Related Experiment Video
Updated: Mar 15, 2026
Implantation of Left Ventricular Assist Device (LVAD) in Juvenile Landrace Swine: A LVAD Implantation Model of Pediatric Heart Failure
Published on: January 16, 2026
Development and Validation of an Interpretable Model for Predicting Postoperative Hyperlactatemia in Young Children
Yuchan Chen1,2, Wenxin Ge1, Lixin Hu1
1Department of Maternal and Child Health, School of Public Health, Sun Yat-sen University, No. 74 Zhongshan 2nd Road, Yuexiu District, Guangzhou 510080, China.
Insights
This study developed an interpretable machine learning model to predict postoperative hyperlactatemia (POHL) in young children after cardiac surgery, identifying key risk factors for better patient management.
Area of Science:
- Pediatric Cardiac Surgery
- Machine Learning in Medicine
- Critical Care Medicine
Background:
- Postoperative hyperlactatemia (POHL) is a frequent complication in pediatric cardiac surgery.
- Perioperative risk factors for POHL in young children are not well understood.
Purpose of the Study:
- To develop and internally validate an interpretable machine learning (ML) model for identifying children at risk of POHL.
- To identify established and novel perioperative risk factors for POHL.
Main Methods:
- Retrospective analysis of 3224 children (0-36 months) undergoing cardiac surgery.
- Training and validation of four ML models: logistic regression, random forest, SVM, and XGBoost.
- Interpretability using SHapley Additive exPlanation (SHAP) to identify key predictors.
Main Results:
- The random forest (RF) model demonstrated strong performance (AUC 0.821).
- SHAP analysis identified 8 key predictors, including cardiopulmonary bypass duration, temperature, epinephrine dose, RACHS-1 category, low body weight, reduced LV end-diastolic diameter, plasma transfusion, and continued mechanical ventilation.
- 22.7% of children developed POHL.
Conclusions:
- An interpretable RF model was developed and validated to estimate POHL risk in young children post-cardiac surgery.
- The model integrates known and new predictors, potentially aiding early risk recognition.
- Further external validation is needed to support personalized perioperative management.
Abstract:
Objectives: Postoperative hyperlactatemia (POHL) is a common complication after pediatric cardiac surgery, yet its perioperative risk factors remain unclear. This study developed and internally validated an interpretable machine learning (ML) model to identify young children at risk for POHL. Methods: We retrospectively analyzed 3224 children aged 0 to 36 months from 2018 to 2023. Four ML models, including logistic regression (LR), random forest (RF), support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost), were trained and validated. Model performance was assessed using discrimination, calibration, and classification metrics, and decision curve analysis evaluated clinical utility. SHapley Additive exPlanation (SHAP) provided both global and local interpretability. Results: Of the 3224 children, 731 (22.7%) developed POHL, with a median age of 5 months. The RF model performed best (AUC, 0.821; 95% CI, 0.787-0.854; sensitivity, 69.7%; specificity, 84.1%; Brier score, 0.146). SHAP analysis identified 8 key predictors of POHL. Established factors included cardiopulmonary bypass duration, lowest bypass temperature, epinephrine dose, and RACHS-1 category. Novel contributors comprised low body weight, reduced left ventricular end-diastolic diameter, plasma transfusion, and continued mechanical ventilation within the first 24 postoperative hours. Conclusions: We developed and internally validated an interpretable RF model that integrates established and novel predictors to estimate POHL risk in young children after cardiac surgery. Pending external validation, it may support earlier risk recognition and more personalized perioperative management in this high-risk pediatric population.
