Machine Learning-Based Predictive Model for Acute Pancreatitis-Associated Lung Injury: A Retrospective Analysis

Qiang Tang^1*Zhaohui Du²Qiaoling Ying²Huicong Ma²Hongchang Zhao²Jie Yang²Zhenjie Wang²Chuanming Zheng²Shurui Wang¹Yisen Yang³

• ¹Cancer Institute, Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China
• ²The First Affiliated Hospital of Bengbu Medical University, Bengbu, China
• ³Chinese Academy of Medical Sciences and Peking Union Medical College Institute of Basic Medical Sciences, Beijing, China

Background: Acute Pancreatitis-Associated Lung Injury (APALI) is one of the most severe and life-threatening systemic complications in acute pancreatitis patients, with high rates of morbidity and mortality. This study aims to develop a prediction model for the diagnosis of APALI based on machine learning algorithms. Methods: This study included data from the First Affiliated Hospital of Bengbu Medical College (July 2012 to June 2022), which were randomly categorized into the training and testing set. And data from the Second Affiliated Hospital of Zhejiang University (January 2018 to April 2023) served as the external validation set. LASSO regression was applied to eliminate irrelevant or highly collinear independent variables. Six machine learning models were constructed, with evaluation metrics including Area Under Curve (AUC), accuracy, sensitivity, specificity, F1 score, and recall. The impact of model features was analyzed using SHapley Additive exPlanations (SHAP). Results: A total of 1,975 patients with acute pancreatitis were randomly assigned to a training set (1,480 patients) and a testing set (495 patients). In the training set, 480 cases (32.43%) were diagnosed with APALI. The eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) models demonstrated the best predictive performance, achieving the highest AUC (0.92 and 0.914, respectively), along with higher accuracy, F1 score, and recall in the testing set. Six particularly influential factors were identified and ranked as follows: CRP, BMI, neutrophil, calcium, lactate, and neutrophil-to-albumin ratio (NAR). The global interpretability of the XGBoost and RF models, along with these six features, is shown in the SHAP summary plot. These two models were selected as the optimal models for the development of an online calculator for clinical applications and risk stratification. Conclusion: We developed and internally validated a machine learning model to predict APALI, showing strong performance in our study population. To support further research and clinical use, we created an open-access web-based risk calculator. Prospective multicenter validation is needed to confirm generalizability. If successful, the tool may support early risk identification and guide interventions to prevent APALI.