• Improved early prediction of a...

Treffer: Improved early prediction of acute pancreatitis severity using SHAP-based XGBoost model: Beyond traditional scoring systems.

Title:
Improved early prediction of acute pancreatitis severity using SHAP-based XGBoost model: Beyond traditional scoring systems.
Authors:
Cisnal A; Institute of Advanced Production Technologies, School of Industrial Engineering, University of Valladolid, Paseo Prado de la Magdalena 3-5, 47011, Valladolid Spain. Electronic address: ana.cisnal@uva.es., Ruiz Rebollo ML; Department of Digestive Diseases, Hospital Clínico Universitario. Valladolid, Avda. Ramón y Cajal 3, 47005 Valladolid, Spain., Flórez-Pardo C; Department of Digestive Diseases, Hospital Clínico Universitario. Valladolid, Avda. Ramón y Cajal 3, 47005 Valladolid, Spain., Matesanz-Isabel J; Institute of Health Sciences of Castilla y León (IECSCYL), Research Unit. Hospital Clínico Universitario. Avda. Ramón y Cajal 3, 47005 Valladolid, Spain., Pérez Turiel J; Institute of Advanced Production Technologies, School of Industrial Engineering, University of Valladolid, Paseo Prado de la Magdalena 3-5, 47011, Valladolid Spain., Fraile JC; Institute of Advanced Production Technologies, School of Industrial Engineering, University of Valladolid, Paseo Prado de la Magdalena 3-5, 47011, Valladolid Spain.
Source:
Digestive and liver disease : official journal of the Italian Society of Gastroenterology and the Italian Association for the Study of the Liver [Dig Liver Dis] 2026 Jan; Vol. 58 (1), pp. 104-112. Date of Electronic Publication: 2025 Nov 07.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Elsevier Country of Publication: Netherlands NLM ID: 100958385 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1878-3562 (Electronic) Linking ISSN: 15908658 NLM ISO Abbreviation: Dig Liver Dis Subsets: MEDLINE
Imprint Name(s):
Publication: 2003- : Amsterdam : Elsevier
Original Publication: Roma, Italy : Editrice gastroenterologica italiana, c2000-
MeSH Terms:
Pancreatitis*/diagnosis , Severity of Illness Index* , Machine Learning*, Humans ; Retrospective Studies ; Male ; Female ; Middle Aged ; ROC Curve ; Adult ; Aged ; Acute Disease ; Predictive Value of Tests ; Early Diagnosis ; Boosting Machine Learning Algorithms
Contributed Indexing:
Keywords: Acute pancreatitis; Clinical decision support; Machine learning; Severity prediction
Entry Date(s):
Date Created: 20251108 Date Completed: 20260121 Latest Revision: 20260121
Update Code:
20260122
DOI:
10.1016/j.dld.2025.10.017
PMID:
41206321
Database:
MEDLINE

Weitere Informationen

Background: Acute pancreatitis (AP) progresses to severe forms in about 20 % of cases, leading to high morbidity and mortality. Traditional clinical scoring systems for severity prediction (e.g., Ranson, BISAP), are limited by delayed applicability, and suboptimal diagnostic accuracy.
Aims: To develop and validate machine learning (ML) models for early prediction of moderately severe and severe acute pancreatitis (MSAP-SAP), and to compare them with conventional scores.
Methods: A retrospective cohort of 816 patients (2014-2023) was analyzed. ML models were developed using admission (24-hour) and early (48-hour) data. Models were trained and tested using an 80:20 stratified split and evaluated based on ROC-AUC. F-Anova, Mutual Information and SHapley Additive exPlanations (SHAP) were used for feature selection. SHAP was also used for model interpretability.
Results: The XGBoost model with SHAP-based feature selection (XGB <sup>SH</sup> ) achieved the highest predictive performance with ROC-AUCs of 0.89 (24-hour) and 0.94 (48-hour) on the test cohort. Key predictive features included SIRS, BUN, CRP, creatinine, and pleural effusion. Compared to Ranson and BISAP (both ROC-AUC = 0.72), the XGB <sup>SH</sup> models demonstrated superior accuracy and allowed flexible, threshold-based classification.
Conclusion: The proposed SHAP-enhanced XGBoost model offers a reliable and interpretable tool for early prediction of AP severity, improving clinical decision-making and patient management.
(Copyright © 2025 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Declaration of competing interest The authors declare that they have no conflicts of interest related to the content of this manuscript. No financial, personal, or professional relationships have influenced the conduct or reporting of this research.