Key result
Machine learning algorithm objectively evaluates trainee skill in lumbar epidural anesthesia using a haptic simulator.
Why the study?
Existing simulators lack the realism needed to efficiently learn lumbar epidural anesthesia, leaving training largely to be performed directly on patients.
The study introduces a machine learning-based skill assessment algorithm for a haptic epidural anesthesia simulator to improve training safety and efficiency.
May support objective feedback in epidural simulator training; hypothesis-generating for clinical validation and adoption.
Currently, the training in the lumbar epidural anesthesia procedure, a very common procedure, is mainly performed on patients under the supervision of experts. The reason for this situation is that the simulators that exist on the market are not realistic enough to efficiently learn this particularly haptic-sense-based gesture. To avoid this ethical issue and provide an efficient, repeatable, and affordable way of safely learning this gesture, the Ampère laboratory designed PeriSIM: a haptic training computer-based simulator. In this article, the trainees' skill assessment is tackled. This work presents various machine learning approaches to the evaluation of trainees and introduces a complete skill assessment algorithm to use in conjunction with the PeriSIM simulator. This work also aims to determine the important variables of an lumbar epidural anesthesia procedure for objective assessment purpose.
No takes yet. Share an insight, caveat, or question.
Sénac et al. (2020) studied Lumbar epidural anesthesia training. PeriSIM simulator and machine learning skill assessment algorithm was evaluated on Skill assessment of trainees. A machine learning-based skill assessment algorithm was developed for use with the PeriSIM haptic simulator to objectively evaluate trainees performing lumbar epidural anesthesia.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: