Video-based self-assessment enhances laparoscopic skills on a virtual reality simulator: a randomized controlled trial

Self-assessment, and not continuous training, improves basic open suturing skills

BACKGROUND

To develop and maintain suturing skills, clinical exposure is important. When clinical exposure cannot be guaranteed, an adequate training schedule for suturing skills is required. This study evaluates the effect of continuous training, 'reflection before practice' and self-assessment on basic open suturing skills.

METHODS

Medical students performed four basic suturing tasks on a simulation set up before ('pre-test') and after their surgical rotation ('after-test'). Participants were divided in three groups; the 'clinical exposure group' (n = 44) had clinical exposure during their rotation only, the 'continuous training group' (n = 16) completed a suturing interval training during their rotation and the 'self-assessment group' (n = 16) also completed a suturing interval training, but with the use of reflection before practice and self-assessment. Parameters measured by a tracking system during the suturing tasks and a calculated 'composite score' were compared between groups and test-moments.

RESULTS

A significantly better composite score was found at the after-test compared to the pre-test for all groups for all basic suturing tasks (0.001 ≤ p ≤ 0.049). The self-assessment group scored better at the pre-test than the other two groups for all tasks, except for 'knot tying by hand' (0.004 ≤ p ≤ 0.063). However, this group did not score better at the after-test for all tasks, compared to the other two groups. This resulted in a smaller delta of time ('transcutaneous suture', p = 0.013), distance ('Donati suture' and 'intracutaneous suture', 0.005 ≤ p ≤ 0.009) or composite score (all tasks, except for knot tying by hand, 0.007 ≤ p ≤ 0.061) in the self-assessment group.

CONCLUSION

Reflection before practice and self-assessment during continuous training of basic open suturing tasks, may improve surgical skills at the start of the learning curve.

Exploring the use of metacognitive monitoring cues following a diagram completion intervention

Studying texts constitutes a significant part of student learning in health professions education. Key to learning from text is the ability to effectively monitor one's own cognitive performance and take appropriate regulatory steps for improvement. Inferential cues generated during a learning experience typically guide this monitoring process. It has been shown that interventions to assist learners in using comprehension cues improve their monitoring accuracy. One such intervention is having learners to complete a diagram. Little is known, however, about how learners use cues to shape their monitoring judgments. In addition, previous research has not examined the difference in cue use between categories of learners, such as good and poor monitors. This study explored the types and patterns of cues used by participants after being subjected to a diagram completion task prior to their prediction of performance (PoP). Participants' thought processes were studied by means of a think-aloud method during diagram completion and the subsequent PoP. Results suggest that relying on comprehension-specific cues may lead to a better PoP. Poor monitors relied on multiple cue types and failed to use available cues appropriately. They gave more incorrect responses and made commission errors in the diagram, which likely led to their overconfidence. Good monitors, on the other hand, utilized cues that are predictive of learning from the diagram completion task and seemed to have relied on comprehension cues for their PoP. However, they tended to be cautious in their judgement, which probably made them underestimate themselves. These observations contribute to the current understanding of the use and effectiveness of diagram completion as a cue-prompt intervention and provide direction for future research in enhancing monitoring accuracy.

The Evidence Basis for Learning Theory and Technology in Surgical Skills Training

Orthopaedic trainees face a complex and challenging training environment that is currently becoming more competency driven. Associated with these changes are an increasing introduction and use of a variety of technologically driven surgical training augments. Although these new learning resources can positively transform the educational environment, they must be used appropriately by both learners and educators. To aid in this, we review learning theories because they apply to surgical skills training and highlight recent surgical training evidence that demonstrates how technology use can be optimized to promote surgical learning, with an emphasis on procedural learning theory and cognitive load theory. Specifically, we review the evidence demonstrating the importance of targeting technology to a learner's experience level and methods to optimize cognitive load by managing intrinsic load, minimizing extraneous load, and maximizing germane load.

Specific steps in the operation determine resident speed: Experience with a live tissue simulation model of laparoscopic nephrectomy

INTRODUCTION

It is increasingly important to identify and eliminate inefficiencies in resident education. We hypothesize that slower performance of specific operative steps in laparoscopic nephrectomy accounts for much of the slower operative speed observed in junior residents vs. their senior colleagues. Therefore, we sought to evaluate the by-step time-differential between experienced senior residents and their junior colleagues in a live-tissue simulation.

MATERIALS AND METHODS

Residents participated in our swine model surgical simulation of laparoscopic radical and partial nephrectomy (LRNx and LPNx). PGY5 and 6 residents were considered senior; junior residents were PGY3 and 4. We defined discrete surgical steps. Residents' post-graduate training levels were tracked and time-to-completion of each operative step was recorded.

RESULTS

Seven live-tissue simulations sessions took place, with 12 residents conducting 22 operations (12 LRNx, 10 LPNx). On average, each resident operated in 2 simulation sessions (range 1-4). The average time required by senior residents for LPNx was 152 min; junior residents required 173 min (p = 0.35). When considering the operative steps, juniors required nearly twice as much time to achieve hilar control (42 min vs. 23 min, p = 0.03). Significant differences in performance time were not seen in the other steps.

DISCUSSION

The performance differential between senior and junior residents conducting nephrectomies was most evident during hilar dissection. Our study suggests that specific efforts should be focused on teaching junior residents the skills required for this step early in their training.

Improving robotic skills by video review

Background Since the transition of surgical robot systems into the medical field, physicians have had to develop new dexterity skills. The ideal learning environment for robotic surgery has yet to be discovered. Virtual-reality (VR) simulation is a possible safe and economic method. In VR-simulator training human feedback is hardly used, an alternative may be found in video revision. The purpose of this study is to investigate whether adding video review to VR-simulation-based training in novice physicians improves their ability to complete a complex robot task. In addition, the secondary goal is to investigate whether the skills learned on the robotic simulator can be transferred to a real robotic system. Methods 40 participants, medical students and, medical-PhD candidates, from one university hospital, were included. Baseline dexterity skills were measured through completion of a vesico-urethral anastomosis on a VR-robot simulator and the DaVinci robot. Participants were randomized into a video and control group. The video group practiced skills on the robot simulator with intermediate video revision, whereas the control group had intermediate pause instead. Post-intervention dexterity skills were measured using the same exercises as the baseline tests. Results No significant differences were found in baseline performance. Post-intervention results on the VR-simulator show that the video group commits significantly fewer injuries to the urethra and sutures at a greater optimal depth. The control group was significantly faster, had less camera travel, and had their instruments less out of view. On the DaVinci robot, participants in both groups performed significantly faster and had better GEARS-score after the training sessions on the VR simulator. Conclusions Video revision significantly improves the quality of robotic skills in novice surgeons on the VR-simulator, though at the expense of time. Furthermore, both groups demonstrated enhanced skills on the DaVinci robot after training sessions, which advocates the transferability of skill.