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.

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.

Bleeding After Elective Interventional Endoscopic Procedures in a Large Cohort of Patients With Cirrhosis.

INTRODUCTION: Elective therapeutic endoscopy is an important component of care of cirrhotic patients, but there are concerns regarding the risk of bleeding. This study examined the incidence, risk factors, and outcomes of bleeding after endoscopic variceal ligation (EVL), colonoscopic polypectomy, and endoscopic retrograde cholangiopancreatography with sphincterotomy in cirrhotic patients. METHODS: A cohort study of patients with cirrhosis who underwent the above procedures at a single center between 2012 and 2014 was performed. Patients with active bleeding at the time of procedure were excluded. Patients were followed for 30 days to assess for postprocedural bleeding and for 90 days for mortality. RESULTS: A total of 1,324 procedures were performed in 857 patients (886 upper endoscopies, 358 colonoscopies, and 80 endoscopic retrograde cholangiopancreatograpies). After EVL, bleeding occurred in 2.8%; after polypectomy, bleeding occurred in 2.0%; and after sphincterotomy, bleeding occurred in 3.8%. Independent predictors of bleeding after EVL and polypectomy included younger age and lower hemoglobin. For EVL, bleeding was also associated with infection and model for end-stage liver disease-Na. International normalized ratio was associated with bleeding in univariate analysis only, and platelet count was not associated with bleeding in any procedure. Bleeding after EVL was associated with 29% 90-day mortality, and bleeding after polypectomy was associated with 14% mortality. Of the 3 patients with postsphincterotomy bleeding, none were outliers regarding their baseline characteristics. DISCUSSION: In patients with cirrhosis, bleeding occurs infrequently after elective therapeutic endoscopy and is associated with younger age, lower hemoglobin, and high mortality. Consideration of these risk factors may guide appropriate timing and preprocedural management to optimize outcomes.

Pembrolizumab-Induced Immune-Mediated Hepatitis and Concurrent Hepatitis B Reactivation in a Patient With Non-Small Cell Lung Cancer.

New immuno-therapeutic agents like pembrolizumab used in cancer treatment are known to cause immune-mediated hepatitis. Most of these cases are straightforward when the onset of transaminitis correlates with the introduction of the medication. This agent causing hepatitis B reactivation has been reported only once. To have both these adverse effects occurring at the same time in a patient is uncommon and presents a clinical challenge. Our patient was a 49-year-old gentleman diagnosed with metastatic adenocarcinoma of the lung seven months ago. He was started on pembrolizumab, as the malignant tissue obtained during biopsy had high program death-ligand 1 (PDL1) expression. On reviewing the labs ordered during the time of cancer diagnosis, this man has evidence of chronic hepatitis B with positive hepatitis B surface antigen and positive hepatitis B core immunoglobulin G (IgG) antibody. He presented with acute hepatitis, and workup showed features of hepatitis B reactivation, but the extent of reactivation was not adequate to explain the presentation, hence investigations were pursued. This led the way to the diagnosis of a combined hepatitis B reactivation and drug-induced immune hepatitis in this case. He responded promptly to the withdrawal of the agent and steroids. On follow-up, his liver function panel had significantly improved.  This case is very unique in two aspects. First, to our knowledge, there is only one case reported of pembrolizumab-induced hepatitis B reactivation. In addition, our patient also had immune-mediated hepatitis induced by pembrolizumab. It is very rare to have a combination of these two presentations to be seen in a patient at the same time. Pembrolizumab-induced immune hepatitis can coexist with hepatitis B reactivation following therapy with this agent.

Metastatic Mucinous Adenocarcinoma of the Cervix Presenting as Acute Hepatitis.

Cervical cancer is well known to cause metastasis in liver. Not usually they present in a pattern of acute hepatitis with the liver enzymes trending above the range of thousands. Here we present an interesting case of a patient who presented as acute hepatitis in the setting of metastatic cervical cancer to the liver. She presented with elevated liver enzymes above thousands. Her imaging studies revealed new metastatic lesions in the liver. She was subsequently started on chemotherapy but unfortunately, two months later developed septic shock and expired. To our knowledge this is the only case describing a malignancy with metastasis to the liver presenting as an acute hepatitis picture. All the other cases that have been described in the literature presented with acute liver failure.

Variations in Screening Adenoma Detection Rate by Specialty of Physicians in a Predominately African American Population.

BACKGROUND: Screening colonoscopy aims to interrupt the adenoma-carcinoma sequence by removing all precancerous adenomatous polyps. Adenomatous polyp detection rate (ADR) can vary between endoscopists as well as between race, age, and risk of colorectal cancer (CRC). The purpose of this study was to compare ADR among academic gastroenterologists (A-GI), non-A-GI, and surgeons for endoscopies performed in the same endoscopic suite of a large medical center with a predominately African American (AA) population. METHODS: All screening colonoscopies performed in 2014 for patients aged 62-76 years were identified using the electronic medical records data. Patients with average risk and high risk of CRC defined as having a 'personal history of polyps' or 'family history of CRC', and history of ulcerative colitis and Fecal Occult Blood Test/Fecal Immunochemical Test (FOBT/FIT) positivity were included. Patients with incomplete colonoscopy (defined as failing to achieve cecal intubation or poor preparation) and unrecovered tissue biopsy were excluded. ADR was calculated for three groups of endoscopists: A-GIs, non-A-GIs, and surgeons. RESULTS: A total of 573 screening colonoscopies was analyzed. The endoscopists comprised five A-GIs, eight non-A-GIs, and six surgeons. The majority of patients were of AA decent (71%), female (54%) with an average age of 66 years. Patients classified as average risk comprised 79% of the population. Most of the colonoscopies were performed by A-GI (n=339), followed by non-A-GI (n=144), and surgeons (n=90). The ADR for A-GI was 50% as compared to 32% for non-A-GI (p<0.001) and 25% for surgeons (p<0.001). Also, A-GI were more likely to identify ≥3 adenomas during screening colonoscopies. Significant differences were observed (p<0.001) in the mean time of colonoscopy for A-GI (30 mins) non-A-G (14 mins), and surgeons (18 mins). CONCLUSION: Significant variation in the ADR between endoscopists belonging to different specialties were observed. Although all appear to achieve acceptable ADR (ie at least 25 for men and 15 for women), academic gastroenterologists had better performance than non-academic GI and surgeons. This may be explained by a significantly longer average duration of procedures for the highest ADR group.

A case of acute liver failure due to carfilzomib in multiple myeloma.

WHAT IS KNOWN AND STUDY OBJECTIVE: Carfilzomib is a newer drug approved for the treatment of relapsing and refractory multiple myeloma. It has been rarely associated with acute liver failure (ALF). CASE SUMMARY: We present a case of 58-year-old man presenting with abnormal liver function tests and subsequently diagnosed with ALF due to carfilzomib. Liver enzymes improved significantly after discontinuation of the drug. WHAT IS NEW AND CONCLUSION: Even though ALF due to carfilzomib has been documented rarely in clinical studies, no detailed case report has been published so far. Patients on carfilzomib should be monitored for ALF, and prompt discontinuation of drug is necessary in such cases.