Deep Learning Computer-aided Polyp Detection Reduces Adenoma Miss Rate: A United States Multi-center Randomized Tandem Colonoscopy Study (CADeT-CS Trial).

BACKGROUND & AIMS: Artificial intelligence-based computer-aided polyp detection (CADe) systems are intended to address the issue of missed polyps during colonoscopy. The effect of CADe during screening and surveillance colonoscopy has not previously been studied in a United States (U.S.) population. METHODS: We conducted a prospective, multi-center, single-blind randomized tandem colonoscopy study to evaluate a deep-learning based CADe system (EndoScreener, Shanghai Wision AI, China). Patients were enrolled across 4 U.S. academic medical centers from 2019 through 2020. Patients presenting for colorectal cancer screening or surveillance were randomized to CADe colonoscopy first or high-definition white light (HDWL) colonoscopy first, followed immediately by the other procedure in tandem fashion by the same endoscopist. The primary outcome was adenoma miss rate (AMR), and secondary outcomes included sessile serrated lesion (SSL) miss rate and adenomas per colonoscopy (APC). RESULTS: A total of 232 patients entered the study, with 116 patients randomized to undergo CADe colonoscopy first and 116 patients randomized to undergo HDWL colonoscopy first. After the exclusion of 9 patients, the study cohort included 223 patients. AMR was lower in the CADe-first group compared with the HDWL-first group (20.12% [34/169] vs 31.25% [45/144]; odds ratio [OR], 1.8048; 95% confidence interval [CI], 1.0780-3.0217; P = .0247). SSL miss rate was lower in the CADe-first group (7.14% [1/14]) vs the HDWL-first group (42.11% [8/19]; P = .0482). First-pass APC was higher in the CADe-first group (1.19 [standard deviation (SD), 2.03] vs 0.90 [SD, 1.55]; P = .0323). First-pass ADR was 50.44% in the CADe-first group and 43.64 % in the HDWL-first group (P = .3091). CONCLUSION: In this U.S. multicenter tandem colonoscopy randomized controlled trial, we demonstrate a decrease in AMR and SSL miss rate and an increase in first-pass APC with the use of a CADe-system when compared with HDWL colonoscopy alone.

ERCP within 6 or 12 h for acute cholangitis: a propensity score-matched analysis.

BACKGROUND: The optimal timing of biliary drainage by endoscopic retrograde cholangiopancreatography (ERCP) for patients with acute cholangitis remains controversial. The aim of our study was to determine if ERCP performed within 6 or 12 h of presentation was associated with improved clinical outcomes. METHODS: Medical records for all patients with acute cholangitis who underwent ERCP at our institution between 2009 and 2018 were reviewed. Outcomes were compared between those who underwent ERCP within or after 12 h using propensity score framework. Our primary outcome was length of hospitalization. Secondary outcomes included in-hospital mortality, adverse events, ERCP failure, length of ICU stay, organ failure, recurrent cholangitis, and 30-day readmission. In secondary analysis, outcomes for ERCP done within or after 6 h were also compared. RESULTS: During study period, 487 patients with cholangitis were identified, of whom 147 had ERCP within 12 h of presentation. Using propensity score matching, we selected 145 pairs of patients with similar characteristics. Length of hospitalization was similar between ERCP within or after 12 h (135.9 vs 122.1 h, p 0.094). No difference was noted in mortality, ERCP failure, adverse events, need and length of ICU stay, and recurrent cholangitis. However, 30-day readmission rates were lower when ERCP within 12 h (7.6 vs 15.2, p 0.042). No significant difference was noted in aforementioned outcomes between ERCP performed within or after 6 h. CONCLUSIONS: ERCP performed within 6 h or 12 h of presentation was not associated with superior clinical outcomes, however, may result in reduced re-hospitalization.

Effectiveness of a Deep-learning Polyp Detection System in Prospectively Collected Colonoscopy Videos With Variable Bowel Preparation Quality.

BACKGROUND: Colonoscopy is the gold standard for polyp detection, but polyps may be missed. Artificial intelligence (AI) technologies may assist in polyp detection. To date, most studies for polyp detection have validated algorithms in ideal endoscopic conditions. AIM: To evaluate the performance of a deep-learning algorithm for polyp detection in a real-world setting of routine colonoscopy with variable bowel preparation quality. METHODS: We performed a prospective, single-center study of 50 consecutive patients referred for colonoscopy. Procedural videos were analyzed by a validated deep-learning AI polyp detection software that labeled suspected polyps. Videos were then re-read by 5 experienced endoscopists to categorize all possible polyps identified by the endoscopist and/or AI, and to measure Boston Bowel Preparation Scale. RESULTS: In total, 55 polyps were detected and removed by the endoscopist. The AI system identified 401 possible polyps. A total of 100 (24.9%) were categorized as "definite polyps;" 53/100 were identified and removed by the endoscopist. A total of 63 (15.6%) were categorized as "possible polyps" and were not removed by the endoscopist. In total, 238/401 were categorized as false positives. Two polyps identified by the endoscopist were missed by AI (false negatives). The sensitivity of AI for polyp detection was 98.8%, the positive predictive value was 40.6%. The polyp detection rate for the endoscopist was 62% versus 82% for the AI system. Mean segmental Boston Bowel Preparation Scale were similar (2.64, 2.59, P=0.47) for true and false positives, respectively. CONCLUSIONS: A deep-learning algorithm can function effectively to detect polyps in a prospectively collected series of colonoscopies, even in the setting of variable preparation quality.

A Case of Fulminant Hepatic Failure Secondary to Congestive Heart Failure Without Evidence of Acute Cardiac Decompensation.

There are so far only a few reported cases of acute fulminant hepatic failure resulting from acute cardiomyopathy. This is a rare occurrence, especially in patients that do not exhibit any signs and symptoms of acute cardiac decompensation. We report a case of fulminant liver failure with nondiagnostic work up for the common causes of liver failure. This patient had concurrent history of congestive heart failure, but did not have acute decompensation. Right upper quadrant sonogram revealed hepatomegaly of 15 cm, trace amount of perihepatic ascites, pericholecystic fluid, and also thickened edematous gallbladder wall with no stones, no common bile duct stones, and no portal vein thrombosis. Echocardiogram revealed dilated left atrium and ventricle, severe mitral regurgitation, severe tricuspid regurgitation, grade 4 diastolic dysfunction, diffuse hypokinesis of left ventricle, and severely and newly reduced systolic function with an ejection fraction of 10 percent (decreased from 25 percent on last ECHO 18 months prior). Liver biopsy demonstrated marked centrilobular hepatocyte necrosis and dropout accompanied by congestion, some areas of bridging necrosis and focal confluent necrosis which was suggestive of severe congestive hepatopathy. With initiation of heart failure medications, liver function improved significantly.

Prospective assessment of the accuracy of ASGE and ESGE guidelines for choledocholithiasis.

Background and study aims American Society of Gastrointestinal Endoscopy (ASGE) and European Society of Gastrointestinal Endoscopy (ESGE) guidelines recommend categorizing patients by risk for choledocholithiasis to determine management. The goal of our study was to compare the accuracy of criteria proposed in these guidelines. Patients and methods All patients with suspected choledocholithiasis at our institution were prospectively identified. Based upon initial test results, patients were categorized as low, intermediate, and high risk for choledocholithiasis per ASGE 2010 and 2019, and ESGE criteria. Patients were followed until 30 days post-discharge. Results of endoscopic retrograde cholangiography (ERCP), endoscopic ultrasound, and magnetic resonance cholangiopancreatography were used as criteria standard for choledocholithiasis. The accuracy of each criterion for choledocholithiasis was computed. Results During the study period, 359 consecutive patients with suspected choledocholithiasis were identified, of whom 225 had choledocholithiasis. Median patient age was 69 years and 55.3% were women. ESGE criteria categorized 47.9% as high-risk, lower than ASGE 2010 (62.7%, P <0.01), and 2019 criteria (54.6%, P =0.07). In high-risk patients, choledocholithiasis was noted in 83.1% for ESGE criteria, similar for ASGE 2019 (81.6%, P =0.7) and 2010 criteria (79.1%, P =0.3). The percentage of patients who underwent unnecessary ERCP was 8.1% per ESGE criteria, lower than ASGE 2010 (13.1%, P =0.03), but similar to 2019 criteria (10%, P =0.4). No difference in accuracy for choledocholithiasis was noted among the three criteria. No 30-day readmissions for choledocholithiasis were noted in the low-risk category. Conclusions ESGE and ASGE guidelines have similar accuracy for diagnosis of choledocholithiasis. However, ESGE criteria result in more patients needing additional testing, but also a smaller proportion of patients undergoing unnecessary ERCP.

An Intriguing Case of Multisystem Inflammatory Syndrome in an Adult Patient with Remote Infection with COVID-19 and Acute Chlamydia.

INTRODUCTION: COVID-19 is associated with a broad range of immune inflammatory phenomena, with different manifestations in adults and children. We describe a case of COVID-19-related multisystem inflammatory syndrome in an adult (MIS-A), similar to that described in children (MIS-C), which may have been set off by an unrelated secondary infection. CASE: A 27-year-old male patient presented with acute epididymitis secondary to acute Chlamydia infection that progressed to multisystem inflammatory failure with respiratory failure requiring endotracheal intubation and mechanical ventilation, cardiogenic shock with heart failure, and gastrointestinal and renal dysfunction. He tested negative for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by reverse transcriptase-polymerase chain reaction on a nasopharyngeal swab thrice within 4 days of presentation, but positive for SARS-CoV-2 immunoglobulin G antibody signifying remote infection. The patient was treated with tocilizumab and steroids, along with doxycycline for concurrent Chlamydia infection, resulting in dramatic improvement in all organ function. We suspect that C. trachomatis infection in this instance may have triggered an aberrant immune response that was shaped by prior exposure to SARS-CoV-2. CONCLUSION: We present a case of an adult patient with acute Chlamydia trachomatis infection occurring in the wake of asymptomatic (or at least unrecognized) COVID-19 resulting in MIS-A. Clinicians should be alert to the possibility of other such unusual reactions occurring in the aftermath of COVID-19. This case also highlights the importance for clinicians who care for adult patients of being familiar with the multisystem inflammatory syndrome of children, as an identical syndrome may occur in adult patients.

Use of fully covered self-expanding metal biliary stents for managing endoscopic biliary sphincterotomy related bleeding.

Background and study aims Endoscopic biliary sphincterotomy (EBS) related-bleeding is a common adverse event related to endoscopic retrograde cholangiopancreatography (ERCP). Traditionally, endoscopic modalities such as epinephrine injection, cauterization, and balloon tamponade have been used for management. Recently, use of a fully covered self-expandable metal stent (FCSEMS) to manage EBS-related bleeding has gained popularity. However, data regarding its use are limited to small case series. Therefore, we aimed to evaluate the safety and efficacy of FCSEMS placement for the treatment of EBS-related bleeding. Patients and methods All patients referred to our center from October 2014 to November 2019 who had an FCSEMS placed for EBS-related bleeding were included. FCSEMS was placed either for primary control of bleeding or after failure of other traditional endoscopic hemostasis techniques at the discretion of the endoscopist. Data was collected regarding patient demographics, procedural characteristics, clinical and technical success rates of FCSEMS, as well as adverse events. Results A total of 97 patients underwent placement of FCSEMS for EBS-related bleeding, of which 76.3 % had immediate bleeding and 23.7 % had delayed bleeding. Mean age was 67.2 years and 47.4 % were males. Seven patients who had immediate EBS-related bleeding at index ERCP underwent other endoscopic therapies prior to placement of FCSEMS for rebleeding. The technical success rate for FCSEMS placement was 100 % and the rebleeding rate was 6.2 %. Four patients with FCSEMS placement developed pancreatitis and four had stent migration. Conclusions Our findings suggest that FCSEMS is a highly effective treatment modality for managing EBS-related bleeding and has an acceptable safety profile.

EUS-guided fiducial placement for pancreatobiliary malignancies: safety, infection risk, and use of peri-procedural antibiotics.

Background and study aims Chemoradiation with stereotactic body radiation therapy (SBRT) is increasingly being used for optimal treatment of locally advanced pancreatobiliary cancers. Fiducial markers are used to track these tumors during SBRT. Endoscopic ultrasound (EUS) is the preferred route for fiducial marker placement for ease of access to pancreatobiliary structures and accurate placement. Here we evaluate the safety and infection risk associated with EUS-guided fiducial placement for pancreatobiliary malignancies and use of peri-procedural prophylactic antibiotics. Patients and methods This was a retrospective, single-center study including consecutive patients presenting for EUS-guided fiducial placement in pancreatobiliary region by three expert interventional endoscopists for SBRT from July 2010 to February 2018 at a tertiary care center. Patient demographics, tumor characteristics, EUS technique, fiducials, use of prophylactic antibiotics, adverse events (AEs) and SBRT/Cyberknife administration were reported. Results A total of 355 patients with pancreatobiliary malignancy underwent EUS-guided fiducial placement, of whom 308 patients (86.76 %) successfully underwent SBRT. Of the patients, 304 (85.63 %) received peri-procedural prophylactic antibiotic. Of 355 total patients, 5.9 % (n = 21) were noted to develop AEs (mild to severe) with no significant difference in incidence of infection with or without use of peri-procedural prophylactic antibiotic. Only three patients developed infectious AEs, none of which were definitively related to fiducial placement. Conclusion EUS-guided fiducial placement for pancreatobiliary malignancy is safe and efficacious, and risk of infection is rare, regardless of whether or not peri-procedural antibiotics are used. We favor limiting routine use of peri-procedural antibiotics for patients undergoing EUS-guided fiducial placement in pancreaticobiliary malignancy.

Combined Approach of Cryoablation and Stent-In-Stent Technique for Removal of an Embedded Esophageal Stent.

Self-expanding removable stents are used for the treatment of esophageal strictures. Partially covered metal stents become embedded in the esophageal wall due to mucosal tissue reaction providing good anchorage. This can also lead to extreme difficulty in the removal of such stents. Several different individual techniques have been used in literature for removal of these esophageal stents. Ours is the first case using a combination of cryoablation and stent-in-stent technique for removal of an extremely difficult case of embedded esophageal stent.

Eicosapentaenoic and Docosahexaenoic Acids Attenuate Progression of Albuminuria in Patients With Type 2 Diabetes Mellitus and Coronary Artery Disease.

BACKGROUND: Albuminuria is a marker of inflammation and an independent predictor of cardiovascular morbidity and mortality. The current study evaluated whether eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) supplementation attenuates progression of albuminuria in subjects with coronary artery disease. METHODS AND RESULTS: Two-hundred sixty-two subjects with stable coronary artery disease were randomized to either Lovaza (1.86 g of EPA and 1.5 g of DHA daily) or no Lovaza (control) for 1 year. Percent change in urine albumin-to-creatinine ratio (ACR) was compared. Mean (SD) age was 63.3 (7.6) years; 17% were women and 30% had type 2 diabetes mellitus. In nondiabetic subjects, no change in urine ACR occurred in either the Lovaza or control groups. In contrast, ACR increased 72.3% (P<0.001) in diabetic subjects not receiving Lovaza, whereas those receiving Lovaza had no change. In diabetic subjects on an angiotensin-converting enzyme-inhibitor or angiotensin-receptor blocker, those receiving Lovaza had no change in urine ACR, whereas those not receiving Lovaza had a 64.2% increase (P<0.001). Change in ACR was directly correlated with change in systolic blood pressure (r=0.394, P=0.01). CONCLUSIONS: EPA and DHA supplementation attenuated progression of albuminuria in subjects with type 2 diabetes mellitus and coronary artery disease, most of whom were on an angiotensin-converting enzyme-inhibitor or angiotensin-receptor blocker. Thus, EPA and DHA supplementation should be considered as additional therapy to an angiotensin-converting enzyme-inhibitor or angiotensin-receptor blocker in subjects with type 2 diabetes mellitus and coronary artery disease. CLINICAL TRIAL REGISTRATION: URL: http://www.clinicaltrials.gov. Unique identifier: NCT01624727.

A Case Report About the Most Common Yet Most Forgotten Hepatitis E.

BACKGROUND Hepatitis E virus (HEV) is the most common cause of enterically acquired acute viral hepatitis worldwide with major prevalence in the developing countries. An increasing number of sporadic cases of acute HEV infection have also been found in developed countries, but there is still no role for HEV testing in cases of seronegative acute hepatitis in such nonendemic regions. CASE REPORT A 59-year-old male residing in the United States for seven months with a history of malaria treated one year ago presented with fatigue and cholestatic jaundice with very high bilirubin levels. Hepatitis A, B, and C viral serology along with other atypical infections were ruled out. No history of any kind of drug intake was reported. Liver biopsy was obtained and was suggestive of acute hepatitis. Eventually hepatitis E immunoglobulin M was checked and was found positive. The patient was treated with supportive care and improved gradually with normalization of liver function test in a few weeks. CONCLUSIONS Autochthonous HEV infection must be suspected in cases of acute viral hepatitis in developed countries. Timely detection of HEV infection is necessary, especially in immunocompromised patients, in whom treatment is required to eradicate the infection.

Coagulopathy in cirrhosis: A prospective study to correlate conventional tests of coagulation and bleeding following invasive procedures in cirrhotics.

BACKGROUND: Conventional tests of coagulation which only measure procoagulant factors do not correctly estimate the actual in vivo hemostatic balance in cirrhosis. This prospective multicenter study was conducted to evaluate safety of various invasive procedures in the presence of abnormal coagulation tests and to correlate conventional coagulation parameters with clinically significant bleeding in cirrhotics. METHODS: Three hundred and eighty patients (median age 54 years, 287 males) enrolled in the study were divided into two groups (A and B), according to the presence or absence of abnormal coagulation parameters (defined as INR ≥1.5 and/or platelet count ≤50,000/cum). RESULTS: One hundred and twenty-eight patients (33.68%) were qualified in group A. Alcohol was the predominant etiology of cirrhosis (40% and 32% in groups A and B, respectively). The two groups were similar in baseline characteristics other than tests of coagulation and severity of liver disease. Low risk procedures (abdominal paracentesis most common) were carried out in 47% and 53% patients in two groups, respectively. None of the patients in either group had clinically significant bleeding. Similarly, high risk procedures (central vein cannulation, liver biopsy, etc.) were carried out in 14% and 10%, respectively, in two groups. Three patients in group A developed clinically significant bleeding, however, the difference was statistically nonsignificant (p=0.061). None of our patients received periprocedural correction of abnormal coagulation parameters with plasma/platelet concentrate. CONCLUSIONS: Deranged conventional coagulation parameters did not predict clinically significant bleeding in cirrhosis. Whenever indicated, any invasive procedure could be safely carried out in patients with cirrhosis without prior correction of coagulation abnormalities.

Acute-on-chronic liver failure: a prospective study to determine the clinical profile, outcome, and factors predicting mortality.

BACKGROUND: Acute-on-chronic liver failure (ACLF), defined differently by different associations, lacks consensus on clinical profile, precipitating events and factors predicting mortality. This prospective multicentric study was conducted to determine the relevance of European Association for Study of Liver (EASL) and Asia Pacific Association for Study of Liver (APASL) definitions and to determine prognostic factors predicting the survival. METHODS: Consecutive patients over a 3-month period with any form of acute deterioration were evaluated for presence of ACLF, as defined by APASL or EASL-Chronic Liver Failure (CLIF) criteria. Those enrolled underwent complete evaluation for identifying the acute insults, underlying chronic etiologies, presence of organ failures, and short-term survival. RESULTS: Sixty-two patients (median age 53 years, 51 males) who presented with either raised bilirubin (n = 52), international normalized ratio (INR) >1.5 (n = 46), new onset ascites (n = 53), or hepatic encephalopathy (n = 39) were included in study. Forty-four patients (36 males, 25 alcoholics) satisfied APASL definition of ACLF, with a mortality rate of 43.1 %. Hepatic encephalopathy (p-value 0.022) was significantly associated with mortality. By CLIF-Sequential Organ Failure Assessment (SOFA) score criteria for organ failure, 50 patients (80.6 %) had at least 1 organ failure whereas 15 had ≥3 organ failures (mortality rate >75 %). Twenty-nine patients classified as ACLF (1, 2, or 3) as per EASL-CLIF criteria. Bacterial infection, >1 precipitating event, additional organ failure, total leukocyte count, INR, and serum creatinine were significantly higher in patients with ACLF across all grades. Mortality rates were 6.6 and >60 % in patients with ACLF only by APASL criteria vs. by both criteria, respectively. CONCLUSIONS: ACLF, as defined by APASL in terms of liver failure, identified some patients with better survival rates as compared to EASL-CLIF definition which identifies presence of additional organ failures and high mortality.

A multicenter prospective study of infections related morbidity and mortality in cirrhosis of liver.

BACKGROUND AND AIMS: Infections are a common and serious complication among patients with cirrhosis. We assessed the epidemiology, risk factors, and clinical consequences of bacterial infections in cirrhotic patients. METHODS: In this multicenter prospective study, all patients with cirrhosis of liver with different infections were analyzed. Infections were classified as community-acquired (CA), healthcare-associated (HCA), or hospital-acquired (HA). Site of infection and characteristics of bacteria were recorded; effect on liver function and 30-day survival were evaluated. RESULTS: One hundred and six out of 420 (25 %) patients with cirrhosis of liver had infection. Infection rate among indoor patients was 37.5 % (92/245) and among outdoor patients was 8 % (14/175). Out of 106 patients, CA, HCA, and HA were seen in 19.8 %, 50 %, and 30.2 %, respectively. Spontaneous bacterial peritonitis (31.1 %), urinary tract infections (22.6 %), and pneumonia and cellulitis (11.3 % each) were common infections. Gram-negative bacteria (54 %) were more common than Gram-positive cocci (46 %). Multidrug resistant (MDR) organisms were seen in 41.7 % of patients. Most of the MDR organisms were seen in HCA and HA patients. The degree of liver impairment was significantly more severe in patients with infection. Independent predictor of infection was high Child-Turcott-Pugh (CTP) class (p = 0.006, Child B vs. A (odds ratio (OR) 3.04 95 % CI = 1.63 to 5.68) and Child C vs. A (OR 4.17 95 % CI = 2.12 to 8.19). Overall in-hospital mortality was 7.6 %. Patients with infection had increased mortality at 30-day follow up compared to those without infection (23.5 % vs. 2.2 %; p<0.001). CONCLUSIONS: Infections are one of the important causes of morbidity and mortality in patients with cirrhosis of liver. The most frequent infections are HCA and HA. Infection predisposes to deterioration of liver function and increases mortality. Cirrhotic patients should be monitored closely for infections especially those with Child class B and C.