Constructing a prediction model for acute pancreatitis severity based on liquid neural network

Abstract

Acute pancreatitis (AP) is a common disease, and severe acute pancreatitis (SAP) has a high morbidity and mortality rate. Early recognition of SAP is crucial for prognosis. This study aimed to develop a novel liquid neural network (LNN) model for predicting SAP. This study retrospectively analyzed the data of AP patients admitted to the Second Affiliated Hospital of Guilin Medical University between January 2020 and June 2024. Data imbalance was dealt with by data preprocessing and using the synthetic minority oversampling technique (SMOTE). A new feature selection method was designed to optimize model performance. Logistic regression (LR), decision tree (DCT), random forest (RF), Extreme Gradient Boosting (XGBoost), and LNN models were built. The model's performance was evaluated by calculating the area under the receiver operating characteristic (ROC) curve (AUC) and other statistical metrics. In addition, SHapley Additive exPlanations (SHAP) analysis was used to interpret the prediction results of the LNN model. The LNN model performed best in predicting AP severity, with an AUC value of 0.9659 and accuracy, precision, recall, F1 score, and specificity higher than 0.90. SHAP analysis revealed key predictors, such as calcium level, amylase activity, and percentage of basophils, which were strongly associated with AP severity. As an emerging machine learning tool, the LNN model has demonstrated excellent performance and potential in AP severity prediction. The results of this study support the idea that LNN models can be applied to early severity assessment of AP patients in a clinical setting, which can help optimize treatment plans and improve patient prognosis.

Keywords: Liquid neural network; Machine learning; Predictive models; Severe acute pancreatitis.

Fig. 1

LNN schematic diagram.

Fig. 2

The flow chart of this study.

Fig. 3

Correlation analysis heatmap.

Fig. 4

Plot of AUC values versus number of features under the five models. (A) LR model; (B) DCT model; (C) RF model; (D) XGBoost model; (E) LNN model.

Fig. 5

Comparison of AUC values before and after feature selection under five models. (A) LR model; (B) DCT model; (C) RF model; (D) XGBoost model; (E) LNN model; (F) Comparison bar chart.

Fig. 6

Comparison of AUC values before and after SMOTE oversampling under five models. (A) LR model; (B) DCT model; (C) RF model; (D) XGBoost model; (E) LNN model; (F) Comparison bar chart.

Fig. 7

Loss and accuracy variation plots for training LNN models. (A) Loss variation chart; (B) Accuracy change chart.

Fig. 8

Comparative ROC charts for the five models.

Fig. 9

Comparison of AUC values for three models, LNN, CNN, and LSTM, with different training set proportions. (A) 5% training set; (B) 70% training set.

Fig. 10

LNN-based SHAP analysis graph.