Olympus reviewed the following literature titled "artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study".The aim of this study was to develop and validate a convolutional neural networks (cnn)-based algorithm for the automatic detection and differentiation of malignant biliary strictures and benign biliary lesions in digital single-operator cholangioscopy (dsoc) images.A total of 85 patients underwent dsoc (40 (47%) patients had diagnosed with benign disease whereas 45 (53%) were ultimately diagnosed with a malignant biliary stricture).Overall, the estimated model accuracy was 94.9% (95% ci, 92.4%-97.4%).The mean sensitivity and specificity of the model were 94.7% (95% ci, 90.5%-98.9%) and 92.1% (95% ci, 89.4% ¿ 94.6%).The algorithm had a mean auc of 0.988 (95% ci, 0.982-0.994).The sensitivity, specificity, ppv and npv for the detection and differentiation of malignant strictures from benign biliary disease were, respectively, 94.8%, 99.1%, 99.8%, and 80.8%.The introduction of artificial intelligence algorithms to dsoc systems may significantly increase its diagnostic yield for malignant strictures.Type of adverse events/number of patients: [malignant strictures]; cholangitis - 4 patients, pancreatitis - 9 patients, perforation - 1 patient, bacteremia - 1 patient.[benign strictures]: cholangitis - 3 patients, pancreatitis - 5 patients.This literature article requires 2 reports.The related patient identifiers are as follows: (b)(6)(tjf-160vf).(b)(6)(tjf-q180v).This medwatch report is for patient identifier (b)(6).There is no report of any olympus device malfunction in any procedure described in this study.
|
This report is being supplemented to provide additional information based on the legal manufacturer's final investigation and to provide follow up received from the customer.The device history record was unable to be reviewed for this device since the serial and/or lot number was not provided.However, olympus only releases products to market that meet all manufacturing specifications and final product release criteria.Based on the results of the investigation, the relationship between the device and the adverse events cannot be confirmed.There was no complaint reported on the subject device.There is no evidence of an olympus device malfunction.Therefore, the root cause cannot be determined.Olympus will continue to monitor field performance for this device.
|