Screening of Associated Factors for Erectile Dysfunction after Radical Prostatectomy and Construction of a Clinical Risk Assessment Model: A Retrospective Study

ABSTRACT

Objective: In this article, the associated factors for erectile dysfunction (ED) after radical prostatectomy (RP) were explored, and a clinical risk assessment model was constructed. Methods: A total of 155 patients who underwent RP in People’s Hospital of Hunan Province from November 2020, to November 2021, were selected as the study group. In accordance with the results of International Index of Erectile Function (IIEF-5) at 6 months after surgery, 88 patients were included in the ED group (IIEF-5 <22), and 67 patients were included in the non-ED group (IIEF-5 ≥22). Univariate and multivariate logistic regression analyses were conducted to screen the risk factors for ED after RP, and a risk model was constructed on this basis. In addition, 43 patients with ED after RP and 41 patients with non-ED after RP from January 2022, to January 2023, were included in the test group to evaluate the predictive efficacy of the clinical risk assessment model on the basis of the receiver operating characteristic curve. Results: The study group had a lower postoperative IIEF-5 score than before surgery (p < 0.001). The incidence of ED after RP in the study group was 56.77% (88/155). Multivariate analysis showed that advanced age (odds ratio (OR) = 1.155), large prostate volume (OR = 1.077), smoking (OR = 5.676), drinking (OR = 3.495), hypertension (OR = 8.079), diabetes (OR = 6.082), low preoperative serum testosterone (T) level (OR = 0.684) and high preoperative serum endothelin-1 (ET-1) level (OR = 1.192) were risk factors for ED after RP (p < 0.05). A risk model was constructed as follows: Z = 0.144 × (age) + 0.074 × (prostate volume) + 1.736 × (smoking) + 1.251 × (drinking) + 2.089 × (hypertension) + 1.805 × (diabetes) − 0.380 × (preoperative serum T) + 0.175 × (preoperative serum ET-1). The area under curve (AUC), sensitivity, specificity and 95% CI of this model were 0.906, 97.70%, 73.20%, and 0.848–0.964, respectively (p < 0.001)(AU)