Risk Prediction Model for Bladder Spasm After Transurethral Resection of Bladder Tumor Based on Decision Tree Algorithm
Abstract：Objective: To construct a risk prediction model for bladder spasm after transurethral resection of bladder tumor (TURBT) based on decision tree algorithm, providing evidence for clinical prevention and treatment. Methods: A retrospective study was conducted on 220 patients who underwent TURBT in the hospital from January 2022 to January 2024. Patients were divided into spasm group and non-spasm group according to whether they developed bladder spasm after surgery. Univariate analysis and further logistic regression analysis were used to screen independent risk factors for postoperative bladder spasm in TURBT patients, and a predictive model was built based on the decision tree algorithm. Results: Univariate analysis showed that preoperative urinary tract infection, number of tumors, operation time, number of operations, and duration of catheterization were associated with postoperative bladder spasm in TURBT patients (all P < 0.05). Logistic regression analysis showed that preoperative urinary tract infection, long operation time, multiple tumors, and prolonged catheterization were risk factors for postoperative bladder spasm in TURBT patients (all P < 0.05). In the decision tree model, the area under the receiver operating characteristic curve (AUC) for predicting bladder spasm was 0.926 [95% CI (0.887, 0.966)], with the duration of catheterization being the most important predictive factor. Conclusion: The prediction model for bladder spasm after TURBT constructed based on the decision tree algorithm has high application value and can provide reference for screening patients at risk of bladder spasm in clinical practice.
Keywords：decision tree algorithmtransurethral resection of bladder tumorbladder spasmrisk prediction model
Publication Date：2025-08-25
Online Publishing Date：2025-09-04(First online date of this platform, not the publication date of the document)
Pages：5( 3036-3040 )