WP6.14 - Automated analysis of operative video in surgical training: Scoping review

Abstract Aims There is an increasing availability of operative video for use in surgical training. Emerging technologies can now assess video footage and automatically generate metrics that could be harnessed to improve the assessment of operative performance. This scoping review explores the current application of automated video analytics in surgical training. Methods PubMed, Scopus, Web of Science and the Cochrane database were searched to identify studies which applied automated video analytics to trainee-performed operations. Search terms included ‘trainee’, ‘video analytics’ and ‘education’. Two reviewers independently screened and extracted data on the methods of analysis, metrics generated and application to training. The Preferred Reporting Items for Systematic Reviews and Meta-analyses extension for Scoping Review (PRISMA-ScR) guidelines were followed. Results Thirteen studies were identified. Computer vision tracking was the most common method of video analysis. Metrics were generated for processes (e.g. movement of instruments) and outcomes (e.g. intraoperative phase duration). Two studies generated metrics to assess critical safety elements (e.g. critical view of safety in laparoscopic cholecystectomy). Automated metrics were able to differentiate between different skill levels (e.g. consultant vs. trainee) and correlated with traditional methods of assessment. There was a lack of longitudinal application to training and only one qualitative study reported the experience of trainees using automated video analytics. Conclusion Automated video analytics is an emerging field which provides an objective assessment of operative performance. Gathering evidence to demonstrate the impact of long-term use on training outcomes is a priority for future research.