Explainable Prediction of ICU Transfer in Acute Pancreatitis: A Neural Network Model With SHAP Interpretability for Clinical Decision Support

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Machine learning model predicts ICU admission for acute pancreatitis, highlighting feature importance with SHAP.

The neural network model accurately predicts ICU admission in acute pancreatitis patients, improving healthcare outcomes.
Achieved an AUC of 0.891, with sensitivity of 0.852 and specificity of 0.767, validating prediction accuracy.
Utilized multiple machine learning approaches, with SHAP for interpreting feature importance in the final model.
This interpretable model aids clinicians in timely decision-making for patient management in acute pancreatitis.

Chen et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark