Automatic Assessment of Procedural Skills Based on the Surgical Workflow Analysis Derived from Speech and Video
- PMID: 36550959
- PMCID: PMC9774809
- DOI: 10.3390/bioengineering9120753
Automatic Assessment of Procedural Skills Based on the Surgical Workflow Analysis Derived from Speech and Video
Abstract
Automatic surgical workflow analysis (SWA) plays an important role in the modelling of surgical processes. Current automatic approaches for SWA use videos (with accuracies varying from 0.8 and 0.9), but they do not incorporate speech (inherently linked to the ongoing cognitive process). The approach followed in this study uses both video and speech to classify the phases of laparoscopic cholecystectomy, based on neural networks and machine learning. The automatic application implemented in this study uses this information to calculate the total time spent in surgery, the time spent in each phase, the number of occurrences, the minimal, maximal and average time whenever there is more than one occurrence, the timeline of the surgery and the transition probability between phases. This information can be used as an assessment method for surgical procedural skills.
Keywords: artificial intelligence; procedural skills; skills’ assessment; surgical training.
Conflict of interest statement
The authors declare no conflict of interest.
Figures









References
-
- Verdura J., Maureen E., Ek S., Callery M.P. Systems, Methods, and Instruments for Minimally Invasive Surgery. 6,159,200. U.S. Patent. 2000 December 12;
Grants and funding
LinkOut - more resources
Full Text Sources