Prediction model for delirium in patients with cardiovascular surgery: development and validation

Abstract

BackgroundThe aim of this study was to construct a nomogram model for discriminating the risk of delirium in patients undergoing cardiovascular surgery.MethodsFrom January 2017 to June 2020, we collected data from 838 patients who underwent cardiovascular surgery at the Affiliated Hospital of Nantong University. Patients were randomly divided into a training set and a validation set at a 5:5 ratio. A nomogram model was established based on logistic regression. Discrimination and calibration were used to evaluate the predictive performance of the model.ResultsThe incidence of delirium was 48.3%. A total of 389 patients were in the modelling group, and 449 patients were in the verification group. Logistic regression analysis showed that CPB duration (OR = 1.004, 95% CI: 1.001–1.008, P= 0.018), postoperative serum sodium (OR = 1.112, 95% CI: 1.049–1.178, P< 0.001), age (OR = 1.027, 95% CI: 1.006–1.048, P= 0.011), and postoperative MV (OR = 1.019, 95% CI: 1.008–1.030, P< 0.001) were independent risk factors. The results showed that AUC^text {ROC} was 0.712 and that the 95% CI was 0.661–0.762. The Hosmer-Lemeshow goodness of fit test showed that the predicted results of the model were in good agreement with the actual situation (chi ^{2}= 6.200, P= 0.625). The results of verification showed that the AUC^text {ROC} was 0.705, and the 95% CI was 0.657–0.752. The Hosmer-Lemeshow goodness of fit test results were chi ^{2}= 8.653 and P= 0.372, indicating that the predictive effect of the model is good.ConclusionsThe establishment of the model provides accurate and objective assessment tools for medical staff to start preventing postoperative delirium in a purposeful and focused manner when a patient enters the CSICU after surgery.