lieu of plastic stents, the clinical approach to endoscopic management of pancreatic fluid collections (PFCs) is poorly standardized. We compared outcomes of approaches over two time intervals, initially using plastic stents and later integrating LAMS. METHODS: This was a retrospective, observational, before-after study of prospectively collected data on consecutive patients with symptomatic PFCs managed over two time periods. In the initial period (January 2010-January 2015) endoscopic treatment was undertaken with plastic stents and in the later period (February 2015-August 2020) by integration of LAMS with selective use of plastic stents. The treatment strategy in both periods were tailored to size, extent, type of PFC and stepwise response to intervention. The main outcome was treatment success, defined as resolution of PFC and presenting symptoms at 6-month follow-up. RESULTS: A total of 160 patients were treated with plastic stents and 227 patients were treated using an integrated LAMS approach. Treatment success was significantly higher for the integrated approach compared to using only plastic stents (95.6 vs. 89.4%; P = 0.018), which was confirmed to be predictive of treatment success on multivariable logistic regression analysis (odds ratio 2.7, 95% confidence interval 1.1-6.4; P = 0.028). CONCLUSIONS: A structured approach integrating LAMS with selective use of plastic stents improved treatment success in patients with PFCs compared to an approach using only plastic stents.

Developing 3D Organoid Raft Cultures from Patient-Derived Xenografts as Rapid Models to Screen Efficacy of Experimental Therapeutics.

Reliable preclinical models are needed for screening new cancer drugs. Thus, we developed an improved 3D tumor organoid model termed "organoid raft cultures" (ORCs). Development of ORCs involved culturing tumors ex vivo on collagen beds (boats) with grid supports to maintain their morphological structure. The ORCs were developed from patient-derived xenografts (PDXs) of colon cancers excised from immune-deficient mice (NOD/SCID/IL2Rgammanull). We utilized these new models to evaluate the efficacy of an investigational drug, Navitoclax (ABT-263). We tested the efficacy of ABT-263, an inhibitor of BCL-2 family proteins, in these ORCs derived from a PDX that showed high expression of antiapoptotic BCL2 family proteins (BCL-2, BCL-XL, and BCL-W). Hematoxylin and eosin staining evaluation of PDXs and corresponding ORCs indicated the retention of morphological and other histological integrity of ORCs. ORCs treated with ABT-263 showed decreased expression of antiapoptotic proteins (BCL2, BCL-XL and BCL-W) and increased proapoptotic proteins (BAX and PUMA), with concomitant activation of caspase 3. These studies support the usefulness of the ORCs, developed from PDXs, as an alternative to PDXs and as faster screening models.

Single-use duodenoscopes: where are we and where are we going?

PURPOSE OF REVIEW: Given the growing concerns about infection transmission from use of contaminated reusable duodenoscopes, technological advancements have been made that vary from modifications of existing designs to development of single-use devices. RECENT FINDINGS: To circumvent mechanical limitations that preclude access to critical areas of a duodenoscope to perform thorough cleaning and disinfection, single-use disposable duodenoscopes have been developed. A thorough assessment of this technology is limited by the minimal published data that is currently available. This opinion assesses the current technical functionality of these devices, potential for further improvements, implications for healthcare economics and the future of gastrointestinal endoscopy. SUMMARY: Currently available data suggest that majority of endoscopic retrograde cholangiopancreatography procedures can be safely performed using single-use duodenoscopes. The ability to improve technical functionality, incorporate futuristic technology and secure financial reimbursement from insurance carriers will largely define the future prospects of this recent innovation.

NCCN Guidelines Insights: Colorectal Cancer Screening, Version 2.2020.

The NCCN Guidelines for Colorectal Cancer (CRC) Screening describe various colorectal screening modalities as well as recommended screening schedules for patients at average or increased risk of developing sporadic CRC. They are intended to aid physicians with clinical decision-making regarding CRC screening for patients without defined genetic syndromes. These NCCN Guidelines Insights focus on select recent updates to the NCCN Guidelines, including a section on primary and secondary CRC prevention, and provide context for the panel's recommendations regarding the age to initiate screening in average risk individuals and follow-up for low-risk adenomas.

NCCN Guidelines Insights: Genetic/Familial High-Risk Assessment: Colorectal, Version 2.2019.

Identifying individuals with hereditary syndromes allows for improved cancer surveillance, risk reduction, and optimized management. Establishing criteria for assessment allows for the identification of individuals who are carriers of pathogenic genetic variants. The NCCN Guidelines for Genetic/Familial High-Risk Assessment: Colorectal provide recommendations for the assessment and management of patients with high-risk colorectal cancer syndromes. These NCCN Guidelines Insights focus on criteria for the evaluation of Lynch syndrome and considerations for use of multigene testing in the assessment of hereditary colorectal cancer syndromes.

Impact of Disconnected Pancreatic Duct Syndrome on the Endoscopic Management of Pancreatic Fluid Collections.

OBJECTIVE: To study the effect of disconnected pancreatic duct syndrome (DPDS) on endoscopic management of pancreatic fluid collections (PFCs). BACKGROUND: Data on the impact of DPDS in patients undergoing endoscopic treatment of PFCs are limited. METHODS: Retrospective study of patients undergoing endoscopic drainage of PFCs from 2003 to 2015. If treatment response was suboptimal following initial endoscopic or endoscopic ultrasound-guided transmural drainage, hybrid interventions (endoscopic ultrasound-guided multigate/dual modality technique, endoscopic/percutaneous sinus tract necrosectomy) were performed. Transmural stents were left permanently in situ in DPDS patients from 2008 onwards. Main outcome measures were to evaluate the effect of DPDS on need for hybrid treatment, reinterventions, rescue surgery, length of stay, and overall treatment success. RESULTS: Of 361 patients, 34 (9.4%) were acute collections, 178 (49.3%) pseudocysts, and 149 (41.3%) walled-off necrosis (WON). DPDS was present in 167 (46.3%) patients, absent in 124 (34.3%), unknown in 70 (19.4%), and occurred more frequently in WON compared to other PFCs (68.3% vs 31.7%; P < 0.001). Although there was no difference in treatment success, more patients with DPDS required hybrid treatment (31.1% vs 4.8%, P < 0.001), reinterventions (30% vs 18.5%, P = 0.03), rescue-surgery (13.2% vs 4.8%, P = 0.02), and longer length of stay [median (interquartile range) days, 3 (2-10) vs 2 (1-4), P = 0.003]. PFC recurrence was lower in patients with DPDS with permanent transmural stents (17.4% vs 1.7%, P < 0.001). On multivariate logistic regression, DPDS [odds ratio (OR) 2.99], WON (OR 3.37), PFC size of 100 mm or more (OR 2.66), and multiple PFCs (OR 10.6) were associated with need for hybrid treatment. CONCLUSIONS: DPDS has a significant effect on endoscopic management of PFCs as more patients required hybrid treatment, reinterventions, and rescue surgery for achieving optimal clinical outcomes.

Length of Barrett's segment predicts failure of eradication in radiofrequency ablation for Barrett's esophagus: a retrospective cohort study.

BACKGROUND: We aim to investigate factors that may contribute to failure of eradication of dysplastic Barrett's Esophagus among patients undergoing radiofrequency ablation treatment. METHODS: A retrospective review of patients undergoing radiofrequency ablation for treatment of Barrett's Esophagus was performed. Data analyzed included patient demographics, medical history, length of Barrett's Esophagus, number of radiofrequency ablation sessions, and histopathology. Subsets of patients achieving complete eradication were compared with those not achieving complete eradication. RESULTS: A total of 107 patients underwent radiofrequency ablation for Barrett's Esophagus, the majority white, overweight, and male. Before treatment, 63 patients had low-grade dysplasia, and 44 patients had high-grade dysplasia or carcinoma. Complete eradication was achieved in a majority of patients (57% for metaplasia, and 76.6% for dysplasia). Failure of eradication occurred in 15.7% of patients. The median number of radiofrequency ablation treatments in patients achieving complete eradication was 3 sessions, compared to 4 sessions for failure of eradication (p = 0.06). Barrett's esophagus length of more than 5 cm was predictive of failure of eradication (p < 0.001). CONCLUSIONS: Radiofrequency ablation for dysplastic Barrett's Esophagus is a proven and effective treatment modality, associated with a high rate of complete eradication. Our rates of eradication from a center starting an ablation program are comparable to previously published studies. Length of Barrett's segment > 5 cm was found to be predictive of failure of eradication in patients undergoing radiofrequency ablation.

Monitoring colonoscopy withdrawal time significantly improves the adenoma detection rate and the performance of endoscopists.

BACKGROUND AND STUDY AIMS: The recommended minimum withdrawal time for screening colonoscopy is 6 minutes. Adenoma detection rates (ADRs) increase with longer withdrawal times. We aimed to compare withdrawal times and ADRs of endoscopists unaware of being monitored vs. aware. PATIENTS AND METHODS: Seven experienced gastroenterologists prospectively performed 558 screening colonoscopies during a 9-month period in a Swiss University hospital. Colonoscopy withdrawal times were first measured without the gastroenterologists' knowledge of being monitored (n = 355 colonoscopies) and then with their knowledge (n = 203 colonoscopies). RESULTS: The median withdrawal time when gastroenterologists were unaware of being monitored was 4.5 minutes (interquartile range [IQR] 4 ­â€Š5.5 minutes) without intervention and 6 minutes (IQR 4 ­â€Š9 minutes) with intervention, increasing significantly to 7.3 minutes (IQR 6.5 ­â€Š9 minutes) and 8 minutes (IQR 7 ­â€Š11 minutes), respectively, when they were aware of being monitored (P < 0.001 both for colonoscopies with and without intervention). The ADR increased from 21.4 % when the gastroenterologists were unaware of being monitored to 36.0 % when they were aware (P < 0.001). In the multivariate regression model, the endoscopists knowing they were being monitored was the strongest factor associated with ADR (odds ratio 4.417; 95 % confidence interval [CI] 2.241 ­â€Š8.705; P < 0.001). CONCLUSIONS: Colonoscopy withdrawal time in unmonitored gastroenterologists is shorter than recommended and increases with awareness of monitoring. ADR significantly increases when gastroenterologists are aware of being monitored. Implementation of systematic monitoring, and analysis of withdrawal time and ADR for each endoscopist may help to increase the ADR.