Abstract
OBJECTIVE: To develop and validate a risk prediction model for Chemical cystitis in patients with non-muscle-invasive bladder cancer (NMIBC) undergoing intravesical instillation. METHODS: This study retrospectively enrolled 225 patients with NMIBC who received intravesical instillation between January 2024 and January 2026. Predictive variables, including demographic characteristics, oncological features, medical history, treatment-related factors, and procedural anatomy, were collected. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression from 18 candidate variables. A multivariable logistic regression model was constructed based on the selected variables and visualized as a risk prediction nomogram. The model's performance was evaluated and validated using the Area Under the Curve (AUC), calibration curves, and Decision Curve Analysis (DCA) to assess discrimination, calibration, and clinical utility. RESULTS: Five independent predictors were identified from the candidate variables through LASSO and multivariable logistic regression analysis: type of instillation agent, tumor multifocality, retention time of the agent, bladder capacity, and tumor grade. The predictive model demonstrated robust discriminative ability in both the training and validation cohorts, with AUC values of 0.840 and 0.868, respectively. Calibration curves showed high consistency between the predicted and observed risks, and DCA further confirmed the model's positive net benefit in clinical decision-making. CONCLUSION: We successfully developed and validated a practical nomogram for the individualized prediction of Chemical cystitis risk in patients with NMIBC. This tool can assist clinicians in identifying high-risk patients prior to treatment, thereby enabling more targeted monitoring and preventive strategies. This study is limited by its single-center retrospective design, and external prospective validation is warranted.