(ANSA) – PISA, 05 JUL – A simulator based on virtual reality to analyze and facilitate, thanks to artificial intelligence, the training of future surgeons who will operate with the robot. It is the heart of an international study, the first of its kind, carried out at the University of Pisa and which involved a research group led by the engineer Andrea Moglia of the Department of Translational Research and New Technologies in Medicine and Surgery, in collaboration with Professor Sir Alfred Cuschieri of the University of Dundee (United Kingdom).
The study explains a note, which required a group of medical students to perform specific exercises in the simulator for robotic surgery until the required level of competence was reached. Subsequently, various artificial intelligence models were developed via software to predict the time and number of attempts of each exercise in which participants would complete their training. Using a particular configuration (called ensemble learning) in which multiple neural network models were aggregated, it was possible to obtain a higher accuracy (up to 95% in some cases) than any other machine learning model. The results of the study, in which the general surgery group of Professor Luca Morelli also participated, were published in Surgical Endoscopy, one of the most authoritative journals in surgery. The study conducted at the Pisa University represents the highest international case history in the sector and is based on Andrea Moglia’s experience in simulation in robotic surgery, which began in 2009 at the EndoCas center, directed by Professor Mauro Ferrari, and who saw it to be the first in Italy to use virtual simulators for the robotic surgery system called da Vinci. (HANDLE).