Pediatric Cardiac Surgery: Machine Learning Models for Postoperative Complication Prediction

Purpose: Managing children undergoing cardiac surgery with cardiopulmonary bypass (CPB) presents a significant challenge for anesthesiologists. Machine Learning (ML)-assisted tools have the potential to enhance the recognition of patients at risk of complications and predict potential issues, ultimately improving outcomes.

Methods: We evaluated the prediction capacity of six models, ranging from logistic regression to support vector machine, using a dataset comprising 33 variables and 1364 subjects. The Area Under the Curve (AUC) and the F1 score served as the primary evaluation metrics. Our primary objectives were twofold: first, to develop an effective prediction model, and second, to create a user-friendly comprehensive model for identifying high-risk patients.

Results: The logistic regression model demonstrated the highest effectiveness, achieving an AUC of 83.65%, and an F1 score of 0.7296, with balanced sensitivity and specificity of 77.94% and 76.47%, respectively. In comparison, the comprehensive three-layer decision tree model achieved an AUC of 72.84%, with sensitivity (79.41%) comparable to more complex models.

Conclusion: Our machine learning-assisted tools provide an additional perspective and enhance the predictive capabilities of traditional scoring methods. These tools can assist anesthesiologists in making well-informed decisions. Furthermore, we have successfully demonstrated the feasibility of creating a practical white-box model. The next steps involve conducting clinical validation and multicenter cross-validation.

Trial Registration: NCT05537168.