{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T13:50:16Z","timestamp":1778939416760,"version":"3.51.4"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T00:00:00Z","timestamp":1753056000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Acute pancreatitis (AP) in the intensive care unit (ICU) is linked to elevated in-hospital mortality rates. Timely identification of high-risk patients remains challenging. This study aimed to develop an interpretable machine learning model for predicting in-hospital mortality in ICU patients with AP and to identify key contributing factors.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A retrospective analysis was performed on 306 ICU patients diagnosed with AP. After data preprocessing and feature selection via the Least Absolute Shrinkage and Selection Operator (LASSO), seven machine learning models were developed: decision tree, random forest, XGBoost, support vector machine (SVM), multilayer perceptron, k-nearest neighbors (KNN), and logistic regression. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), Brier score, calibration plots, and decision curve analysis (DCA). The SHapley Additive exPlanations (SHAP) framework was utilized to interpret model predictions and assess feature importance rankings.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Multivariate logistic regression analysis identified the following independent risk factors for in-hospital mortality in ICU patients with AP: acute physiology and chronic health evaluation (APACHE II) score, activated partial thromboplastin time (APTT), albumin (Alb), blood urea nitrogen (BUN), creatinine (Cr), use of vasoactive agents, and ICU length of stay. The AUC values for the seven machine learning models in the training set were DT (0.947), RF (0.900), XGBoost (0.887), SVM (0.901), MLP (0.837), KNN (0.983), and LR (0.876). In the validation set, the corresponding AUC values were DT (0.698), RF (0.850), XGBoost (0.878), SVM (0.892), MLP (0.822), KNN (0.755), and LR (0.858). Although DT and KNN demonstrated high sensitivity and specificity in the training set, their performance was suboptimal in the validation set. SHAP analysis ranked APACHE II score as the most influential predictor of mortality.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>An interpretable SVM model incorporating routinely available clinical variables effectively predicts in-hospital mortality in ICU patients with AP. SHAP-enhanced interpretation highlights key predictors and enhances model transparency, supporting clinical decision-making.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1592051","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T11:04:27Z","timestamp":1753095867000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Predicting mortality in intensive care unit patients with acute pancreatitis using an interpretable machine learning model"],"prefix":"10.3389","volume":"12","author":[{"given":"Li","family":"Zhuangli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Xingcheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Xiaoli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Zhonghua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1016\/s0140-6736(20)31310-6","article-title":"Acute pancreatitis","volume":"396","author":"Boxhoorn","year":"2020","journal-title":"Lancet"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.1002\/bjs.9665","article-title":"Meta-analysis of gut barrier dysfunction in patients with acute pancreatitis","volume":"101","author":"Wu","year":"2014","journal-title":"Br J Surg"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1177\/2050640618764049","article-title":"Risk factors and outcomes of infected pancreatic necrosis: retrospective cohort of 148 patients admitted to the ICU for acute pancreatitis","volume":"6","author":"Garret","year":"2018","journal-title":"United European Gastroenterol J"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1080\/17474124.2021.1924058","article-title":"Ranson score to stratify severity in acute pancreatitis remains valid - old is gold","volume":"15","author":"Ong","year":"2021","journal-title":"Expert Rev Gastroenterol Hepatol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ijsu.2018.04.026","article-title":"Evaluation of the BISAP scoring system in prognostication of acute pancreatitis - a prospective observational study","volume":"54","author":"Hagjer","year":"2018","journal-title":"Int J Surg"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"152","DOI":"10.4103\/ijri.IJRI_300_16","article-title":"Severity assessment of acute pancreatitis using CT severity index and modified CT severity index: correlation with clinical outcomes and severity grading as per the revised Atlanta classification","volume":"27","author":"Sahu","year":"2017","journal-title":"Indian J Radiol Imaging"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1093\/gastro\/gox029","article-title":"A comparison of APACHE II, BISAP, Ranson's score and modified CTSI in predicting the severity of acute pancreatitis based on the 2012 revised Atlanta classification","volume":"6","author":"Kumar","year":"2018","journal-title":"Gastroenterol Rep"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1167\/tvst.9.2.14","article-title":"Introduction to machine learning, neural networks, and deep learning","volume":"9","author":"Choi","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e740","DOI":"10.1002\/ams2.740","article-title":"Artificial intelligence and machine learning in emergency medicine: a narrative review","volume":"9","author":"Mueller","year":"2022","journal-title":"Acute Med Surg"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1111\/jgh.15384","article-title":"Opening the black box of AI-medicine","volume":"36","author":"Poon","year":"2021","journal-title":"J Gastroenterol Hepatol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/s2213-2600(18)30425-9","article-title":"Opening the black box of machine learning","volume":"6","year":"2018","journal-title":"Lancet Respir Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12874-022-01540-w","article-title":"Comparative analysis of explainable machine learning prediction models for hospital mortality","volume":"22","author":"Stenwig","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e842","DOI":"10.1002\/ctm2.842","article-title":"EASY-APP: an artificial intelligence model and application for early and easy prediction of severity in acute pancreatitis","volume":"12","author":"Kui","year":"2022","journal-title":"Clin Transl Med"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1097\/mpa.0000000000000957","article-title":"Comparison of various scoring systems and biochemical markers in predicting the outcome in acute pancreatitis","volume":"47","author":"Vasudevan","year":"2018","journal-title":"Pancreas"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.23812\/20-362-l","article-title":"Effects of ulinastatin combined with octreotide on blood coagulation function, inflammatory factors and amylase in patients with severe acute pancreatitis","volume":"34","author":"Li","year":"2020","journal-title":"J Biol Regul Homeost Agents"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.3390\/diagnostics13142361","article-title":"Acute kidney injury in liver cirrhosis","volume":"13","author":"Attieh","year":"2023","journal-title":"Diagnostics"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1076121","DOI":"10.3389\/fimmu.2022.1076121","article-title":"Association between lactate-to-albumin ratio and 28-days all-cause mortality in patients with acute pancreatitis: a retrospective analysis of the MIMIC-IV database","volume":"13","author":"Liu","year":"2022","journal-title":"Front Immunol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1186\/cc13991","article-title":"Albumin administration in the acutely ill: what is new and where next?","volume":"18","author":"Vincent","year":"2014","journal-title":"Crit Care"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12876-023-02801-8","article-title":"Albumin infusion may decrease the mortality of hypoalbuminemia patients with severe acute pancreatitis: a retrospective cohort study","volume":"23","author":"Xu","year":"2023","journal-title":"BMC Gastroenterol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1097\/MPA.0b013e318273066b","article-title":"Effect of serum from patients with severe acute pancreatitis on vascular endothelial permeability","volume":"42","author":"Zheng","year":"2013","journal-title":"Pancreas"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.3390\/ijms20153714","article-title":"Potential prognostic markers of acute kidney injury in the early phase of acute pancreatitis","volume":"20","author":"Wajda","year":"2019","journal-title":"Int J Mol Sci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1186\/s12876-022-02490-9","article-title":"Identification of early predictors for infected necrosis in acute pancreatitis","volume":"22","author":"Wiese","year":"2022","journal-title":"BMC Gastroenterol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/ajg.2008.66","article-title":"Elevated serum creatinine as a marker of pancreatic necrosis in acute pancreatitis","volume":"104","author":"Muddana","year":"2009","journal-title":"Am J Gastroenterol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1038\/ajg.2013.218","article-title":"American College of Gastroenterology guideline: management of acute pancreatitis","volume":"108","author":"Tenner","year":"2013","journal-title":"Am J Gastroenterol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.2215\/cjn.13191118","article-title":"AKI associated with acute pancreatitis","volume":"14","author":"Nassar","year":"2019","journal-title":"Clin J Am Soc Nephrol"},{"key":"ref26","first-page":"383","article-title":"Preventive strategies for septic complications of acute pancreatitis","volume":"102","author":"Ol\u00e1h","year":"2007","journal-title":"Chirurgia"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1007\/s10620-022-07618-1","article-title":"Effect of Synbiotics in reducing the systemic inflammatory response and septic complications in moderately severe and severe acute pancreatitis: a prospective parallel-arm double-blind randomized trial","volume":"68","author":"Rohith","year":"2023","journal-title":"Dig Dis Sci"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1592051\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T11:04:28Z","timestamp":1753095868000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1592051\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,21]]},"references-count":27,"alternative-id":["10.3389\/fmed.2025.1592051"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1592051","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,21]]},"article-number":"1592051"}}