Search

Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases. [ABSTRACT FROM AUTHOR]

Conventional endoscopic mucosal resection (CEMR) with submucosal injection is the current standard for the resection of large, nonmalignant colorectal polyps. We investigated whether underwater endoscopic mucosal resection (UEMR) is superior to CEMR for large (20–40mm) sessile or flat colorectal polyps. In this prospective randomized controlled study, patients with sessile or flat colorectal polyps between 20 and 40 mm in size were randomly assigned to UEMR or CEMR. The primary outcome was the recurrence rate after 6 months. Secondary outcomes included en bloc and R0 resection rates, number of resected pieces, procedure time, and adverse events. En bloc resection rates were 33.3% in the UEMR group and 18.4% in the CEMR group (P =.045); R0 resection rates were 32.1% and 15.8% for UEMR vs CEMR, respectively (P =.025). UEMR was performed with significantly fewer pieces compared to CEMR (2 pieces: 45.5% UEMR vs 17.7% CEMR; P =.001). The overall recurrence rate did not differ between both groups (P =.253); however, subgroup analysis showed a significant difference in favor of UEMR for lesions of >30 mm to ≤40 mm in size (P =.031). The resection time was significantly shorter in the UEMR group (8 vs 14 minutes; P <.001). Adverse events did not differ between both groups (P =.611). UEMR is superior to CEMR regarding en bloc resection, R0 resection, and procedure time for large colorectal lesions and shows significantly lower recurrence rates for lesions >30 mm to ≤40 mm in size. UEMR should be considered for the endoscopic resection of large colorectal polyps. [Display omitted] Underwater endoscopic mucosal resection was compared to conventional endoscopic mucosal resection for the resection of large colorectal polyps (20–40 mm). Underwater endoscopic mucosal resection was faster and more effective without increasing the risk of complications. [ABSTRACT FROM AUTHOR]

Background Combination chemotherapy has shown benefit in the treatment of biliary cancer and further improvements might be achieved by the addition of a biological agent. We report here the effect of chemotherapy with the monoclonal EGFR antibody panitumumab as therapy for KRAS wild-type biliary cancer. Patients and methods Patients with advanced biliary tract cancer were randomised (2:1) to receive cisplatin 25 mg/m 2 and gemcitabine 1000 mg/m 2 on day 1 and day 8/q3w with (arm A) or without panitumumab (arm B; 9 mg/kg BW, i.v q3w). The primary end-point was the evaluation of progression-free survival (PFS) at 6 months. Secondary end-points included objective response rate (ORR), overall survival (OS), and toxicity. In addition, a post hoc assessment of genetic alterations was performed. Finally, we performed a meta-analysis of trials with chemotherapy with and without EGFR antibodies. Results Sixty-two patients were randomised in arm A and 28 patients in arm B. Patients received 7 treatment cycles in median (1–35) with a median treatment duration of 4.7 months (141 days, 8–765). PFS rate at 6 months was 54% in patients treated with cisplatin/gemcitabine and panitumumab but was 73% in patients treated with cisplatin/gemcitabine without antibody, respectively. Secondary end-points were an ORR of 45% in treatment arm A compared with 39% receiving treatment B and a median OS of 12.8 months (arm A) and of 20.1 months (arm B), respectively. In contrast to the p53-status, genetic alterations in IDH1/2 were linked to a high response after chemotherapy and prolonged survival. In accordance with our results, the meta-analysis of 12 trials did not reveal a survival advantage for patients treated with EGFR antibodies compared with chemotherapy alone. Conclusions Panitumumab in combination with chemotherapy does not improve ORR, PFS and OS in patients with KRAS wild-type, advanced biliary cancer. Genetic profiling should be included in CCA trials to identify and validate predictive and prognostic biomarkers. Clinical Trials Number The trial was registered with NCT01320254 . [ABSTRACT FROM AUTHOR]

Introduction Human epidermal growth factor receptor 2 (HER2) amplification is present in a subgroup of gastroo-esophageal cancers (GCs). HER2 inhibition with trastuzumab has shown to improve outcomes in advanced disease. Lapatinib ditosylate (LAP), a dual anti-epidermal growth factor receptor (EGFR) and anti-HER2 tyrosine kinase inhibitor with preclinical activity against GC, has been approved in HER2-positive breast cancer. We aimed to study the activity of LAP in HER2-amplified GC. Materials and methods Patients (pts) with HER2-positive (gene amplification or increased copy numbers based on predefined criteria) advanced GC were randomly allocated 1:1 to receive LAP 1250 mg per day 1–21 plus capecitabine (CAP) 2000 mg/m 2 on days 1–14 of a 21-day cycle or LAP 1500 mg monotherapy day 1–21 after having failed on a platinum-based first-line therapy. HER2 status was assessed centrally. The primary end-point was the objective response rate (ORR) as assessed by the investigator using Response Evaluation Criteria in Solid Tumors (RECIST, version 1.1). We aimed to include 38 pts per arm to show an interesting response rate of ⩾20% in either of the two arms. Results 37 pts were enrolled (18 to LAP + CAP, 19 to LAP). Pts had received a median of three prior treatment lines. 12 pts in the LAP + CAP group (67%) and 12 pts in the LAP group (63%) had received prior trastuzumab. Only two pts (11.1%; 95% confidence interval (CI): 1.37–34.7), both in the LAP + CAP arm, achieved an objective response. The study was closed prematurely for futility. Median time to progression was 42 (95% CI: 38–61) days in the LAP group and 83 (95% CI: 42–86) days in the LAP + CAP group. Other secondary efficacy end-points (progression-free and overall survival) were comparable in the two treatment groups. Rates of diarrhoea were higher with LAP + CAP (61%; 95% CI: 35–83) compared to 26% (95% CI 9–51) with LAP mono, whereas other adverse events were mostly similar between the groups (18 [100%] versus 17 [90%]). Discussion Lapatinib showed insufficient activity in HER2-amplified pretreated advanced GC. The safety profile of LAP or LAP + CAP was as expected with some more toxicity in the combination arm. (ClinicalTrials.gov Identifier, NCT01145404). [ABSTRACT FROM AUTHOR]