Querying the capability of the post-HoLEP endoscopic aspect of the membranous urethral mucosa in predicting urinary incontinence: a prospective AI-based analysis.

Abstract

Introduction: Transient stress urinary incontinence (SUI) after holmium laser enucleation of prostate (HoLEP) is commonly linked to intraoperative injury of the external urethral sphincter (EUS). We assessed the reliability of the post-HoLEP endoscopic appearance of the membranous urethra mucosa (MUM) in predicting post-HoLEP continence.

Methods: Forty HoLEPs were prospectively recorded by an artificial intelligence video platform capable of segmenting clips by surgical steps. The final clip was assessed for postoperative MUM integrity by 2 experts in HoLEP and 2 residents, all blinded to the clinical outcome. Their findings were scored as no injury, anterior injury, and lateral injury, and the results underwent statistical analyses.

Results: The referent rating was 72% for no injury, 23% for anterior injury, and 5% for lateral injury. The overall inter-observer agreement was K = 0.26, the inter-experts' agreement was K = 0.12, and the inter-residents' agreement was K = 0.38, reflecting low inter-observer reliability. The postoperative rate of SUI, defined as any drop on a pad, was 30% at 1 month and 12.5% at 3 months. There was no association between the MUM injury graded and SUI according to any of the evaluators (univariate analysis OR 0.83, 95%CI 0.17-3.89). A multivariate analysis controlling for age, prostate size, resectoscope size (22 vs. 26 FR), surgery time, and use of final fulguration showed no significantly independent predictor of post-HoLEP-related incontinence.

Conclusion: The post-HoLEP endoscopic appearance of the MUM is apparently not a reliable marker of EUS injury. Further studies are needed to better understand the mechanism underlying post-HoLEP SUI.