Development and validation of a nomogram for predicting prolonged ICU stays after pediatric cardiac surgery.

Abstract

Background: This study aimed to develop and validate a nomogram to estimate the probability of prolonged intensive care unit (ICU) stays.

Methods: Pediatric patients who underwent cardiac surgery were included, with data collected from the pediatric intensive care database. The datasets were randomly divided into a training set (75%) and a testing set (25%). A nomogram model was developed to predict prolonged ICU stays in the training set and then validated in the testing set.

Results: A total of 795 patients and 266 patients were assigned to the training and testing sets, respectively, with consistent variables. The nomogram developed from the training set included eight characteristics: age, systolic blood pressure, respiratory rate, bicarbonate, direct bilirubin, high-sensitivity C-reactive protein, international normalized ratio, and operation time. The area under the curve values of the nomogram in the training and testing sets were 0.812 and 0.736, respectively. The nomogram demonstrated excellent discrimination and calibration. Decision curve analysis showed that the use of the nomogram resulted in more favorable outcomes compared with the strategies of treating all or none of the patients.

Conclusion: This study presents a nomogram that may enable early identification of high-risk patients and facilitates tailored postoperative care and better outcomes after pediatric cardiac surgery.