JMIR Publications

ABSTRACT

Background:

Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication following pediatric cardiac surgery, which is associated with increased morbidity and mortality. The early prediction of CSA-AKI could significantly improve the implementation of preventive and therapeutic strategies during the perioperative periods. However, there is limited clinical information on how to identify pediatric patients at high risk of CSA-AKI.

Objective:

The study aimed to develop and validate machine learning models with which to predict the development of CSA-AKI in the pediatric population.

Methods:

The retrospective cohort study enrolled patients aged 1 month to 18 years who underwent cardiac surgery with cardiopulmonary bypass at three medical centers of Central South University in China. CSA-AKI was defined according to the 2012 Kidney Disease: Improving Global Outcomes criteria. Feature selection was applied separately to two datasets, the preoperative dataset, and the combined preoperative and intraoperative dataset. Multiple machine learning algorithms were tested, including K-nearest neighbor, naive Bayes, support vector machines, random forest, eXtreme Gradient Boosting (XGBoost), and neural networks. The best-performing model was identified in cross-validation using the area under the receiver operating characteristic curve (AUROC). Model interpretations were generated using the Shapley Additive exPlanations (SHAP) method.

Results:

A total of 3,278 patients from one of the centers were used for model derivation, while 616 patients from another two centers served as an external validation cohort. The incidence of CSA-AKI was 17.2% in the derivation cohort and 8.6% in the external validation cohort. Among the considered machine learning models, the XGBoost model achieved the best predictive performance in cross-validation. The AUROC of the XGBoost model using only the preoperative variables was 0.890 (95% CI 0.876-0.906) in the derivation cohort and 0.849 (95% CI 0.797-0.898) in the external validation cohort. When the intraoperative variables were included, the AUROC increased to 0.912 (95% CI 0.899-0.924) and 0.883 (95% CI 839-0.913) in the two cohorts, respectively. The SHAP method revealed that baseline serum creatinine, perfusion time, body length, operation time, and intraoperative blood loss were the top five predictors of CSA-AKI.

Conclusions:

The interpretable XGBoost models provide practical tools for the early prediction of CSA-AKI that are valuable in risk stratification and perioperative management of pediatric patients undergoing cardiac surgery.