AI in Surgical Curriculum Design and Unintended Outcomes for Technical Competencies in Simulation Training

Importance

To better elucidate the role of artificial intelligence (AI) in surgical skills training requires investigations in the potential existence of a hidden curriculum.

Objective

To assess the pedagogical value of AI-selected technical competencies and their extended effects in surgical simulation training.

Design, Setting, and Participants

This cohort study was a follow-up of a randomized clinical trial conducted at the Neurosurgical Simulation and Artificial Intelligence Learning Centre at the Montreal Neurological Institute, McGill University, Montreal, Canada. Surgical performance metrics of medical students exposed to an AI-enhanced training curriculum were compared with a control group of participants who received no feedback and with expert benchmarks. Cross-sectional data were collected from January to April 2021 from medical students and from March 2015 to May 2016 from experts. This follow-up secondary analysis was conducted from June to September 2022. Participants included medical students (undergraduate year 0-2) in the intervention cohorts and neurosurgeons to establish expertise benchmarks.

Exposure

Performance assessment and personalized feedback by an intelligent tutor on 4 AI-selected learning objectives during simulation training.

Main Outcomes and Measures

Outcomes of interest were unintended performance outcomes, measured by significant within-participant difference from baseline in 270 performance metrics in the intervention cohort that was not observed in the control cohort.

Results

A total of 46 medical students (median [range] age, 22 [18-27] years; 27 [59%] women) and 14 surgeons (median [range] age, 45 [35-59] years; 14 [100%] men) were included in this study, and no participant was lost to follow-up. Feedback on 4 AI-selected technical competencies was associated with additional performance change in 32 metrics over the entire procedure and 20 metrics during tumor removal that was not observed in the control group. Participants exposed to the AI-enhanced curriculum demonstrated significant improvement in safety metrics, such as reducing the rate of healthy tissue removal (mean difference, -7.05 × 10-5 [95% CI, -1.09 × 10-4 to -3.14 × 10-5] mm3 per 20 ms; P < .001) and maintaining a focused bimanual control of the operative field (mean difference in maximum instrument divergence, -4.99 [95% CI, -8.48 to -1.49] mm, P = .006) compared with the control group. However, negative unintended effects were also observed. These included a significantly lower velocity and acceleration in the dominant hand (velocity: mean difference, -0.13 [95% CI, -0.17 to -0.09] mm per 20 ms; P < .001; acceleration: mean difference, -2.25 × 10-2 [95% CI, -3.20 × 10-2 to -1.31 × 10-2] mm per 20 ms2; P < .001) and a significant reduction in the rate of tumor removal (mean difference, -4.85 × 10-5 [95% CI, -7.22 × 10-5 to -2.48 × 10-5] mm3 per 20 ms; P < .001) compared with control. These unintended outcomes diverged students' movement and efficiency performance metrics away from the expertise benchmarks.

Conclusions and Relevance

In this cohort study of medical students, an AI-enhanced curriculum for bimanual surgical skills resulted in unintended changes that improved performance in safety but negatively affected some efficiency metrics. Incorporating AI in course design requires ongoing assessment to maintain transparency and foster evidence-based learning objectives.

Face and Construct Validity of a Novel Virtual Reality-Based Bimanual Laparoscopic Force-Skills Trainer With Haptics Feedback

BACKGROUND

The purpose of this study was to examine the face and construct validity of a custom-developed bimanual laparoscopic force-skills trainer with haptics feedback. The study also examined the effect of handedness on fundamental and complex tasks.

METHODS

Residents (n = 25) and surgeons (n = 25) performed virtual reality-based bimanual fundamental and complex tasks. Tool-tissue reaction forces were summed, recorded, and analysed. Seven different force-based measures and a 1-time measure were used as metrics. Subsequently, participants filled out face validity and demographic questionnaires.

RESULTS

Residents and surgeons were positive on the design, workspace, and usefulness of the simulator. Construct validity results showed significant differences between residents and experts during the execution of fundamental and complex tasks. In both tasks, residents applied large forces with higher coefficient of variation and force jerks (P < .001). Experts, with their dominant hand, applied lower forces in complex tasks and higher forces in fundamental tasks (P < .001). The coefficients of force variation (CoV) of residents and experts were higher in complex tasks (P < .001). Strong correlations were observed between CoV and task time for fundamental (r = 0.70) and complex tasks (r = 0.85). Range of smoothness of force was higher for the non-dominant hand in both fundamental and complex tasks.

CONCLUSIONS

The simulator was able to differentiate the force-skills of residents and surgeons, and objectively evaluate the effects of handedness on laparoscopic force-skills. Competency-based laparoscopic skills assessment curriculum should be updated to meet the requirements of bimanual force-based training.

Objective Assessment of Laparoscopic Force and Psychomotor Skills in a Novel Virtual Reality-Based Haptic Simulator

BACKGROUND

Most of the commercially available virtual reality-based laparoscopic simulators do not effectively evaluate combined psychomotor and force-based laparoscopic skills. Consequently, the lack of training on these critical skills leads to intraoperative errors.

OBJECTIVES

To assess the effectiveness of the novel virtual reality-based simulator, this study analyzed the combined psychomotor (i.e., motion or movement) and force skills of residents and expert surgeons. The study also examined the effectiveness of real-time visual force feedback and tool motion during training.

DESIGN

Bimanual fundamental (i.e., probing, pulling, sweeping, grasping, and twisting) and complex tasks (i.e., tissue dissection) were evaluated. In both tasks, visual feedback on applied force and tool motion were provided. The skills of the participants while performing the early tasks were assessed with and without visual feedback. Participants performed 5 repetitions of fundamental and complex tasks. Reaction force and instrument acceleration were used as metrics.

SETTING

Surgical Gastroenterology, Government Stanley Medical College and Hospital; Institute of Surgical Gastroenterology, Madras Medical College and Rajiv Gandhi Government General Hospital.

PARTICIPANTS

Residents (N = 25; postgraduates and surgeons with <2 years of laparoscopic surgery) and expert surgeons (N = 25; surgeons with >4 and ≤10 years of laparoscopic surgery).

RESULTS

Residents applied large forces compared with expert surgeons and performed abrupt tool movements (p < 0.001). However, visual + haptic feedback improved the performance of residents (p < 0.001). In complex tasks, visual + haptic feedback did not influence the applied force of expert surgeons, but influenced their tool motion (p < 0.001). Furthermore, in complex tissue sweeping task, expert surgeons applied more force, but were within the tissue damage limits. In both groups, exertion of large forces and abrupt tool motion were observed during grasping, probing or pulling, and tissue sweeping maneuvers (p < 0.001).

CONCLUSIONS

Modern day curriculum-based training should evaluate the skills of residents with robust force and psychomotor-based exercises for proficient laparoscopy. Visual feedback on force and motion during training has the potential to enhance the learning curve of residents.