الملخص
Objective:To develop a novel, flexible, dual-arm, master-slave digestive endoscopic minimally invasive surgical robot system named dual-arm robotic endoscopic assistant for minimally invasive surgery (DREAMS) and to evaluate its feasibility for endoscopic submucosal dissection (ESD) by using ex vivo porcine stomachs.Methods:A novel endoscopic robot (DREAMS) system was developed which was composed of a flexible two-channel endoscope, two flexible robotic manipulators, a master controller, a robotic arm, and a control system. A total of 10 artificial round-like lesions with diameters ranging from 15 to 25 mm were created (5 in gastric antrum and 5 in gastric body) by using fresh peeled stomach of healthy pigs as the model. Submucosal dissection was performed with the assistance of the DREAMS system by two operators. The main outcome was submucosal dissection speed, and the secondary outcomes included muscular injury rate, perforation rate, and grasping efficiency of the robot.Results:All 10 lesions were successfully dissected en bloc by using the DREAMS system. The diameter of the artificial lesions was 22.34±2.39 mm, dissection time was 15.00±8.90 min, submucosal dissection speed was 141.79±79.12 mm 2/min, and the number of tractions required by each ESD was 4.2 times. Muscular injury occurred in 4/10 cases of ESD. No perforation occurred. Conclusion:The initial animal experiment shows the DREAMS system is safe and effective.
الملخص
Acute respiratory distress syndrome (ARDS) is a clinical syndrome defined by acute onset of hypoxemia and bilateral pulmonary opacities not fully explained by cardiac failure or volume overload. At present, there is no specific drug treatment for ARDS, and the mortality rate is high. The reason may be that ARDS has rapid onset, rapid progression, complex etiology, and great heterogeneity of clinical manifestations and treatment. Compared with traditional data analysis, machine learning algorithms can automatically analyze and obtain rules from complex data and interpret them to assist clinical decision making. This review aims to provide a brief overview of the machine learning progression in ARDS clinical phenotype, onset prediction, prognosis stratification, and interpretable machine learning in recent years, in order to provide reference for clinical.