Dataset Information

How to Bring Surgery to the Next Level: Interpretable Skills Assessment in Robotic-Assisted Surgery.

ABSTRACT:

Introduction

A surgeon's technical skills are an important factor in delivering optimal patient care. Most existing methods to estimate technical skills remain subjective and resource intensive. Robotic-assisted surgery (RAS) provides a unique opportunity to develop objective metrics using key elements of intraoperative surgeon behavior which can be captured unobtrusively, such as instrument positions and button presses. Recent studies have shown that objective metrics based on these data (referred to as objective performance indicators [OPIs]) correlate to select clinical outcomes during robotic-assisted radical prostatectomy. However, the current OPIs remain difficult to interpret directly and, therefore, to use within structured feedback to improve surgical efficiencies.

Methods

We analyzed kinematic and event data from da Vinci surgical systems (Intuitive Surgical, Inc., Sunnyvale, CA, USA) to calculate values that can summarize the use of robotic instruments, referred to as OPIs. These indicators were mapped to broader technical skill categories of established training protocols. A data-driven approach was then applied to further sub-select OPIs that distinguish skill for each technical skill category within each training task. This subset of OPIs was used to build a set of logistic regression classifiers that predict the probability of expertise in that skill to identify targeted improvement and practice. The final, proposed feedback using OPIs was based on the coefficients of the logistic regression model to highlight specific actions that can be taken to improve.

Results

We determine that for the majority of skills, only a small subset of OPIs (2-10) are required to achieve the highest model accuracies (80-95%) for estimating technical skills within clinical-like tasks on a porcine model. The majority of the skill models have similar accuracy as models predicting overall expertise for a task (80-98%). Skill models can divide a prediction into interpretable categories for simpler, targeted feedback.

Conclusion

We define and validate a methodology to create interpretable metrics for key technical skills during clinical-like tasks when performing RAS. Using this framework for evaluating technical skills, we believe that surgical trainees can better understand both what can be improved and how to improve.

SUBMITTER: Brown KC

PROVIDER: S-EPMC7768128 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundNon-technical skills (NTS) are essential for safe surgical practice as they impact workflow and patient outcomes. Observational tools to measure operating room (OR) teams' NTS have been introduced. However, there are none that account for the specific teamwork challenges introduced by robotic-assisted surgery (RAS). We set out to develop and content-validate a tool to assess multidisciplinary NTS in RAS.MethodologyStepwise, multi-method procedure. Observations in different surgical departments and a scoping literature review were first used to compile a set of RAS-specific teamwork behaviours. This list was refined and expert validated using a Delphi consensus approach consisting of qualitative interviews and a quantitative survey. Then, RAS-specific behaviours were merged with a well-established assessment tool on OR teamwork (NOTECHS II). Finally, the new tool-RAS-NOTECHS-was applied in standardized observations of real-world procedures to test its reliability (inter-rater agreement via intra-class correlations).ResultsOur scoping review revealed 5242 articles, of which 21 were included based on pre-established inclusion criteria. We elicited 16 RAS-specific behaviours from the literature base. These were synthesized with further 18 behavioural markers (obtained from 12 OR-observations) into a list of 26 behavioural markers. This list was reviewed by seven RAS experts and condensed to 15 expert-validated RAS-specific behavioural markers which were then merged into NOTECHS II. For five observations of urologic RAS procedures (duration: 13 h and 41 min), inter-rater agreement for identification of behavioural markers was strong. Agreement of RAS-NOTECHS scores indicated moderate to strong agreement.ConclusionsRAS-NOTECHS is the first observational tool for multidisciplinary NTS in RAS. In preliminary application, it has been shown to be reliable. Since RAS is rapidly increasing and challenges for effective and safe teamwork remain at the forefront of quality and safety of surgical care, RAS-NOTECHS may contribute to training and improvement efforts in technology-facilitated surgeries.