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

BACKGROUND: The aim of this study was to construct a nomogram model for discriminating the risk of delirium in patients undergoing cardiovascular surgery. METHODS: From 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. RESULTS: The 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 [Formula: see text] 1.004, 95% CI: 1.001–1.008, [Formula: see text] 0.018), postoperative serum sodium (OR [Formula: see text] 1.112, 95% CI: 1.049–1.178, [Formula: see text] 0.001), age (OR [Formula: see text] 1.027, 95% CI: 1.006–1.048, [Formula: see text] 0.011), and postoperative MV (OR [Formula: see text] 1.019, 95% CI: 1.008–1.030, [Formula: see text] 0.001) were independent risk factors. The results showed that AUC[Formula: see text] 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 ([Formula: see text] 6.200, [Formula: see text] 0.625). The results of verification showed that the AUC[Formula: see text] was 0.705, and the 95% CI was 0.657–0.752. The Hosmer-Lemeshow goodness of fit test results were [Formula: see text] 8.653 and [Formula: see text] 0.372, indicating that the predictive effect of the model is good. CONCLUSIONS: The 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.