XGBoost model predicts acute lung injury after acute pancreatitis

To develop an XGBoost model to predict the occurrence of acute lung injury (ALI) in patients with acute pancreatitis (AP). Using the case database of Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine, 1231 cases suffering from AP were screened, and after 137 variables were identified, the clinical characteristics of the samples were statistically analyzed, and the data were randomly divided into a training set (75%) to build the XGBoost model and a test set (25%) for validation. Finally, the performance of the model was evaluated based on accuracy, specificity, sensitivity, and subject characteristics working characteristic curves. The model performance is also compared with that of three other commonly used machine learning algorithms (support vector machine (SVM), logistic regression, and random forest). The age and laboratory tests of patients with AP combined with ALI differed from those of patients without combined acute lung injury. The area under the receiver operating characteristic (ROC) curve of the test set after model evaluation was 0.9534, the specificity was 0.7333, and the sensitivity was 0.7857, with arterial partial pressure of oxygen, bile acid, aspartate transaminase, urea nitrogen, and arterial blood pH as its most important influencing factors. In this study, the XGBoost model has advantages compared with other three machine learning algorithms. The XGBoost model has potential in the application of predicting acute lung injury after acute pancreatitis.

Acute pancreatitis; Acute lung injury; XGBoost; Predictive model

[1] GBD 2017 Disease and Injury Incidence and Prevalence Collaborators. Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the global burden of disease study 2017. The Lancet. 2018; 392: 1789–1858.

[2] van Dijk SM, Hallensleben NDL, van Santvoort HC, Fockens P, van Goor H, Bruno MJ, et al. Acute pancreatitis: recent advances through randomised trials. Gut. 2017; 66: 2024–2032.

[3] Steer ML. Relationship between pancreatitis and lung diseases. Respiration Physiology. 2001; 128: 13–16.

[4] Zhou M. Acute lung injury and ARDS in acute pancreatitis: mechanisms and potential intervention. World Journal of Gastroenterology. 2010; 16: 2094.

[5] Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H. EDoctor: machine learning and the future of medicine. Journal of Internal Medicine. 2018; 284: 603–619.

[6] Association PSGotCM. Guidelines for the diagnosis and management of acute pancreatitis in China (2021). Chinese Journal of Practical Surgery. 2021; 41: 739–746.

[7] Chinese Medical Association ICMB. Guidelines for the diagnosis and treatment of acute lung injury/acute respiratory distress syndrome (2006). Chinese Journal of Internal Medicine. 2007; 02: 19–28.

[8] Ge P, Luo Y, Okoye CS, Chen H, Liu J, Zhang G, et al. Intestinal barrier damage, systemic inflammatory response syndrome, and acute lung injury: a troublesome trio for acute pancreatitis. Biomed Pharmacother. 2020; 132: 110770.

[9] Shah J, and Rana SS. Acute respiratory distress syndrome in acute pancreatitis. Indian Journal of Gastroenterology. 2020; 39: 123–132.

[10] Le NQK, Do DT, Chiu FY, Yapp EKY, Yeh HY, Chen CY. XGBoost improves classification of MGMT promoter methylation status in IDH1 wildtype glioblastoma. Journal of Personalized Medicine. 2020; 10: 128.

[11] Liu Y, Mu S, Li X, Liang Y, Wang L, Ma X. Unfractionated heparin alleviates sepsis-induced acute lung injury by protecting tight junctions. Journal of Surgical Research. 2019; 238: 175–185.

[12] Güngör B, Cağlayan K, Polat C, Seren D, Erzurumlu K, Malazgirt Z. The predictivity of serum biochemical markers in acute biliary pancreatitis. ISRN Gastroenterol. 2011; 2011: 279607.

[13] Tran QT, Tran VH, Sendler M, Doller J, Wiese M, Bolsmann R, et al. Role of bile acids and bile salts in acute pancreatitis: from the experimental to clinical studies. Pancreas. 2021; 50: 3–11.

[14] Chen B, Cai H, Xue S, You W, Liu B, Jiang H. Bile acids induce activation of alveolar epithelial cells and lung fibroblasts through farnesoid X receptor-dependent and independent pathways. Respirology. 2016; 21: 1075–1080.

[15] Pando E, Alberti P, Mata R, Gomez MJ, Vidal L, Cirera A, et al. Early changes in blood urea nitrogen (BUN) can predict mortality in acute pancreatitis: comparative study between BISAP score, APACHE-II, and other laboratory markers—a prospective observational study. Canadian Journal of Gastroenterology and Hepatology. 2021; 2021: 6643595.

[16] Nassar TI, and Qunibi WY. AKI associated with acute pancreatitis. Clinical Journal of the American Society of Nephrology. 2019; 14: 1106–1115.

[17] Koutroumpakis E, Wu BU, Bakker OJ, Dudekula A, Singh VK, Besselink MG, et al. Admission hematocrit and rise in blood urea nitrogen at 24 h outperform other laboratory markers in predicting persistent organ failure and pancreatic necrosis in acute pancreatitis: a post hoc analysis of three large prospective databases. The American Journal of Gastroenterology. 2015; 110: 1707–1716.

[18] Zhang W, Zhang M, Kuang Z, Huang Z, Gao L, Zhu J. The risk factors for acute respiratory distress syndrome in patients with severe acute pancreatitis: a retrospective analysis. Medicine. 2021; 100: e23982.