Introduction
Lower urinary tract diseases resulting from benign prostatic hyperplasia (BPH) constitute a common urological issue in men, previously addressed through transurethral resection of the prostate (TURP). However, TURP surgery presents limitations—it's unsuitable for patients at high risk of bleeding or those with significantly enlarged prostates. HoLEP, introduced in 1995, was deemed a potential solution to mitigate issues associated with TURP surgery. Nonetheless, postoperative temporary urinary incontinence has emerged as a troubling complication of HoLEP procedures.
To monitor postoperative recovery, we gathered and analyzed data from 337 male patients with BPH. Our goal was to determine whether machine learning methods could train a model to assist clinicians in predicting the occurrence or duration of temporary postoperative incontinence in patients with benign prostatic hypertrophy. This information could significantly aid medical decision-making processes.