PD57-07 AUTOMATED PERFORMANCE METRICS THAT ANTICIPATE EARLY AND LATE URINARY CONTINENCE RECOVERY AFTER ROBOT-ASSISTED RADICAL PROSTATECTOMY

Abstract

You have accessJournal of UrologyProstate Cancer: Localized: Surgical Therapy IV (PD57)1 Sep 2021PD57-07 AUTOMATED PERFORMANCE METRICS THAT ANTICIPATE EARLY AND LATE URINARY CONTINENCE RECOVERY AFTER ROBOT-ASSISTED RADICAL PROSTATECTOMY Runzhuo Ma, Ryan S. Lee, Sharath S. Reddy, Jessica H. Nguyen, Steven Cen, Katarina Urbanova, Joern H. Witt, Inderbir S. Gill, Christian Wagner, and Andrew J. Hung Runzhuo MaRunzhuo Ma More articles by this author , Ryan S. LeeRyan S. Lee More articles by this author , Sharath S. ReddySharath S. Reddy More articles by this author , Jessica H. NguyenJessica H. Nguyen More articles by this author , Steven CenSteven Cen More articles by this author , Katarina UrbanovaKatarina Urbanova More articles by this author , Joern H. WittJoern H. Witt More articles by this author , Inderbir S. GillInderbir S. Gill More articles by this author , Christian WagnerChristian Wagner More articles by this author , and Andrew J. HungAndrew J. Hung More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002091.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Automated performance metrics (APMs), objective metrics derived from kinematic/system events data and captured by a systems data recorder (Intuitive Surgical) during surgery, are a validated surgical assessment tool. We previously showed APMs from certain steps of robot-assisted radical prostatectomy (RARP) to be predictors of early urinary continence recovery. Having expanded our cohort to include two high-volume centers with longer follow-up, we now explore how APMs may be associated with both early and late urinary continence recovery after RARP. METHODS: Non-teaching RARP cases from 2016-2019 from two centers were included in this study. Non-teaching cases were defined as cases in which an expert surgeon (>100 prior robotic surgery cases) performed all seven major steps, including anterior/posterior bladder neck dissection (BND), left/right neurovascular bundle (NVB) preservation, apical dissection, and posterior/anterior vesicourethral anastomosis. The outcome of interest was 6-month (early) and 12-month (late) continence recovery status. Continence was defined as using 0 or 1 safety pad per day. Decision tree (CART©) was used to predict outcomes. APMs from the seven major steps (38 x 7), 9 patient factors, and 5 treatment factors were utilized in the model. Gini impurity was used as splitting criteria and a 10-fold cross-validation was conducted. Out-of-bag Gini impurity index was used for feature ranking. RESULTS: 110 non-teaching RARP cases from 22 expert surgeons were included in this study. At 6 and 12 months, 59.1% (65/110) and 74.5% (82/110) of cases recovered continence, respectively. In the training phase of the model, the 6- and 12-month continence recovery prediction achieved 71.8% and 65.5% accuracy, respectively; in the testing phase, the accuracies slightly decreased to 67.3% and 61.8%. At both time points, the top 10 features came from APMs; none were patient factors. For 6-month continence status prediction, all top 10 features came from anterior BND. For 12-month continence status prediction, 6/10 came from anterior BND, 3/10 came from left NVB, and 1/10 came from posterior BND. CONCLUSIONS: Surgical performance, as measured by APMs, was the strongest predicter of both early and late continence recovery after RARP. Bladder neck dissection was the most important surgical performance step for early continence recovery in this non-teaching case cohort, while late continence recovery was affected by performance in more varied steps. Source of Funding: This study was funded in part by an Intuitive Surgical Clinical Grant; Intuitive Surgical provided the systems data recorder. Research reported in this publication was also supported in part by the National Institute Of Biomedical Imaging And Bioengineering of the National Institutes of Health under Award Number K23EB026493. © 2021 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e1012-e1012 Advertisement Copyright & Permissions© 2021 by American Urological Association Education and Research, Inc.MetricsAuthor Information Runzhuo Ma More articles by this author Ryan S. Lee More articles by this author Sharath S. Reddy More articles by this author Jessica H. Nguyen More articles by this author Steven Cen More articles by this author Katarina Urbanova More articles by this author Joern H. Witt More articles by this author Inderbir S. Gill More articles by this author Christian Wagner More articles by this author Andrew J. Hung More articles by this author Expand All Advertisement Loading ...