Influence of Artificial Intelligence on the Adenoma Detection Rate throughout the Day.

BACKGROUND: Artificial intelligence systems recently demonstrated an increase in polyp and adenoma detection rate. Over the daytime, the adenoma detection rate decreases as tiredness leads to a lack of attention. It is not clear if a polyp detection system with artificial intelligence leads to constant adenoma detection over the day. METHODS: We performed a database analysis of screening and surveillance colonoscopies with and without the use of AI. In both groups, patients were investigated with the same endoscopy equipment and by the same endoscopists. Only patients with good bowel preparation (BBPS >6) were included. We correlated the daytime, the investigational time, day of the week, and the adenoma and polyp detection. RESULTS: A total of 303 colonoscopies were analyzed. 163 endoscopies in the AI+ group and 140 procedures in the AI- group were included. In both groups, the total adenoma detection rate was equal (AI+ 0.39 vs. AI- 0.43). The adenoma detection rate throughout the day had a significant decreasing trend in the group without the use of AI (p = 0.015), whereas this trend was not present in the investigations that have been performed with AI (p = 0.65). The duration of investigation did not show a significant difference between the groups (8.9 min in both groups). No relevant effect was noticed in adenoma detection between single days of the working week with or without the use of AI. CONCLUSION: AI helps overcome the decay in adenoma detection over the daytime. This may be attributed to a constant awareness caused by the use of the AI system.

Percutaneous transhepatic or endoscopic ultrasound-guided biliary drainage in malignant distal bile duct obstruction using a self-expanding metal stent: Study protocol for a prospective European multicenter trial (PUMa trial).

BACKGROUND: Endoscopic ultrasound-guided biliary drainage (EUS-BD) was associated with better clinical success and a lower rate of adverse events (AEs) than fluoroscopy-guided percutaneous transhepatic biliary drainage (PTBD) in recent single center studies with mainly retrospective design and small case numbers (< 50). The aim of this prospective European multicenter study is to compare both drainage procedures using ultrasound-guidance and primary metal stent implantation in patients with malignant distal bile duct obstruction (PUMa Trial). METHODS: The study is designed as a non-randomized, controlled, parallel group, non-inferiority trial. Each of the 16 study centers performs the procedure with the best local expertise (PTBD or EUS-BD). In PTBD, bile duct access is performed by ultrasound guidance. EUS-BD is performed as an endoscopic ultrasound (EUS)-guided hepaticogastrostomy (EUS-HGS), EUS-guided choledochoduodenostomy (EUS-CDS) or EUS-guided antegrade stenting (EUS-AGS). Insertion of a metal stent is intended in both procedures in the first session. Primary end point is technical success. Secondary end points are clinical success, duration pf procedure, AEs graded by severity, length of hospital stay, re-intervention rate and survival within 6 months. The target case number is 212 patients (12 calculated dropouts included). DISCUSSION: This study might help to clarify whether PTBD is non-inferior to EUS-BD concerning technical success, and whether one of both interventions is superior in terms of efficacy and safety in one or more secondary endpoints. Randomization is not provided as both procedures are rarely used after failed endoscopic biliary drainage and study centers usually prefer one of both procedures that they can perform best. TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT03546049 (22.05.2018).

LiMAx Prior to Radioembolization for Hepatocellular Carcinoma as an Additional Tool for Patient Selection in Patients with Liver Cirrhosis.

BACKGROUND AND AIMS: Radioembolization (RE) has recently demonstrated a non-inferior survival outcome compared to systemic therapy for advanced hepatocellular carcinoma (HCC). Therefore, current guidelines recommend RE for patients with advanced HCC and preserved liver function who are unsuitable for transarterial chemoembolization (TACE) or systemic therapy. However, despite the excellent safety profile of RE, post-therapeutic hepatic decompensation remains a serious complication that is difficult to predicted by standard laboratory liver function parameters or imaging modalities. LiMAx® is a non-invasive test for liver function assessment, measuring the maximum metabolic capacity for 13C-Methacetin by the liver-specific enzyme CYP 450 1A2. Our study investigates the potential of LiMAx® for predicting post-interventional decompensation of liver function. PATIENTS AND METHODS: In total, 50 patients with HCC with or without liver cirrhosis and not amenable to TACE or systemic treatments were included in the study. For patients prospectively enrolled in our study, LiMAx® was carried out one day before RE (baseline) and 28 and 90 days after RE. Established liver function parameters were assessed at baseline, day 28, and day 90 after RE. The relationship between baseline LiMAx® and pre-and post-interventional liver function parameters, as well as the ability of LiMAx® to predict hepatic decompensation, were analyzed. RESULTS: We observed a strong association between baseline LiMAx® and bilirubin, albumin, ALBI grade, and MELD score. Patients presenting with Child-Pugh score B 28 days after RE or with a deterioration in Child-Pugh score by at least one point had a significantly lower baseline LiMAx® compared to those with Child-Pugh score A or with stable Child-Pugh score. The ability of LiMAx® to predict hepatic decompensation after RE was determined using ROC curve analysis and was compared to MELD score and ALBI grade. LiMAx® achieved a substantial AUC of 0.8117, comparable to MELD score and ALBI grade. CONCLUSION: Patients with lower LiMAx® values at baseline have a significantly increased risk for hepatic decompensation after RE, despite being categorized as Child-Pugh A. Therefore, LiMAx® can be used as an additional tool to identify patients at high risk of post-interventional hepatic failure.

Can a Polyp Detection and Characterization System Predict Complete Resection?

INTRODUCTION: Artificial Intelligence (AI) is one of the most evolving fields in endoscopy. We aimed to test if a system for polyp detection and polyp characterization can be used to predict complete endoscopic resection of colon adenomas. METHODS: We used the CAD-Eye AI system (Fujifilm Europe) in consecutive patients who received polypectomy using a cold snare. After resection, the submucosal space was flushed with water using an irrigation pump. Images were obtained using the CAD Eye system, and the characterization of the system was noted and afterward compared to histology of the removed specimen. RESULTS: In total, 17 polypectomies were observed, and in no case the AI was able to give information about resection status. First, the resection plane itself was classified as being adenomatous in all cases, while, second, all adenomas were resected completely, thus harboring no potential for overlying misinterpretations in the images. CONCLUSION: An AI system trained to characterize polyps in healthy surrounding colorectal mucosa cannot predict the state of resection after removal of the adenoma. This is explained by the training and programming. Endoscopists using AI from now on should learn about the basics of AI and the pitfalls in interpreting results from AI.

Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia.

BACKGROUND: Use of artificial intelligence may increase detection of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe) and reduce pathology costs by improving optical diagnosis (CADx). METHODS: A multicenter library of ≥ 200 000 images from 1572 polyps was used to train a combined CADe/CADx system. System testing was performed on two independent image sets (CADe: 446 with polyps, 234 without; CADx: 267) from 234 polyps, which were also evaluated by six endoscopists (three experts, three non-experts). RESULTS: CADe showed sensitivity, specificity, and accuracy of 92.9 %, 90.6 %, and 91.7 %, respectively. Experts showed significantly higher accuracy and specificity, and similar sensitivity, while non-experts + CADe showed comparable sensitivity but lower specificity and accuracy than CADe and experts. CADx showed sensitivity, specificity, and accuracy of 85.0 %, 79.4 %, and 83.6 %, respectively. Experts showed comparable performance, whereas non-experts + CADx showed comparable accuracy but lower specificity than CADx and experts. CONCLUSIONS: The high accuracy shown by CADe and CADx was similar to that of experts, supporting further evaluation in a clinical setting. When using CAD, non-experts achieved a similar performance to experts, with suboptimal specificity.

Cold versus hot polypectomy/endoscopic mucosal resection-A review of current evidence.

BACKGROUND: Colonoscopy with polypectomy substantially reduces the risk of colorectal cancer (CRC) but interval cancers still account for 9% of all CRCs, some of which are due to incomplete resection. AIM: The aim of this review is to compare the outcomes of cold and hot endoscopic resection and provide technical tips and tricks for optimizing cold snare polypectomy. RESULTS: Cold snare polypectomy (CSP) is the standard technique for small (≤10 mm) colorectal polyps. For large colonic polyps (>10 mm), hot resection techniques with use of electrocautery (polypectomy or endoscopic mucosal resection) were recommended until recently. However, the use of electrocoagulation brings serious adverse effects in up to 9% of the patients, such as delayed bleeding, post-polypectomy syndrome and perforation. In recent years, efforts have been made to improve the polypectomy with cold snare in order to avoid these adverse effects of electrocoagulation without compromising the efficacy of the resection. Several authors have recently shown that the complication rates of CSP of polyps >10 mm is close to zero and recurrence rates varies between 5-18%. Lower recurrence rates are found in serrated lesions (<8%).

Inflammatory microRNAs in gastric mucosa are modulated by Helicobacter pylori infection and proton-pump inhibitors but not by aspirin or NSAIDs.

Gastric carcinogenesis is associated with alterations of microRNAs (miRNAs) and reversal of these alterations may be a crucial element in cancer prevention. Here we evaluate the influence of H. pylori eradication, low-dose aspirin (LDA), non-steroidal anti-inflammatory drugs (NSAIDs) and proton-pump inhibitors (PPI) on modification of inflammatory mucosal miRNAs miR-155 and miR-223 in Helicobacter pylori-infected and non-infected subjects. The study was performed in two parts: 1) interventional study in 20 healthy subjects with and without H. pylori infection or following eradication (each n = 10) where LDA (100 mg) was given daily for 7 days; 2) prospective case-control observational study (n = 188). MiR-155 and miR-223 expression was strongly linked to H. pylori-infection and in short-term view showed a trend for reversal after eradication. Daily LDA as well as regular NSAIDs showed no influence on miRNAs expression both in healthy subjects and patients, while regular PPI intake was associated with lower miR-155 expression in antrum of patients with chronic gastritis independent of density of neutrophils and mononuclear infiltrate. In summary, PPI but not LDA or NSAIDs were associated with modification of inflammatory miRNAs miR-155 and miR-223 in an H. pylori dependent manner. The functional role of inflammatory miR-155 and miR-223 in understanding of H. pylori-related diseases needs further evaluation.

Biopsy Sampling in Upper Gastrointestinal Endoscopy: A Survey from 10 Tertiary Referral Centres Across Europe.

BACKGROUND: Guidelines give robust recommendations on which biopsies should be taken when there is endoscopic suggestion of gastric inflammation. Adherence to these guidelines often seems arbitrary. This study aimed to give an overview on current practice in tertiary referral centres across Europe. METHODS: Data were collected at 10 tertiary referral centres. Demographic data, the indication for each procedure, endoscopic findings, and the number and sampling site of biopsies were recorded. Findings were compared between centres, and factors influencing the decision to take biopsies were explored. RESULTS: Biopsies were taken in 56.6% of 9,425 procedures, with significant variation between centres (p < 0.001). Gastric biopsies were taken in 43.8% of all procedures. Sampling location varied with the procedure indication (p < 0.001) without consistent pattern across the centres. Fewer biopsies were taken in centres which routinely applied the updated Sydney classification for gastritis assessment (46.0%), compared to centres where this was done only upon request (75.3%, p < 0.001). This was the same for centres stratifying patients according to the OLGA system (51.8 vs. 73.0%, p < 0.001). More biopsies were taken in centres following the MAPS guidelines on stomach surveillance (68.1 vs. 37.1%, p < 0.001). Biopsy sampling was more likely in younger patients in 8 centres (p < 0.05), but this was not true for the whole cohort (p = 0.537). The percentage of procedures with biopsies correlated directly with additional costs charged in case of biopsies (r = 0.709, p = 0.022). CONCLUSION: Adherence to guideline recommendations for biopsy sampling at gastroscopy was inconsistent across the participating centres. Our data suggest that centre-specific policies are applied instead.

Radiation-induced damage in the upper gastrointestinal tract: clinical presentation, diagnostic tests and treatment options.

Radiation-induced damage of the upper gastrointestinal (GI) tract results from radiation of GI tumors or structures adjacent to the GI tract. Radiation-induced damages of the upper GI tract may be acute or delayed, and ranges from lack of appetite, mucosal inflammation (i.e. esophagitis, gastritis, duodenitis) to ulcers, which may be complicated by perforation, penetration, bleeding and stenosis. Radiation-related factors as well as individual patient predisposing factors may increase susceptibility to post-radiation damage. High quality evidence for the treatment of radiation-induced GI damage is scarce and the management is often extrapolated from studies on GI lesions of different etiology. Treatment depends on severity and localization of the radiation-induced damage, and ranges from supportive and dietary measures to endoscopic interventions or surgery. Modern radiation techniques may decrease the incidence and severity of the radiation-induced upper gastrointestinal disease.

Blue Light Imaging and Linked Color Imaging for the Characterization of Mucosal Changes in Chronic Gastritis: A Clinicians View and Brief Technical Report.

BACKGROUND: Blue light imaging (BLI) and linked color imaging (LCI) are new imaging modalities for the endoscopic evaluation of mucosal changes within the digestive tract. There is little experience with these modalities in the characterization of chronic gastritis (CG) intestinal metaplasia (IM) and atrophy in the stomach. AIMS AND METHODS: In a single-center observational pilot study, we correlated endoscopic findings with histology in selected patients. RESULTS: Findings from 29 patients were included in the analysis. Six patients had macroscopically normal gastric mucosa at endoscopy, and this was confirmed histologically in 5 of them. At endoscopy, 15 patients had the presence of IM in the antrum predicted, and this was confirmed histologically in 11 (73%). In the corpus, we predicted the presence of IM in 14 patients, and this was confirmed in 11 (78%) at histology. Eleven patients had the endoscopic suspicion of atrophy in antrum, which was confirmed in 9 patients (82%). In total, 14 patients had endoscopic suspicion of atrophy in corpus mucosa at endoscopy, but only 10 were confirmed in histology (71%). The concordance of endoscopic classification and histology was 93% for antrum and 88% for corpus. The positive predictive value and negative predictive value for IM were 0.74 and 0.83 and for atrophy 0.63 and 0.97, respectively. CONCLUSIONS: LCI and BLI are helpful in characterization of mucosal changes in CG. The ability to rule out premalignant conditions by endoscopy only reflects the clinical use and harbors significant clinical implications.

Combined Gastric and Colorectal Cancer Screening-A New Strategy.

BACKGROUND: Our aim was to evaluate the feasibility of a serological assessment of gastric cancer risk in patients undergoing colonoscopy in countries with low-to-moderate incidence rates. METHODS: Serum samples were prospectively collected from 453 patients (>50 years old) undergoing colonoscopies. Of these, 279 (61.6%) also underwent gastroscopy to correlate the results for serum pepsinogen I and II (sPG-I and sPG-II), sPG-I/II ratio, and anti-H. pylori antibodies with gastric histopathology findings (graded according to the updated Sydney classification and the Operative Link of Gastritis Assessment (OLGA) and the Operative Link for Gastric Intestinal Metaplasia assessment (OLGIM) systems). RESULTS: H. pylori was found in 85 patients (30.5%). Chronic atrophic gastritis was diagnosed in 89 (31.9%) patients. High-risk OLGA (III⁻IV) stages were present in 24 patients, and high-risk OLGIM stages were present in 14 patients. There was an inverse correlation of sPG-I with the degree of atrophy and intestinal metaplasia (IM), as well as with the respective OLGA (r = -0.425; p < 0.001) and OLGIM (r = -0.303; p < 0.001) stages. A pathological sPG-I result was associated with a relative risk (RR) of 12.2 (95% confidence interval: 6.29⁻23.54; p < 0.001) for gastric preneoplastic changes. CONCLUSIONS: The assessment of serum pepsinogen allows the identification of patients at increased risk of gastric cancer. A prevention strategy of combining a screening colonoscopy with a serological screening for preneoplastic gastric changes should be considered in the general population.

Expression of microRNAs in the ascites of patients with peritoneal carcinomatosis and peritonitis.

BACKGROUND: Peritoneal carcinomatosis (PCA) has a prognostic role in patients with gastrointestinal cancers. The differential diagnosis may be challenging due to the low sensitivity of cytology. Although microRNAs (miRNAs) have been a focus of various specimens and diseases, to the best of the authors' knowledge only limited knowledge exists regarding ascites. Herein, the authors systematically evaluated preanalytical factors and the potential of miRNAs as biomarkers of ascites. METHODS: The authors prospectively analyzed samples from patients with PCA, spontaneous bacterial peritonitis (SBP), and portal hypertension (no SBP/PCA). Various preanalytical factors such as extraction kits, sample storage, stability, and processing were systematically evaluated. MiRNA expression profiling using TaqMan Low Density Array and quantitative reverse transcriptase-polymerase chain reaction were used to evaluate miRNA expression. RESULTS: All selected miRNAs were found to be reliably detectable in ascites samples. Ascites miRNAs were well preserved from degradation with required short-term and long-term stability. MiRNA expression profiling in patients with PCA compared with those with no SBP/PCA revealed miR-21, miR-186, miR-222, and miR-483-5p to be upregulated and miR-26b to be downregulated. MiRNA expression validation analysis confirmed higher expression levels of miR-21 and miR-186 in patients with PCA compared with those with no SBP/PCA, whereas miR-223 was significantly upregulated in patients with SBP. A simple proportion score between miR-21 and miR-223 allowed the authors to discriminate between the patients with PCA and those with SBP with an area under the curve of 0.982 (95% confidence interval, 0.943-1.022). CONCLUSIONS: The data from the current study provide novel evidence of the differential expression of miRNAs in ascites from patients with PCA and SBP, which may offer an additional miRNA-based molecular approach for the differential diagnosis of PCA. Cancer Cytopathol 2018;126:353-63. © 2018 American Cancer Society.

Recurrent diffuse gastric bleeding as a leading symptom of gastrointestinal AL amyloidosis.

Amyloidosis is a rare disease (incidence about 0.8/100 000) characterized by extracellular tissue deposition of fibrils composed of low molecular weight subunits of a variety of serum proteins. Clinical manifestations are largely determined by the type of precursor protein, the tissue distribution and the amount of amyloid deposition. Gastrointestinal (GI) manifestations of amyloidosis are even more uncommon (3 % of all amyloidosis patients). Symptoms of GI amyloidosis are nonspecific, heterogeneous, and include weight loss, GI bleeding, heartburn, early satiety, diarrhea and abdominal pain. The histopathological examination of biopsy specimens from the GI tract leads to the diagnosis.Herein we report the case of a 63-year-old woman with recurrent diffuse gastric bleeding. Endoscopic biopsies revealed distinct amyloid deposits in the mucosa of the stomach. Further histochemical assessment confirmed systemic light chain (AL) amyloidosis with clinically predominant gastrointestinal manifestation. An induction therapy with bortezomib and dexamethasone was initiated.Our report illustrates the importance of the multidisciplinary approach for diagnosis and management of AL amyloidosis. Current treatment of systemic AL amyloidosis is based on cytostatic targeting of immunoglobulin producing plasma cells. Therapeutic options are limited and highly toxic, making the development of novel treatment approaches an urgent need.

Influence of laboratory-related and endoscopy-related factors on the assessment of serum pepsinogens and gastrin-17.

BACKGROUND AND AIM: Serum pepsinogen I (PGI) and pepsinogen II (PGII) are noninvasive parameters in the detection of atrophic gastritis. The diagnostic add-on value of serum gastrin-17 (G-17) remains uncertain. The aim of this study was to assess the stability of these serum parameters over time and to evaluate the influence of clinical factors, such as upper gastrointestinal (GI) endoscopy and bowel cleansing, on serum PGI, PGII, and G-17 assessment. PATIENTS AND METHODS: A prospective study was carried out in healthy individuals and patients. For the stability analyses, the plasma and serum samples from 23 individuals were processed at different time points with and without the addition of a stabilizer. Ten patients were included to evaluate the influence of upper GI endoscopy and 18 patients to evaluate the effect of bowel cleansing before colonoscopy. RESULTS: PGI, PGII, and G-17 levels were not statistically different in the serum and plasma. PGI and PGII serum levels were stable over time. G-17 is associated with time-dependent degradation (P=0.0001). The addition of the G-17 stabilizer showed no improvement in stability. Upper GI endoscopy and bowel preparation before colonoscopy were associated with minimal variations in PGI and PGII, whereas G-17 showed patient-specific alterations. CONCLUSION: PGI and PGII serum levels are stable over time. However, G-17 stability is strongly dependent on the time of processing and storage; therefore, samples for G-17 analysis need to be processed no later than 6 h after blood collection. Upper GI endoscopy and colonoscopy preparation lead to minimal nonsignificant changes in basal PGI, PGII, and G-17 levels.

Oxyntic gastric atrophy in Helicobacter pylori gastritis is distinct from autoimmune gastritis.

AIM: To assess characteristics of oxyntic gastric atrophy (OGA) in autoimmune gastritis (AIG) compared with OGA as a consequence of Helicobacter pylori infection. METHODS: Patients undergoing oesophagogastroduodenoscopy from July 2011 to October 2014 were prospectively included (N=452). Gastric biopsies were obtained for histology and H. pylori testing. Serum gastrin-17 (G17), pepsinogen (PG) I, PGII and antibodies against H. pylori and cytotoxin-associated gene A protein were determined in all patients. Antibodies against parietal cells and intrinsic factor were determined in patients with advanced (moderate to severe) OGA. Areas under the receiver operating characteristic curves (AUCs) were calculated for serum biomarkers and compared with histology. RESULTS: Overall, 34 patients (8.9%) had advanced OGA by histology (22 women, age 61±15 years). Current or past H. pylori infection and AIG were present in 14/34 and 22/34 patients, respectively. H. pylori-negative AIG patients (N=18) were more likely to have another autoimmune disease (OR 6.3; 95% CI 1.3 to 29.8), severe corpus atrophy (OR 10.1; 95% CI 1.9 to 54.1) and corpus intestinal metaplasia (OR 26.9; 95% CI 5.3 to 136.5) compared with H. pylori-positive patients with advanced OGA. Antrum atrophy was present in 39% of H. pylori-negative AIG patients. The diagnostic performance of G17, PG I and PGI/II was excellent for AIG patients (AUC=0.83, 0.95 and 0.97, respectively), but limited for H. pylori-positive patients with advanced OGA (AUC=0.62, 0.75 and 0.67, respectively). CONCLUSIONS: H. pylori-negative AIG has a distinct clinical, morphological and serological phenotype compared with advanced OGA in H. pylori gastritis.