Related Experiment Video
Updated: Jan 10, 2026
Wireless Telemetry Device Implantation in a Fontan Ovine Model for Continuous and Long-Term Hemodynamic Monitoring
Published on: May 2, 2025
Prediction of Postoperative Mortality After Fontan Procedure: A Clinical Prediction Model Study Using Deep Learning
Jacek Kolcz1, Anna Budzynska1, Justyna Stefaniak2
1Department of Pediatric Cardiac Surgery, Collegium Medicum, Jagiellonian University, Wielicka 265 St., 31-007 Krakow, Poland.
Insights
A deep learning model accurately predicts postoperative mortality after Fontan surgery, improving risk stratification for single-ventricle congenital heart disease patients. Key factors like pulmonary artery pressure are identified, enhancing personalized care.
Area of Science:
- Cardiology
- Medical Artificial Intelligence
- Computational Biology
Background:
- The Fontan procedure is a critical surgery for single-ventricle congenital heart disease (CHD).
- Postoperative and long-term risks associated with the Fontan procedure necessitate improved risk stratification methods.
- Current risk models for Fontan surgery have limitations in providing accurate, individualized predictions.
Purpose of the Study:
- To develop and validate a deep learning (DL) model for predicting postoperative mortality after Fontan procedure.
- To identify key factors influencing mortality risk in Fontan surgery patients.
- To create a user-friendly tool for personalized risk assessment.
Main Methods:
- Retrospective analysis of 230 patients undergoing Fontan procedure (2010-2024).
- Development of a Deep Neural Network (DNN) model using comprehensive clinical, biochemical, and hemodynamic data.
- Utilized five-fold cross-validation, SMOTE for class imbalance, and SHAP for interpretability, with a Streamlit interface for clinical application.
Main Results:
- The DNN model achieved high predictive performance: 91.5% accuracy, 83.3% precision, 90.9% recall, and 0.94 AUC-ROC.
- SHAP analysis identified pulmonary artery pressure, ventricular end-diastolic pressure, BNP levels, and AV valve regurgitation severity as key mortality predictors.
- A Streamlit application was developed for accessible, personalized risk evaluation.
Conclusions:
- A DL model utilizing detailed clinical data can accurately predict postoperative mortality in Fontan surgery.
- AI-driven risk assessment, enhanced by interpretability, offers a valuable tool for personalized patient care.
- This approach has the potential to improve preoperative counseling, perioperative management, and patient outcomes, pending external validation.
Background:
The 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.
Methods:
We 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.
Results:
The 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.
Conclusions:
A 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.
