Dataset and Analysis of Long-Term Skill Acquisition in Robot-Assisted Minimally Invasive Surgery

TL;DR

This study investigates long-term skill acquisition in robot-assisted minimally invasive surgery by tracking surgical residents over six months with three training sessions around a 26-hour hospital shift. Using the da Vinci Research Kit and three dry-lab tasks, the authors collected a multimodal dataset consisting of synchronized kinematic data, video, and tissue-scan information, plus fatigue/activity measures, to analyze retention, forgetting, and potential fatigue effects. Their exploratory analysis with two repeated-measures ANOVA models shows learning across six shifts and nuanced between-shift dynamics that vary by task and metric, suggesting that fatigue and interval spacing influence different aspects of optimization. The dataset and initial findings aim to advance surgical robotics training, AI applications in skill assessment, and motor-learning theory, offering a resource for future controlled studies and methodological improvements.

Abstract

Objective: We aim to investigate long-term robotic surgical skill acquisition among surgical residents and the effects of training intervals and fatigue on performance. Methods: For six months, surgical residents participated in three training sessions once a month, surrounding a single 26-hour hospital shift. In each shift, they participated in training sessions scheduled before, during, and after the shift. In each training session, they performed three dry-lab training tasks: Ring Tower Transfer, Knot-Tying, and Suturing. We collected a comprehensive dataset, including videos synchronized with kinematic data, activity tracking, and scans of the suturing pads. Results: We collected a dataset of 972 trials performed by 18 residents of different surgical specializations. Participants demonstrated consistent performance improvement across all tasks. In addition, we found variations in between-shift learning and forgetting across metrics and tasks, and hints for possible effects of fatigue. Conclusion: The findings from our first analysis shed light on the long-term learning processes of robotic surgical skills with extended intervals and varying levels of fatigue. Significance: This study lays the groundwork for future research aimed at optimizing training protocols and enhancing AI applications in surgery, ultimately contributing to improved patient outcomes. The dataset will be made available upon acceptance of our journal submission.

Figures (8)

• Figure 1: The da Vinci Research Kit (dVRK). (a) A participant sits on the surgeon side and uses SSMs to control the PSMs on the patient side remotely. (b) Surgeon side configuration. (c) Patient side configuration with the Knot-Tying task.
• Figure 2: The surgical training tasks. (a) Ring Tower Transfer. (b) Knot-Tying. (c) Suturing.
• Figure 3: Data collection protocol. (a) The three sessions surrounding a single hospital shift. (b) The 18 sessions throughout six months.
• Figure 4: Examples of the recorded data. (a) The path of the tools in a Ring Tower Transfer task. (b),(c) Suturing pad scans of two participants.
• Figure 5: Timeline of training sessions relative to the start date of each participant. Each letter represents a participant who completed the study, and each marker indicates a training session. Note that for sessions conducted in accordance with the protocol (surrounding a single shift), all three markers appear as a single point.