Objective: This study aimed to construct a predictive model for assessing the risk of peripherally inserted central catheter (PICC) tip migration in patients with bladder cancer, facilitating early detection and tailored management of high-risk cases through comprehensive risk stratification. Methods: A total of 280 patients with bladder cancer who underwent PICC placement for chemotherapy at our institution between January 2021 to May 2023 were retrospectively enrolled and randomly allocated into a training set (n = 196) and a validation set (n = 84) in a 7:3 ratio. Independent risk factors were identified through univariate analysis, variable compression via Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariate logistic regression. Subsequently, random forest, support vector machine and K-nearest neighbour models were constructed. The optimal model was selected based on the area under the curve (AUC), calibration curves and decision curve analysis (DCA). Visualisation and interpretability were further assessed using a nomogram and SHapley Additive exPlanations (SHAP) values. Results: The baseline characteristics were balanced between the training and validation sets (p > 0.05). Multivariate logistic regression analysis further confirmed that body mass index (BMI), abnormal catheter tip position, catheter indwelling duration, number of puncture attempts and range of motion in the limb with the catheter were independent risk factors for PICC tip migration (p Conclusions: BMI, abnormal catheter tip position, number of puncture attempts, range of motion in the limb with the catheter and catheter indwelling duration were identified as risk factors for PICC tip migration in patients with bladder cancer. The risk prediction model developed in this study, based on these factors, demonstrates substantial clinical predictive value.
A Thu, study studied this question.