We randomly split the initial dataset into training and testing datasets in a 7:3 ratio to develop and validate a prediction model. The LASSO method was utilized on the training dataset to select significant indicators, followed by COX regression to establish the prediction model and create a nomogram. A calibration curve was generated in the training group to assess the concordance between predicted probability and actual observation probability. Furthermore, decision curve analysis assessed the clinical usefulness of our column chart by measuring net benefits at various threshold probabilities.
