A deep‐learning model using automated performance metrics and clinical features to predict urinary continence recovery after robot‐assisted radical prostatectomy

• Published in: BJU international Vol. 124; no. 3; pp. 487 - 495
• Main Authors: Hung, Andrew J., Chen, Jian, Ghodoussipour, Saum, Oh, Paul J., Liu, Zequn, Nguyen, Jessica, Purushotham, Sanjay, Gill, Inderbir S., Liu, Yan
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.09.2019
• Subjects: Aged; artificial intelligence; Automation; Business metrics; Cancer surgery; Cohort Studies; Deep Learning; Feasibility studies; Humans; Male; Middle Aged; Models, Statistical; Postoperative Complications - epidemiology; Prostate - surgery; Prostate cancer; Prostatectomy; Prostatectomy - adverse effects; Prostatectomy - statistics & numerical data; quality of life; Recovery of Function - physiology; Robotic surgery; robotic surgical procedures; Robotic Surgical Procedures - adverse effects; Robotic Surgical Procedures - statistics & numerical data; Surgeons; Surgeons - statistics & numerical data; Treatment Outcome; urinary incontinence; Urinary Incontinence - epidemiology; Urological surgery; robotic surgical procedures; prostatectomy; quality of life; urinary incontinence; artificial intelligence
• ISSN: 1464-4096; 1464-410X; 1464-410X
• DOI: 10.1111/bju.14735

Objectives To predict urinary continence recovery after robot‐assisted radical prostatectomy (RARP) using a deep learning (DL) model, which was then used to evaluate surgeon's historical patient outcomes. Subjects and Methods Robotic surgical automated performance metrics (APMs) during RARP, and patient clinicopathological and continence data were captured prospectively from 100 contemporary RARPs. We used a DL model (DeepSurv) to predict postoperative urinary continence. Model features were ranked based on their importance in prediction. We stratified eight surgeons based on the five top‐ranked features. The top four surgeons were categorized in ‘Group 1/APMs’, while the remaining four were categorized in ‘Group 2/APMs’. A separate historical cohort of RARPs (January 2015 to August 2016) performed by these two surgeon groups was then used for comparison. Concordance index (C‐index) and mean absolute error (MAE) were used to measure the model's prediction performance. Outcomes of historical cases were compared using the Kruskal–Wallis, chi‐squared and Fisher's exact tests. Results Continence was attained in 79 patients (79%) after a median of 126 days. The DL model achieved a C‐index of 0.6 and an MAE of 85.9 in predicting continence. APMs were ranked higher by the model than clinicopathological features. In the historical cohort, patients in Group 1/APMs had superior rates of urinary continence at 3 and 6 months postoperatively (47.5 vs 36.7%, P = 0.034, and 68.3 vs 59.2%, P = 0.047, respectively). Conclusion Using APMs and clinicopathological data, the DeepSurv DL model was able to predict continence after RARP. In this feasibility study, surgeons with more efficient APMs achieved higher continence rates at 3 and 6 months after RARP.