Does Centralization of Radical Prostatectomy Reduce the Incidence of Postoperative Urinary Incontinence?

Estimating Surgical Urethral Length on Intraoperative Robot-Assisted Prostatectomy Images Using Artificial Intelligence Anatomy Recognition

Objective: To construct a convolutional neural network (CNN) model that can recognize and delineate anatomic structures on intraoperative video frames of robot-assisted radical prostatectomy (RARP) and to use these annotations to predict the surgical urethral length (SUL). Background: Urethral dissection during RARP impacts patient urinary incontinence (UI) outcomes, and requires extensive training. Large differences exist between incontinence outcomes of different urologists and hospitals. Also, surgeon experience and education are critical toward optimal outcomes. Therefore, new approaches are warranted. SUL is associated with UI. Artificial intelligence (AI) surgical image segmentation using a CNN could automate SUL estimation and contribute toward future AI-assisted RARP and surgeon guidance. Methods: Eighty-eight intraoperative RARP videos between June 2009 and September 2014 were collected from a single center. Two hundred sixty-four frames were annotated according to prostate, urethra, ligated plexus, and catheter. Thirty annotated images from different RARP videos were used as a test data set. The dice (similarity) coefficient (DSC) and 95th percentile Hausdorff distance (Hd95) were used to determine model performance. SUL was calculated using the catheter as a reference. Results: The DSC of the best performing model were 0.735 and 0.755 for the catheter and urethra classes, respectively, with a Hd95 of 29.27 and 72.62, respectively. The model performed moderately on the ligated plexus and prostate. The predicted SUL showed a mean difference of 0.64 to 1.86 mm difference vs human annotators, but with significant deviation (standard deviation = 3.28-3.56). Conclusion: This study shows that an AI image segmentation model can predict vital structures during RARP urethral dissection with moderate to fair accuracy. SUL estimation derived from it showed large deviations and outliers when compared with human annotators, but with a small mean difference (<2 mm). This is a promising development for further research on AI-assisted RARP.

Validation of Claims Data for Absorbing Pads as a Measure for Urinary Incontinence after Radical Prostatectomy, a National Cross-Sectional Analysis

The use of healthcare insurance claims data for urinary incontinence (UI) pads has the potential to serve as an objective measure for assessing post-radical prostatectomy UI rates, but its validity for this purpose has not been established. The aim of this study is to correlate claims data with Patient Reported Outcome Measures (PROMs) for UI pad use. Patients who underwent RP in the Netherlands between September 2019 and February 2020 were included. Incontinence was defined as the daily use of ≥1 pad(s). Claims data for UI pads at 12-15 months after RP were extracted from a nationwide healthcare insurance database in the Netherlands. Participating hospitals provided PROMS data. In total, 1624 patients underwent RP. Corresponding data of 845 patients was provided by nine participating hospitals, of which 416 patients were matched with complete PROMs data. Claims data and PROMs showed 31% and 45% post-RP UI (≥1 pads). UI according to claims data compared with PROMs had a sensitivity of 62%, specificity of 96%, PPV of 92%, NPV of 75% and accuracy of 81%. The agreement between both methods was moderate (κ = 0.60). Claims data for pads moderately align with PROMs in assessing post-prostatectomy urinary incontinence and could be considered as a conservative quality indicator.