Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 3;25(1):131.
doi: 10.1186/s12876-025-03723-3.

Explainable machine learning model for predicting acute pancreatitis mortality in the intensive care unit

Meng Jiang #  1 , Xiao-Peng Wu #  2 , Xing-Chen Lin  3 , Chang-Li Li  4
Affiliations

Explainable machine learning model for predicting acute pancreatitis mortality in the intensive care unit

Meng Jiang et al. BMC Gastroenterol. .

Abstract

Background: Current prediction models are suboptimal for determining mortality risk in patients with acute pancreatitis (AP); this might be improved by using a machine learning (ML) model. In this study, we aimed to construct an explainable ML model to calculate the risk of mortality in patients with AP admitted in intensive care unit (ICU) and compared it with existing scoring systems.

Methods: A gradient-boosting ML (XGBoost) model was developed and externally validated based on two public databases: Medical Information Mart for Intensive Care (MIMIC, training cohort) and the eICU Collaborative Research Database (eICU-CRD, validation cohort). We compared the performance of the XGBoost model with validated clinical risk scoring systems (the APACHE IV, SOFA, and Bedside Index for Severity in Acute Pancreatitis [BISAP]) by area under receiver operating characteristic curve (AUC) analysis. SHAP (SHapley Additive exPlanations) method was applied to provide the explanation behind the prediction outcome.

Results: The XGBoost model performed better than the clinical scoring systems in correctly predicting mortality risk of AP patients, achieving an AUC of 0.89 (95% CI: 0.84-0.94). When set the sensitivity at 100% for death prediction, the model had a specificity of 38%, much higher than the APACHE IV, SOFA and BISAP score, which had a specificity of 1%, 16% and 1% respectively.

Conclusions: This model might increase identification of very low-risk patients who can be safely monitored in a general ward for management. By making the model explainable, physicians would be able to better understand the reasoning behind the prediction.

Keywords: Acute pancreatitis; Mortality; Prediction; Prognostic factor; XGBoost.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: Since the study was an analysis of the third party anonymized publicly available database with pre-existing institutional review board (IRB) approval, IRB approval from The First Affiliated Hospital of Zhejiang university was waived. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Flow chart of patient selection
Fig. 2
Fig. 2
SHAP summary plot of the top 25 features of the XGBoost model. The higher the SHAP value of a variable, the higher the probability of mortality. A dot is created for each feature attribution value for the model of each patient, and thus one patient is allocated one dot on the line for each variable. Dots are colored according to the values of variables for the respective patient and accumulate vertically to depict density. Red represents higher variable values, and blue represents lower variable values
Fig. 3
Fig. 3
Comparison of AUCs among machine learning models and clinical risk scores. XGBoost yielded the greatest AUC in the external validation cohort
Fig. 4
Fig. 4
SHAP explanation force plot for 3 patients from the eICU-CRD validation cohort of the ML model. ALT, aminotransferase alanine; BUN, blood urea nitrogen; GCS, Glasgow Coma Scale/Score; HR, heart rate; INR, international normalized ratio; MAP, mean arterial pressure; PT, prothrombin time; RR, respiratory rate; SPO2, oxygen saturation; WBC, white blood cell; Na+, sodium; K+, potassium; SBP, systolic blood pressure; RR, respiratory rate; INR, international normalized ratio; DBP, diastolic blood pressure; Scr, serum creatinine; HCT, hematocrit
See this image and copyright information in PMC

References

    1. Li C, Jiang M, Pan C, Li J, Xu L. The global, regional, and National burden of acute pancreatitis in 204 countries and territories, 1990–2019. BMC Gastroenterol. 2021;21(1):332. - PMC - PubMed
    1. Boxhoorn L, Voermans RP, Bouwense SA, Bruno MJ, Verdonk RC, Boermeester MA, et al. Acute pancreatitis. Lancet. 2020;396(10252):726–34. - PubMed
    1. Buter A, Imrie CW, Carter CR, Evans S, McKay CJ. Dynamic nature of early organ dysfunction determines outcome in acute pancreatitis. Brit J Surg. 2002;89(3):298–302. - PubMed
    1. Banks PA, Bollen TL, Dervenis C, Gooszen HG, Johnson CD, Sarr MG, et al. Classification of acute pancreatitis-2012: revision of the Atlanta classification and definitions by international consensus. Gut. 2013;62(1):102–11. - PubMed
    1. Di MY, Liu H, Yang ZY, Bonis PA, Tang JL, Lau J. Prediction models of mortality in acute pancreatitis in adults: A systematic review. Ann Intern Med. 2016;165(7):482–90. - PubMed

LinkOut - more resources