What does this research mean for the field?

An interpretable random forest model can predict postoperative hyperlactatemia in young children following congenital heart surgery with an AUC of 0.821. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to develop and validate a machine learning model to identify young children at risk for postoperative hyperlactatemia following cardiac surgery.

March 2, 2026Open Access

Development and Validation of an Interpretable Model for Predicting Postoperative Hyperlactatemia in Young Children Following Congenital Heart Surgery

Key Result

Random forest model predicted postoperative hyperlactatemia with AUC 0.821, sensitivity 69.7%, specificity 84.1% in 3224 children post congenital heart surgery.

Key Points

The aim is to develop and validate a machine learning model to identify young children at risk for postoperative hyperlactatemia following cardiac surgery.
Retrospective analysis of 3224 children aged 0 to 36 months from 2018 to 2023
Training and validation of four machine learning models: logistic regression, random forest, support vector machine, and eXtreme Gradient Boosting
Model performance assessed through discrimination, calibration, and classification metrics
SHapley Additive exPlanation analysis for model interpretability
731 out of 3224 children (22.7%) developed postoperative hyperlactatemia
Random forest model showed the best performance with an AUC of 0.821
Key predictors included cardiopulmonary bypass duration and lowest bypass temperature
Novel predictors were identified, such as low body weight and reduced left ventricular end-diastolic diameter

Structured PICO

Can machine learning models accurately predict postoperative hyperlactatemia in young children following congenital heart surgery?

Population

3224 children aged 0 to 36 months undergoing congenital heart surgery

Intervention

Machine learning models (Random Forest, Logistic Regression, Support Vector Machine, XGBoost) for predicting postoperative hyperlactatemia

Outcome

Postoperative hyperlactatemia (POHL)surrogate

A random forest machine learning model can accurately predict postoperative hyperlactatemia in young children after congenital heart surgery using 8 key perioperative predictors.

Main Result

Absolute Event Rate: 0% vs 0%

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.