Risk factors for complications after performance of ERCP

BACKGROUND

ERCP has become widely available for the diagnosis and treatment of benign and malignant pancreaticobiliary diseases. In this prospective study, the overall complication rate and risk factors for diagnostic and therapeutic ERCP were identified.

METHODS

Data were collected prospectively on patient characteristics and endoscopic techniques from 1223 ERCPs performed at a single referral center and entered into a database. Univariate and multivariate analyses were used to identify risk factors for ERCP-associated complications.

RESULTS

Of 1223 ERCPs performed, 554 (45.3%) were diagnostic and 667 (54.7%) therapeutic. The overall complication rate was 11.2%. Post-ERCP pancreatitis was the most common (7.2%) and in 93% of cases was self-limiting, requiring only conservative treatment. Bleeding occurred in 10 patients (0.8%) and was related to a therapeutic procedure in all cases. Nine patients had cholangitis develop, most cases being secondary to incomplete drainage. There was one perforation (0.08%). All other complications totaled 1.5%. Variables derived from cannulation technique associated with an increased risk for post-ERCP pancreatitis were precut access papillotomy (20%), multiple cannulation attempts (14.9%), sphincterotome use to achieve cannulation (13.1%), pancreatic duct manipulation (13%), multiple pancreatic injections (12.3%), guidewire use to achieve cannulation (10.2%), and the extent of pancreatic duct opacification (10%). Patient characteristics associated with an increased risk of pancreatitis were sphincter of Oddi dysfunction (21.7%) documented by manometry, previous ERCP-related pancreatitis (19%), and recurrent pancreatitis (16.2%). Pain during the procedure was an important indicator of an increased risk of post-ERCP pancreatitis (27%). Independent risk factors for post-ERCP pancreatitis were identified as a history of recurrent pancreatitis, previous ERCP-related pancreatitis, multiple cannulation attempts, pancreatic brush cytology, and pain during the procedure.

CONCLUSIONS

The most frequent ERCP-related complication was pancreatitis, which was mild in the majority of patients. The frequency of post-ERCP pancreatitis was similar for both diagnostic and therapeutic procedures. Bleeding was rare and mostly associated with sphincterotomy. Other complications such as cholangitis and perforation were rare. Specific patient- and technique-related characteristics that can increase the risk of post-ERCP complications were identified.

A randomized trial comparing uncovered and partially covered self-expandable metal stents in the palliation of distal malignant biliary obstruction

BACKGROUND

The most common complication of uncovered biliary self-expandable metal stents (SEMSs) is tumor ingrowth. The addition of an impenetrable covering may prolong stent patency.

OBJECTIVE

To compare stent patency between uncovered and partially covered SEMSs in malignant biliary obstruction.

DESIGN

Multicenter randomized trial.

SETTING

Four teaching hospitals.

PATIENTS

Adults with inoperable distal malignant biliary obstruction.

INTERVENTIONS

Uncovered or partially covered SEMS insertion.

MAIN OUTCOME MEASURES

Time to recurrent biliary obstruction, patient survival, serious adverse events, and mechanism of recurrent biliary obstruction.

RESULTS

From October 2002 to May 2008, 129 patients were randomized. Recurrent biliary obstruction was observed in 11 of 61 uncovered SEMSs (18%) and 20 of 68 partially covered SEMSs (29%). The median times to recurrent biliary obstruction were 711 days and 357 days for the uncovered and partially covered SEMS groups, respectively (P = .530). Median patient survival was 239 days for the uncovered SEMS and 227 days for the partially covered SEMS groups (P = .997). Serious adverse events occurred in 27 (44%) and 42 (62%) patients in the uncovered and partially covered SEMS groups, respectively (P = .046). None of the uncovered and 8 (12%) of the partially covered SEMSs migrated (P = .0061).

LIMITATIONS

Intended sample size was not reached. Allocation to treatment groups was unequal.

CONCLUSIONS

There was no significant difference in time to recurrent biliary obstruction or patient survival between the partially covered and uncovered SEMS groups. Partially covered SEMSs were associated with more serious adverse events, particularly migration.

Pancreatic stent placement for duct disruption

BACKGROUND

The aim of this study was to identify predictors of outcome after pancreatic duct stent placement for duct disruption.

METHODS

Patients were identified from endoscopy databases. Disruption was defined by extravasation of contrast from the pancreatic duct during endoscopic retrograde pancreatography. Data collected included demographic information, imaging studies, management before and outcome after stent placement. Success was defined as resolution of the disruption clinically, on radiologic imaging, and/or at endoscopic retrograde pancreatography.

RESULTS

Forty-three patients (23 women, 20 men; mean age 57 years, [SD] 15.2 years) were studied. The etiology of pancreatic duct disruption was acute pancreatitis in 24, chronic pancreatitis in 9, operative injury in 7, and trauma in 3 patients. In 25 patients there was resolution of the disruption, whereas stent therapy was unsuccessful in 16 and the outcome was indeterminate in 2 patients. On univariate analysis, stent positioned to bridge the disruption (p = 0.04) and longer duration of stent therapy (p = 0.002) were associated with a successful outcome. Female gender (p = 0.05) and acute pancreatitis (p = 0.05) were associated with a lack of success. On multivariate analysis, only the bridging stent position remained correlated to outcome. Complications occurred in 4 patients.

CONCLUSIONS

A bridging stent is associated with a successful outcome after pancreatic duct stent placement for duct disruption.

Risk factors for complications after performance of ERCP

BACKGROUND

ERCP has become widely available for the diagnosis and treatment of benign and malignant pancreaticobiliary diseases. In this prospective study, the overall complication rate and risk factors for diagnostic and therapeutic ERCP were identified.

METHODS

Data were collected prospectively on patient characteristics and endoscopic techniques from 1223 ERCPs performed at a single referral center and entered into a database. Univariate and multivariate analyses were used to identify risk factors for ERCP-associated complications.

RESULTS

Of 1223 ERCPs performed, 554 (45.3%) were diagnostic and 667 (54.7%) therapeutic. The overall complication rate was 11.2%. Post-ERCP pancreatitis was the most common (7.2%) and in 93% of cases was self-limiting, requiring only conservative treatment. Bleeding occurred in 10 patients (0.8%) and was related to a therapeutic procedure in all cases. Nine patients had cholangitis develop, most cases being secondary to incomplete drainage. There was one perforation (0.08%). All other complications totaled 1.5%. Variables derived from cannulation technique associated with an increased risk for post-ERCP pancreatitis were precut access papillotomy (20%), multiple cannulation attempts (14.9%), sphincterotome use to achieve cannulation (13.1%), pancreatic duct manipulation (13%), multiple pancreatic injections (12.3%), guidewire use to achieve cannulation (10.2%), and the extent of pancreatic duct opacification (10%). Patient characteristics associated with an increased risk of pancreatitis were sphincter of Oddi dysfunction (21.7%) documented by manometry, previous ERCP-related pancreatitis (19%), and recurrent pancreatitis (16.2%). Pain during the procedure was an important indicator of an increased risk of post-ERCP pancreatitis (27%). Independent risk factors for post-ERCP pancreatitis were identified as a history of recurrent pancreatitis, previous ERCP-related pancreatitis, multiple cannulation attempts, pancreatic brush cytology, and pain during the procedure.

CONCLUSIONS

The most frequent ERCP-related complication was pancreatitis, which was mild in the majority of patients. The frequency of post-ERCP pancreatitis was similar for both diagnostic and therapeutic procedures. Bleeding was rare and mostly associated with sphincterotomy. Other complications such as cholangitis and perforation were rare. Specific patient- and technique-related characteristics that can increase the risk of post-ERCP complications were identified.

Brush cytology during ERCP for the diagnosis of biliary and pancreatic malignancies

Endoscopic retrograde cholangiopancreatography is a valuable tool in the diagnosis and management of pancreaticobiliary diseases. The diagnostic sensitivity of brush cytology is reported as between 18% and 70% for malignant bile duct or pancreatic duct strictures. We report our findings in 74 patients with pancreaticobiliary strictures who underwent ERCP. Brush cytology was performed on 55 bile duct specimens and 19 pancreatic duct specimens. No complications related to the procedure occurred; 4 specimens (5.4%) were unsatisfactory for interpretation. Strictures were benign in 22 patients (12 pancreatitis, 5 sclerosing cholangitis, 3 Mirizzi syndrome, and 2 papillitis) and malignant in 52 patients (29 pancreatic carcinoma, 10 cholangiocarcinoma, 6 metastatic disease, 4 pancreatic mucinous ductal ectasia, 1 ampullary carcinoma, and 2 non-functioning islet cell tumors). The nature of the stricture was confirmed by surgery, surgical biopsy, necropsy, or follow-up. The overall results for brush cytology were sensitivity 56.2%, specificity 100%, positive predictive value 100%, negative predictive value 51.2%, and accuracy 70%. Our results confirm the value, safety, and utility of obtaining cytologic specimens at the time of ERCP; confirmation was obtained in 65.5% of pancreatic carcinoma cases. Although a negative result does not exclude pancreaticobiliary malignancy, a positive result confirms this diagnosis.

ASGE guideline for endoscopic full-thickness resection and submucosal tunnel endoscopic resection

With the development of reliable endoscopic closure techniques and tools, endoscopic full-thickness resection (EFTR) is emerging as a therapeutic option for the treatment of subepithelial tumors and epithelial neoplasia with significant fibrosis. EFTR may be categorized as "exposed" and "nonexposed." In exposed EFTR, the full-thickness resection is undertaken with a tunneled or nontunneled technique, with subsequent closure of the defect. In nonexposed EFTR, a secure serosa-to-serosa apposition is achieved before full-thickness resection of the isolated lesion. This document reviews current techniques and devices used for EFTR and reviews clinical applications and outcomes.

Amyloidosis of the gastrointestinal tract: a 13-year, single-center, referral experience

Amyloidosis of the gastrointestinal tract, with biopsy-proven disease, is rare. We reviewed a series of patients who presented with biopsy-proven gastrointestinal amyloidosis and report their clinical characteristics, treatments, and survival. This is a retrospective review of data prospectively collected from January 1998 to December 2011 in a tertiary referral center; 2,334 patients with all types of amyloidosis were evaluated during this period. Seventy-six patients (3.2%) had biopsy-proven amyloid involvement of the gastrointestinal tract. Their median age was 61 years (range, 34-79). Systemic amyloidosis with dominant gastrointestinal involvement was present in 60 (79%) patients, whereas the other 16 (21%) patients had amyloidosis localized to the gastrointestinal tract without evidence of an associated plasma cell dyscrasia or other organ involvement. Of the 60 systemic cases, 50 (83%) had immunoglobulin light-chain, five (8%) had familial lysozyme, three (5%) had wild-type transthyretin, and two (3%) had mutant transthyretin amyloidosis. The most frequent symptoms for all patients were weight loss in 33 (45%) and gastrointestinal bleeding in 27 (36%). Incidental identification of amyloidosis on routine endoscopic surveillance played a role in the diagnosis of seven patients with systemic immunoglobulin light-chain, and four patients with immunoglobulin light-chain localized to the gastrointestinal tract. Amyloid protein subtyping was performed in 12 of the cases of localized disease, and all had lambda light chain disease. Of the 50 patients with systemic immunoglobulin light-chain amyloidosis, 45 were treated with anti-plasma cell therapy. The median survival has not been reached for this group. For the 16 patients with localized gastrointestinal amyloidosis, supportive care was the mainstay of treatment; none received anti-plasma cell therapy. All 16 are alive at a median follow-up of 36 months (range, 1-143). Patients with biopsy-proven gastrointestinal amyloidosis often present with weight loss and bleeding. In localized cases, all that underwent typing were due to lambda light chain amyloidosis and none progressed to systemic disease during the period of follow-up. Most patients with systemic disease had immunoglobulin light-chain, and their tolerance of therapy and median survival were excellent. Although a rare manifestation of amyloidosis, staining for amyloid should be considered in patients undergoing gastrointestinal biopsy who have unexplained chronic gastrointestinal symptoms.

Safety of ERCP during pregnancy

OBJECTIVES

There are few data in the literature regarding the indications, therapy, and safety of endoscopic management of pancreatico-biliary disorders during pregnancy. We report the largest single center experience with ERCP in pregnancy.

METHODS

We reviewed 15 patients that underwent ERCP during pregnancy. In all patients, the pelvis was lead-shielded and the fetus was monitored by an obstetrician. Fluoroscopy was minimized and hard copy radiographs taken only when essential.

RESULTS

The mean patient age was 28.9 yr (15-36 yr). The mean duration of gestation was 25 wk (12-33 wk); one patient was in the first, five in the second, and nine in the third trimester. The indications were gallstone pancreatitis (n = 6), choledocholithiasis on ultrasound (n = 5), elevated liver enzymes and a dilated bile duct on ultrasound (n = 2), abdominal pain and gallstones (n = 1), and chronic pancreatitis (n = 1). ERCP findings were bile duct stones (n = 6), patulous papilla (n = 1), bile duct debris (n = 1), normal bile duct and gallstones or gallbladder sludge (n = 3), dilated bile duct and gallstones (n = 1), normal bile duct and no gallstones (n = 2), and chronic pancreatitis (n = 1). Six patients underwent sphincterotomies and one a biliary stent insertion. One sphincterotomy was complicated by mild pancreatitis. All infants delivered to date have had Apgar-scores >8, and continuing pregnancies are uneventful. Mean fluorosocopy time was 3.2 min (SD +/- 1.8). An estimated fetal radiation exposure was 310 mrad (SD +/- 164) which is substantially below the accepted teratogenic dose.

CONCLUSIONS

ERCP in pregnancy seems to be safe for both mother and fetus; however, it should be restricted to therapeutic indications with additional intraprocedure safety measures.

Accuracy and complication rate of brush cytology from bile duct versus pancreatic duct

BACKGROUND

The accuracy and complication rates of brush cytology obtained from pancreaticobiliary strictures have not been fully defined. In this study we compared the accuracy and complications of brush cytology obtained from bile versus pancreatic ducts.

METHODS

We identified 148 consecutive patients for whom brush cytology was done during an ERCP from a database with prospectively collected data. We compared cytology results with the final diagnosis as determined by surgical pathologic examination or long-term clinical follow-up. We followed all patients and recorded ERCP-related complications.

RESULTS

Forty-two pancreatic brush cytology samples and 101 biliary brush cytology samples were obtained. The accuracy rate of biliary cytology was 65 of 101 (64.3%) and the accuracy rate of pancreatic cytology was 30 of 42 (71.4%). Overall sensitivity was 50% for biliary cytology and 58.3% for pancreatic cytology. Of 67 patients with pancreatic adenocarcinoma, sensitivity for biliary cytology was 50% versus 66% for pancreatic cytology. Concurrent pancreatic and biliary cytology during the same procedure increased the sensitivity in only 1 of 10 (10%) patients. Pancreatitis occurred in 11 (11%) patients (9 mild cases, 2 moderate cases) after biliary cytology and in 9 (21%) patients (6 mild cases, 3 moderate cases) after pancreatic cytology (p = 0.22). In 10 patients who had pancreatic brush cytology, a pancreatic stent was placed. None of these patients developed pancreatitis versus 9 of 32 (28%) patients in whom a stent was not placed (p = 0.08). Pancreatic cytology samples obtained from the head of the pancreas were correct in 13 of 18 (72%) cases, from the genu in 7 of 7 (100%) cases, from the body in 5 of 9 (55%) cases, and from the tail in 4 of 7 (57%) cases.

CONCLUSION

The accuracy of biliary brush cytology is similar to the accuracy of pancreatic brush cytology. The yield of the latter for pancreatic adenocarcinoma is similar to that of the former. Complication rates for pancreatic cytology are not significantly higher than the rates for biliary cytology. The placement of a pancreatic stent after pancreatic brushing appears to reduce the risk of postprocedure pancreatitis.

Palliation of malignant gastric outlet obstruction using an endoscopically placed Wallstent

BACKGROUND

Treatment options for malignant gastric outlet obstruction are limited. Surgical gastrojejunostomy, commonly performed, has significant morbidity and mortality.

METHODS

Over 2 years, we prospectively studied the safety, feasibility, and outcomes for use of a newly designed expandable metal stent (Wallstent Enteral; Schneider, Minneapolis, Minn.) to treat malignant gastric outlet obstruction. Stents 16 to 22 mm in diameter and 60 to 90 mm in length were deployed directly through the endoscope.

RESULTS

Twelve patients (ten women, two men; mean age 59.7 years) underwent stenting. Thereafter, six patients were able to eat a regular diet; three could eat pureed food. In three patients, the procedure was unsuccessful because of multiple obstructions not recognized before stenting (one) and stents deployed too proximally (one) or too distally (one).

CONCLUSIONS

Placement of a newly designed stent through the endoscope is safe and effective palliation for various types of malignant gastric outlet obstruction and significantly improves many aspects of patient quality of life.

Management of occluded biliary Wallstents

BACKGROUND

Wallstents (Schneider Stent, Inc., USA) used for the palliation of malignant biliary strictures, although associated with prolonged patency, can occlude. There is no consensus regarding the optimal management of Wallstent occlusion.

AIMS

To evaluate the efficacy of different endoscopic methods for managing biliary Wallstent occlusion.

METHODS

A multicentre retrospective study of patients managed for a biliary Wallstent occlusion.

RESULTS

Data were available for 38 patients with 44 Wallstent occlusions, all of which had initial endoscopic management. Twenty four patients had died and 14 were alive after a median follow up of 231 (30-1095) days following Wallstent occlusion. Occlusions were managed by insertion of another Wallstent in 19, insertion of a plastic stent in 20, and mechanical cleaning in five. Endoscopic management was successful in 43 (98%). Following management of the occlusion, bilirubin decreased from 6.0 (0.5-34.3) to 2.1 (0.2-27.7) mg/100 ml (p < 0.05). No complications occurred. The median duration of second stent patency was 75 days (95% confidence interval 43 to 107) after insertion of another Wallstent, 90 days (71 to 109) after insertion of a plastic stent, and 34 days (30 to 38) after mechanical cleaning (NS). The respective median survivals were 70 days (22-118), 98 days (54-142), and 34 days (30-380) (NS). Incremental cost effective analysis showed that plastic stent insertion is the most cost effective option.

CONCLUSION

Although all three methods are equally effective in managing an occluded Wallstent, the most cost effective method appears to be plastic stent insertion.

Role of endoscopic retrograde cholangiopancreatography for suspected choledocholithiasis in patients undergoing laparoscopic cholecystectomy

BACKGROUND

We report our experience of selective cholangiography in a series of laparoscopic cholecystectomies and evaluate the strategy of using "stricter criteria" to select preoperative endoscopic retrograde cholangiopancreatography (ERCPs).

METHODS

A total of 1847 consecutive laparoscopic cholecystectomies were analyzed for use of cholangiography. A high risk of common bile duct stones (bilirubin level more than 2 mg/dL, jaundice, alkaline phosphatase level more than 150 U/L, pancreatitis, or dilated bile duct and/or stone on ultrasound or CT) was an indication for preoperative ERCP. Selective intraoperative cholangiography was performed for intermediate risk of bile duct stones. The strategy of using "stricter criteria" (jaundice and/or demonstrated bile duct stones on ultrasound or CT) for selecting preoperative ERCP was evaluated retrospectively.

RESULTS

Preoperative ERCP was performed in 135 patients (7.3%) and demonstrated bile duct stones in 43 (32%). Of 36 patients with mild gallstone pancreatitis alone, stones were found only in 6 patients (17%). Selective intraoperative cholangiography was performed in 87 (5%), and stones were found in 2 (2%); 67 (3.6%) postoperative ERCPs were performed for suspected choledocholithiasis, and stones were found in 21 (32%). Applying "stricter criteria" to select preoperative ERCP would predict ductal stones in 56%, whereas 3% of patients with stones would be missed, resulting in a 50% reduction in preoperative ERCPs.

CONCLUSIONS

Even in selected patients considered likely to have choledocholithiasis, the diagnostic yield of preoperative ERCP is low. Using "stricter criteria" to select patients for preoperative ERCP can avoid unnecessary ERCPs.

Endoscopic sphincterotomy for stones by experts is safe, even in younger patients with normal ducts

OBJECTIVE

To provide current information on the risks of endoscopic sphincterotomy for stone.

SUMMARY BACKGROUND DATA

In recent years (since the popularity of laparoscopic cholecystectomy), endoscopic sphincterotomy has been used increasingly for the management of bile duct stones in relatively young and healthy patients. The validity of this trend has been questioned using data on short-term complications derived from earlier decades that involved more elderly and high-risk patients.

METHODS

Seven academic centers collected data prospectively using a common database. Complications within 30 days of the procedures were documented by standard criteria.

RESULTS

Of 1921 patients, 112 (5.8%) developed complications; two thirds of these events were graded as mild (<3 days in hospital). There was no evidence of increased risk in younger patients or in those with smaller bile ducts. There was only one severe complication and there were no fatalities in 238 patients age <60, with bile duct diameters of <9 mm.

CONCLUSION

Sphincterotomy for stones can be performed very safely by experienced endoscopists.

Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy: A Randomized Trial

BACKGROUND & AIMS

Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit and safety of using a computer-aided detection (CADe) device in colonoscopy procedures.

METHODS

This randomized study prospectively evaluated the use of a CADe device at 5 academic and community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled for screening or surveillance (≥3 years) colonoscopy were included; exclusion criteria included incomplete procedure, diagnostic indication, inflammatory bowel disease, and familial adenomatous polyposis. Patients were randomized by endoscopist to the standard or CADe colonoscopy arm using computer-generated, random-block method. The 2 primary endpoints were adenomas per colonoscopy (APC), the total number of adenomas resected divided by the total number of colonoscopies; and true histology rate (THR), the proportion of resections with clinically significant histology divided by the total number of polyp resections. The primary analysis used a modified intention-to-treat approach.

RESULTS

Between January and September 2021, 1440 participants were enrolled to be randomized. After exclusion of participants who did not meet the eligibility criteria, 677 in the standard arm and 682 in the CADe arm were included in a modified intention-to-treat analysis. APC increased significantly with use of the CADe device (standard vs CADe: 0.83 vs 1.05, P = .002; total number of adenomas, 562 vs 719). There was no decrease in THR with use of the CADe device (standard vs CADe: 71.7% vs 67.4%, P for noninferiority < .001; total number of non-neoplastic lesions, 284 vs 375). Adenoma detection rate was 43.9% and 47.8% in the standard and CADe arms, respectively (P = .065).

CONCLUSIONS

For experienced endoscopists performing screening and surveillance colonoscopies in the United States, the CADe device statistically improved overall adenoma detection (APC) without a concomitant increase in resection of non-neoplastic lesions (THR).

CLINICALTRIALS

gov registration: NCT04754347.

Endoscopic palliation for unresectable pancreatic carcinoma

Endoscopic stenting has revolutionized the palliation of malignant biliary obstruction. Individuals with biliary obstruction due to pancreatic malignancy are best managed by a team approach comprising individuals with expertise in oncology, surgery, endoscopy, and radiology. The clinical value of alleviating jaundice and associated symptoms of anorexia, pruritus, and malaise cannot be overestimated. These quality-of-life factors deserve more attention in future studies to define subgroups of patients most likely to derive benefit from the array of treatment options. Further technical improvements are required to solve the most important clinical problem of late stent occlusion. New developments such as expandable metallic stents and refinements in existing equipment and techniques have already resulted in measurable gains and hold great promise for future expansion of their use in malignant gastric outlet obstruction secondary to tumor infiltration of the duodenum. Corresponding advances are being made in the fields of percutaneous transhepatic intervention and hepatobiliary surgery such that further prospective randomized trials are necessary to define optimal therapy.

Artificial intelligence in gastrointestinal endoscopy

BACKGROUND AND AIMS

Artificial intelligence (AI)-based applications have transformed several industries and are widely used in various consumer products and services. In medicine, AI is primarily being used for image classification and natural language processing and has great potential to affect image-based specialties such as radiology, pathology, and gastroenterology (GE). This document reviews the reported applications of AI in GE, focusing on endoscopic image analysis.

METHODS

The MEDLINE database was searched through May 2020 for relevant articles by using key words such as machine learning, deep learning, artificial intelligence, computer-aided diagnosis, convolutional neural networks, GI endoscopy, and endoscopic image analysis. References and citations of the retrieved articles were also evaluated to identify pertinent studies. The manuscript was drafted by 2 authors and reviewed in person by members of the American Society for Gastrointestinal Endoscopy Technology Committee and subsequently by the American Society for Gastrointestinal Endoscopy Governing Board.

RESULTS

Deep learning techniques such as convolutional neural networks have been used in several areas of GI endoscopy, including colorectal polyp detection and classification, analysis of endoscopic images for diagnosis of Helicobacter pylori infection, detection and depth assessment of early gastric cancer, dysplasia in Barrett's esophagus, and detection of various abnormalities in wireless capsule endoscopy images.

CONCLUSIONS

The implementation of AI technologies across multiple GI endoscopic applications has the potential to transform clinical practice favorably and improve the efficiency and accuracy of current diagnostic methods.