Prediction of Postoperative Mortality After Fontan Procedure: A Clinical Prediction Model Study Using Deep Learning Artificial Intelligence Techniques.

backgroundThe Fontan procedure is a palliative surgery for patients with single-ventricle congenital heart disease (CHD), but it is associated with postoperative and long-term mortality and morbidity. Accurate, individualized risk stratification remains a challenge with traditional models. This study aimed to develop and validate a deep learning (DL) model to predict postoperative mortality after the Fontan procedure and to identify key predictive factors.

methodsWe retrospectively analysed data from 230 patients who underwent the Fontan procedure between 2010 and 2024. A Deep Neural Network (DNN) model was developed using comprehensive preoperative, intraoperative, and postoperative clinical, biochemical, and hemodynamic variables. The dataset was split using five-fold cross-validation, with 80% for training and 20% for testing in each fold. The Synthetic Minority Over-sampling Technique (SMOTE) was used to fix class imbalance. Model performance was evaluated using five-fold stratified cross-validation. We assessed accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC). SHapley Additive exPlanations (SHAP) analysis was employed to enhance model interpretability and identify the importance of features. A user-friendly clinical application interface was developed using Streamlit. This study was reported in accordance with the TRIPOD + AI reporting guidelines.

resultsThe DNN model demonstrated superior performance in predicting postoperative mortality, achieving an overall accuracy of 91.5% (95% CI: 87.2-94.8%), precision of 83.3% (95% CI: 76.5-89.1%), recall (sensitivity) of 90.9% (95% CI: 85.2-95.1%), specificity of 92.5% (95% CI: 88.3-95.7%), F1-score of 87.0% (95% CI: 82.1-91.3%), and an AUC-ROC of 0.94 (95% CI: 0.88-0.99). SHAP analysis identified key predictors of mortality, such as pulmonary artery pressure, ventricular end-diastolic pressure, preoperative BNP levels, and severity of AV valve regurgitation. The Streamlit application offered a user-friendly interface for personalized risk evaluation.

conclusionsA deep learning model that incorporates detailed clinical data can precisely forecast postoperative mortality in patients undergoing Fontan surgeries. This AI-based method, combined with interpretability techniques, provides a valuable tool for personalized risk assessment. It has the potential to improve preoperative counseling, optimize perioperative care, and enhance patient outcomes. However, additional external validation is needed to verify its broader applicability and clinical usefulness.