Clinical study of skill assessment based on time sequential measurement changes

Abstract

AbstractEndoscopic sinus surgery is a common procedure for chronic sinusitis; however, complications have been reported in some cases. Improving surgical outcomes requires an improvement in a surgeon’s skills. In this study, we used surgical workflow analysis to automatically extract “errors,” indicating whether there was a large difference in the comparative evaluation of procedures performed by experts and residents. First, we quantified surgical features using surgical log data, which contained surgical instrument information (e.g., tip position) and time stamp. Second, we created a surgical process model (SPM), which represents the temporal transition of the surgical features. Finally, we identified technical issues by creating an expert standard SPM and comparing it to the novice SPM. We verified the performance of our methods by using the clinical data of 39 patients. In total, 303 portions were detected as an error, and they were classified into six categories. Three risky operations were overlooked, and there were 11 overdetected errors. We noted that most errors detected by our method involved dangers. The implementation of our methods of automatic improvement points detection may be advantageous. Our methods may help reduce the time for reviewing and improving the surgical technique efficiently.