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 a...

Full description

Saved in:
Bibliographic Details
Main Authors: Jie Cao, Shike Long, Huan Liu, Fu’an Chen, Shiwei Liang, Haicheng Fang, Ying Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01218-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850273436981526528
author Jie Cao
Shike Long
Huan Liu
Fu’an Chen
Shiwei Liang
Haicheng Fang
Ying Liu
author_facet Jie Cao
Shike Long
Huan Liu
Fu’an Chen
Shiwei Liang
Haicheng Fang
Ying Liu
author_sort Jie Cao
collection DOAJ
description 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.
format Article
id doaj-art-84cf2e6ae84f407780b0bf937a815d48
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-84cf2e6ae84f407780b0bf937a815d482025-08-20T01:51:30ZengNature PortfolioScientific Reports2045-23222025-05-0115111910.1038/s41598-025-01218-5Constructing a prediction model for acute pancreatitis severity based on liquid neural networkJie Cao0Shike Long1Huan Liu2Fu’an Chen3Shiwei Liang4Haicheng Fang5Ying Liu6Department of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityGuangxi University Key Laboratory of Unmanned Aircraft System Technology and Application, Guilin University of Aerospace TechnologyDepartment of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityDepartment of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityDepartment of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityDepartment of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityDepartment of Gastroenterology, The Second Affiliated Hospital of Guilin Medical UniversityAbstract 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.https://doi.org/10.1038/s41598-025-01218-5Liquid neural networkSevere acute pancreatitisPredictive modelsMachine learning
spellingShingle Jie Cao
Shike Long
Huan Liu
Fu’an Chen
Shiwei Liang
Haicheng Fang
Ying Liu
Constructing a prediction model for acute pancreatitis severity based on liquid neural network
Scientific Reports
Liquid neural network
Severe acute pancreatitis
Predictive models
Machine learning
title Constructing a prediction model for acute pancreatitis severity based on liquid neural network
title_full Constructing a prediction model for acute pancreatitis severity based on liquid neural network
title_fullStr Constructing a prediction model for acute pancreatitis severity based on liquid neural network
title_full_unstemmed Constructing a prediction model for acute pancreatitis severity based on liquid neural network
title_short Constructing a prediction model for acute pancreatitis severity based on liquid neural network
title_sort constructing a prediction model for acute pancreatitis severity based on liquid neural network
topic Liquid neural network
Severe acute pancreatitis
Predictive models
Machine learning
url https://doi.org/10.1038/s41598-025-01218-5
work_keys_str_mv AT jiecao constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT shikelong constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT huanliu constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT fuanchen constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT shiweiliang constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT haichengfang constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork
AT yingliu constructingapredictionmodelforacutepancreatitisseveritybasedonliquidneuralnetwork