Towards an Objective Tool for Evaluating the Surgical Skill

In this paper we present a system for the evaluation of the skill of a physician or physician student by means of the analysis of the movements of the hand. By comparing these movements to the ones of a set of subjects known to be skilled, we could tell if they are correct. We consider the execution of a typical surgical task: the suture. For the data acquisition we used the HiTEg sensory glove, then, we extract a set of features from data analysis and classify it by means of different kind of classifiers. We compared results from an RBF neural network and a Bayesian classifier. The system has been tested on a set of 18 subjects. We found that accuracy depends on the feature set that is used, and it can reach 94 % when we consider a set of 20 features: 9 of them are taken from data of bending sensor, 10 from accelerometers and gyroscopes, and one feature is the length of the gesture.