Center for Robotic Simulation & Education, Catherine & Joseph Aresty Department of Urology, University of Southern California Institute of Urology, Los Angeles, CA.
Computer Science Department, Viterbi School of Engineering, University of Southern California, Los Angeles, CA.
Surgery. 2021 May;169(5):1245-1249. doi: 10.1016/j.surg.2020.09.020. Epub 2020 Nov 5.
Automated performance metrics objectively measure surgeon performance during a robot-assisted radical prostatectomy. Machine learning has demonstrated that automated performance metrics, especially during the vesico-urethral anastomosis of the robot-assisted radical prostatectomy, are predictive of long-term outcomes such as continence recovery time. This study focuses on automated performance metrics during the vesico-urethral anastomosis, specifically on stitch versus sub-stitch levels, to distinguish surgeon experience. During the vesico-urethral anastomosis, automated performance metrics, recorded by a systems data recorder (Intuitive Surgical, Sunnyvale, CA, USA), were reported for each overall stitch (C) and its individual components: needle handling/targeting (C), needle driving (C), and suture cinching (C) (Fig 1, A). These metrics were organized into three datasets (GlobalSet [whole stitch], RowSet [independent sub-stitches], and ColumnSet [associated sub-stitches] (Fig 1, B) and applied to three machine learning models (AdaBoost, gradient boosting, and random forest) to solve two classifications tasks: experts (≥100 cases) versus novices (<100 cases) and ordinary experts (≥100 and <2,000 cases) versus super experts (≥2,000 cases). Classification accuracy was determined using analysis of variance. Input features were evaluated through a Jaccard index. From 68 vesico-urethral anastomoses, we analyzed 1,570 stitches broken down into 4,708 sub-stitches. For both classification tasks, ColumnSet best distinguished experts (n = 8) versus novices (n = 9) and ordinary experts (n = 5) versus super experts (n = 3) at an accuracy of 0.774 and 0.844, respectively. Feature ranking highlighted Endowrist articulation and needle handling/targeting as most important in classification. Surgeon performance measured by automated performance metrics on a granular sub-stitch level more accurately distinguishes expertise when compared with summary automated performance metrics over whole stitches.
自动性能指标客观地衡量了机器人辅助前列腺根治术中外科医生的表现。机器学习已经证明，自动性能指标，特别是在机器人辅助前列腺根治术的膀胱输尿管吻合术中，可预测长期结果，如控尿恢复时间。本研究专注于膀胱输尿管吻合术中的自动性能指标，特别是在缝线与亚缝线水平上，以区分外科医生的经验。在膀胱输尿管吻合术中，通过系统数据记录器（Intuitive Surgical，加利福尼亚州桑尼维尔）记录自动性能指标，每个整体缝线（C）及其各个组件：针处理/靶向（C）、针驱动（C）和缝线收紧（C）都有报告（图 1，A）。这些指标分为三组数据集（GlobalSet[整体缝线]、RowSet[独立亚缝线]和 ColumnSet[相关亚缝线]）（图 1，B），并应用于三种机器学习模型（AdaBoost、梯度提升和随机森林）来解决两个分类任务：专家（≥100 例）与新手（<100 例）和普通专家（≥100 例和<2000 例）与超级专家（≥2000 例）。使用方差分析确定分类准确性。通过杰卡德指数评估输入特征。从 68 例膀胱输尿管吻合术中，我们分析了 1570 个缝线，分为 4708 个亚缝线。对于这两个分类任务，ColumnSet 最佳区分了专家（n=8）与新手（n=9）和普通专家（n=5）与超级专家（n=3），准确性分别为 0.774 和 0.844。特征排名突出了腕关节运动和针处理/靶向作为分类的最重要特征。与整体缝线的自动性能指标相比，基于亚缝线级别的自动性能指标更能准确区分外科医生的表现。
