{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T22:37:34Z","timestamp":1783723054501,"version":"3.55.0"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82272226"],"award-info":[{"award-number":["82272226"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Acute upper gastrointestinal bleeding (AUGIB) is one of the most common critical diseases encountered in the intensive care unit (ICU), with a mortality rate ranging from 15 to 20%. Accurate stratification of acute gastrointestinal bleeding into acute variceal gastrointestinal bleeding (AVGIB) and acute non-variceal gastrointestinal bleeding (ANGIB) subtypes is clinically essential as distinct entities require markedly different therapeutic approaches and even divergent prognostic implications. AUGIB characterized by hemorrhagic shock, hypotension, multiple organ dysfunction (MODS), and even circulatory failure is life-threatening. Machine learning (ML) prediction model can be an effective tool for mortality prediction, enabling the timely identification of high-risk patients and improving outcomes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 3,050 acute upper gastrointestinal bleeding (AUGIB) patients were included in our research from the MIMIC-IV database, among which 625 patients were classified as AVGIB and 2,425 patients were categorized as ANGIB. Patients\u2019 clinical features, intervention methods, vital signs, scores, and important laboratory results were collected. The Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors (SMOTE-ENN) and Adaptive Synthetic Sampling (ADASYN) were adopted to address the imbalance of the dataset. As many as 12 machine learning (ML) algorithms, namely, logistic regression (LR), decision tree (DT), random forest (RF), gradient boosting (GB), AdaBoost, XGBoost, Naive Bayes (NB), support vector machine (SVM), light gradient-boosting machine (LightGBM), K-nearest neighbors (KNN), extremely randomized trees (ET), and voting classifier (VC), were performed. The model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Shapley Additive exPlanations (SHAP) analysis was conducted to identify the most influential features contributing to mortality prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In terms of AVGIB patients, extremely randomized trees model demonstrated excellent predictive value among other ML models, with the AUC of 0.996\u202f\u00b1\u202f0.007, accuracy of 0.996\u202f\u00b1\u202f0.009, precision of 0.957\u202f\u00b1\u202f0.024, recall of 0.988\u202f\u00b1\u202f0.012, and F1 score of 0.972\u202f\u00b1\u202f0.007. The top 10 primary feature variables of ET model were whether combined with acute kidney failure, transfusion of albumin, vasoactive drugs, transfusion of plasma, transfusion of platelet, the max of international normalized ratio (INR), the max of prothrombin time (PT), and the max of activated partial thromboplastin time (APTT). In case of ANGIB patients, gradient boosting model proven to be the optimal machine learning models, with the AUC of 0.985\u202f\u00b1\u202f0.002, accuracy of 0.948\u202f\u00b1\u202f0.009, precision of 0.949\u202f\u00b1\u202f0.009, recall of 0.968\u202f\u00b1\u202f0.009, and F1 score of 0.959\u202f\u00b1\u202f0.007. Similarly, the top 10 feature variables of GB model were Glasgow Coma Scale (GCS) score, vasoactive drugs, acute kidney failure, AIMS65 score, APACHE-II score, mechanical ventilation, the minimum of lactate, chronic liver disease, and the minimum and maximum of APTT. The SHAP visualization shows the weights of two ML models feature variables and the average sharp values of variables. Meanwhile, SHAP waterfall outputs the model prediction process with true positive and negative patients. Most importantly, two website prognostic prediction platforms were developed to enhance clinical accessibility: the ET model for AVGIB patients available at <jats:uri>https:\/\/10zr656do5281.vicp.fun<\/jats:uri> while the GB model for ANGIB patients accessible at <jats:uri>http:\/\/10zr656do5281.vicp.fun<\/jats:uri>.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The ET model provides a reliable prognostic tool for AVGIB patients, while the GB model serves as a robust tool for ANGIB patients in predicting in-hospital mortality. By systematically integrating clinical features, risk stratification scores, vital signs, and invention measures, the ML models may deliver comprehensive predictions that benefit for clinical decision-making and potentially enhance clinical outcomes in the near future.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1580094","type":"journal-article","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T05:20:15Z","timestamp":1747372815000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["The future of critical care: AI-powered mortality prediction for acute variceal gastrointestinal bleeding and acute non-variceal gastrointestinal bleeding patients"],"prefix":"10.3389","volume":"12","author":[{"given":"Zhou","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guijun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Palpasa","family":"Shrestha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yugang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanguo","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liying","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,16]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.cger.2020.09.001","article-title":"Upper gastrointestinal bleeding","volume":"37","author":"Costable","year":"2021","journal-title":"Clin Geriatr Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1097\/MCC.0000000000000699","article-title":"Management of severe upper gastrointestinal bleeding in the Icu","volume":"26","author":"Al Duhailib","year":"2020","journal-title":"Curr Opin Crit Care"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"899","DOI":"10.14309\/ajg.0000000000001245","article-title":"Acg clinical guideline: upper gastrointestinal and ulcer bleeding","volume":"116","author":"Laine","year":"2021","journal-title":"Am J Gastroenterol"},{"key":"ref4","first-page":"294","article-title":"Upper gastrointestinal bleeding in adults: evaluation and management","volume":"101","author":"Wilkins","year":"2020","journal-title":"Am Fam Physician"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"a1","DOI":"10.1055\/s-0034-1393172","article-title":"Diagnosis and management of nonvariceal upper gastrointestinal hemorrhage: European Society of Gastrointestinal Endoscopy (Esge) guideline","volume":"47","author":"Gralnek","year":"2015","journal-title":"Endoscopy"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"14515","DOI":"10.3748\/wjg.v20.i39.14515","article-title":"Aims65: a promising upper gastrointestinal bleeding risk score but further validation required","volume":"20","author":"Boyapati","year":"2014","journal-title":"World J Gastroenterol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.3904\/kjim.2022.099","article-title":"Clinical outcomes of acute upper gastrointestinal bleeding according to the risk indicated by Glasgow-Blatchford risk score-computed tomography score in the emergency room","volume":"37","author":"Lee","year":"2022","journal-title":"Korean J Intern Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"i6432","DOI":"10.1136\/bmj.i6432","article-title":"Comparison of risk scoring systems for patients presenting with upper gastrointestinal bleeding: international multicentre prospective study","volume":"356","author":"Stanley","year":"2017","journal-title":"BMJ"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1136\/postgradmedj-2021-140376","article-title":"Cohort study of the Apache ii score and mortality for different types of intensive care unit patients","volume":"98","author":"Sungono","year":"2022","journal-title":"Postgrad Med J"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"10760296231207806","DOI":"10.1177\/10760296231207806","article-title":"Development and validation of a risk prediction model for in-hospital mortality in patients with acute upper gastrointestinal bleeding","volume":"29","author":"Yuan","year":"2023","journal-title":"Clin Appl Thromb Hemost"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3000605221086442","DOI":"10.1177\/03000605221086442","article-title":"Prediction of in-hospital mortality after acute upper gastrointestinal bleeding: cross-validation of several risk scoring systems","volume":"50","author":"Benedeto-Stojanov","year":"2022","journal-title":"J Int Med Res"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1134835","DOI":"10.3389\/fmed.2023.1134835","article-title":"Predicting mortality in patients with nonvariceal upper gastrointestinal bleeding using machine-learning","volume":"10","author":"Ungureanu","year":"2023","journal-title":"Front Med (Lausanne)"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial intelligence in healthcare: past, present and future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc Neurol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e31543","DOI":"10.1097\/MD.0000000000031543","article-title":"Acute gastrointestinal bleeding: a comparison between variceal and nonvariceal gastrointestinal bleeding","volume":"101","author":"Ra\u0163iu","year":"2022","journal-title":"Medicine (Baltimore)"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"Mimic-iv, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1111\/j.1553-2712.2011.01185.x","article-title":"Logistic regression: a brief primer","volume":"18","author":"Stoltzfus","year":"2011","journal-title":"Acad Emerg Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1023\/A:1016409317640","article-title":"Decision trees: an overview and their use in medicine","volume":"26","author":"Podgorelec","year":"2002","journal-title":"J Med Syst"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"bbad002","DOI":"10.1093\/bib\/bbad002","article-title":"A review on longitudinal data analysis with random forest","volume":"24","author":"Hu","year":"2023","journal-title":"Brief Bioinform"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"152","DOI":"10.21037\/atm.2019.03.29","article-title":"Predictive analytics with gradient boosting in clinical medicine","volume":"7","author":"Zhang","year":"2019","journal-title":"Ann Transl Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"5371","DOI":"10.1109\/TIP.2022.3195642","article-title":"Adaptive boosting for domain adaptation: toward robust predictions in scene segmentation","volume":"31","author":"Zheng","year":"2022","journal-title":"IEEE Trans Image Process"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"106466","DOI":"10.1016\/j.compbiomed.2022.106466","article-title":"An explainable knowledge distillation method with Xgboost for Icu mortality prediction","volume":"152","author":"Liu","year":"2023","journal-title":"Comput Biol Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.3390\/e23121703","article-title":"Exact learning augmented naive Bayes classifier","volume":"23","author":"Sugahara","year":"2021","journal-title":"Entropy (Basel)"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1016\/j.ajodo.2023.08.003","article-title":"Support vector machines","volume":"164","author":"Valkenborg","year":"2023","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1080\/01443615.2021.1945006","article-title":"Lightgbm: an efficient and accurate method for predicting pregnancy diseases","volume":"42","author":"Liao","year":"2022","journal-title":"J Obstet Gynaecol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1176935120965542","DOI":"10.1177\/1176935120965542","article-title":"Robust distance measures for knn classification of Cancer data","volume":"19","author":"Ehsani","year":"2020","journal-title":"Cancer Informat"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"6755","DOI":"10.1109\/TNNLS.2022.3212859","article-title":"Online extra trees Regressor","volume":"34","author":"Martiello Mastelini","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"179317","DOI":"10.1109\/ACCESS.2020.3028012","article-title":"Novel feature selection and voting classifier algorithms for Covid-19 classification in Ct images","volume":"8","author":"El-Kenawy","year":"2020","journal-title":"IEEE Access"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"117821","DOI":"10.1016\/j.watres.2021.117821","article-title":"Improving the performance of machine learning models for early warning of harmful algal blooms using an adaptive synthetic sampling method","volume":"207","author":"Kim","year":"2021","journal-title":"Water Res"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1186\/s12911-022-02075-2","article-title":"A hybrid sampling algorithm combining synthetic minority over-sampling technique and edited nearest neighbor for missed abortion diagnosis","volume":"22","author":"Yang","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1093\/ndt\/gfad191","article-title":"A nomogram predicting the histologic activity of lupus nephritis from clinical parameters","volume":"39","author":"Gao","year":"2024","journal-title":"Nephrol Dial Transplant"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e38082","DOI":"10.2196\/38082","article-title":"Predicting mortality in intensive care unit patients with heart failure using an interpretable machine learning model: retrospective cohort study","volume":"24","author":"Li","year":"2022","journal-title":"J Med Internet Res"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1007\/s11596-023-2748-z","article-title":"A nomogram model for prediction of mortality risk of patients with dangerous upper gastrointestinal bleeding: a two-center retrospective study","volume":"43","author":"Liu","year":"2023","journal-title":"Curr Med Sci"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.amjms.2024.01.012","article-title":"Risk factors for massive gastrointestinal bleeding occurrence and mortality: a prospective single-center study","volume":"367","author":"Redondo-Cerezo","year":"2024","journal-title":"Am J Med Sci"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.3760\/cma.j.cn121430-20200520-00395","article-title":"Comparative study on clinical effect of multidisciplinary treatment model and traditional consultation model in treatment of dangerous upper gastrointestinal hemorrhage","volume":"32","author":"Zhang","year":"2020","journal-title":"Zhonghua Wei Zhong Bing Ji Jiu Yi Xue"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1136\/gutjnl-2020-323054","article-title":"Timing of endoscopy for acute upper gastrointestinal bleeding: a territory-wide cohort study","volume":"71","author":"Guo","year":"2022","journal-title":"Gut"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"6985","DOI":"10.3748\/wjg.v27.i40.6985","article-title":"Prophylactic transcatheter arterial embolization reduces rebleeding in non-variceal upper gastrointestinal bleeding: a meta-analysis","volume":"27","author":"Boros","year":"2021","journal-title":"World J Gastroenterol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"310","DOI":"10.5114\/ait.2022.120741","article-title":"Comparison of risk scoring systems for critical care patients with upper gastrointestinal bleeding: predicting mortality and length of stay","volume":"54","author":"Lincoln","year":"2022","journal-title":"Anaesthesiol Intensive Ther"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/j.gie.2022.03.019","article-title":"Adding the analysis or discussion to the Apache ii score may clearly explain the predictive risk associated with upper gastrointestinal bleeding via the re.Co.De score","volume":"96","author":"Deng","year":"2022","journal-title":"Gastrointest Endosc"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1111\/jgh.14147","article-title":"Comparison of clinical outcomes between variceal and non-variceal gastrointestinal bleeding in patients with cirrhosis","volume":"33","author":"Tandon","year":"2018","journal-title":"J Gastroenterol Hepatol"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"e202219170","DOI":"10.1002\/anie.202219170","article-title":"Science-driven atomistic machine learning","volume":"62","author":"Margraf","year":"2023","journal-title":"Angew Chem Int Ed Eng"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1111\/jgh.15560","article-title":"Development of a machine learning model to predict bleed in esophageal varices in compensated advanced chronic liver disease: a proof of concept","volume":"36","author":"Agarwal","year":"2021","journal-title":"J Gastroenterol Hepatol"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"e67346","DOI":"10.2196\/67346","article-title":"Risk factors for gastrointestinal bleeding in patients with acute myocardial infarction: multicenter retrospective cohort study","volume":"27","author":"Kou","year":"2025","journal-title":"J Med Internet Res"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"105049","DOI":"10.1016\/j.ijmedinf.2023.105049","article-title":"Machine learning prediction models and nomogram to predict the risk of in-hospital death for severe Dka: a clinical study based on Mimic-iv, eicu databases, and a college hospital Icu","volume":"174","author":"Xie","year":"2023","journal-title":"Int J Med Inform"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1053\/j.gastro.2023.10.016","article-title":"Aga clinical practice update on the use of vasoactive drugs and intravenous albumin in cirrhosis: expert review","volume":"166","author":"Garcia-Tsao","year":"2024","journal-title":"Gastroenterology"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.ajem.2024.04.052","article-title":"Emergency medicine updates: upper gastrointestinal bleeding","volume":"81","author":"Long","year":"2024","journal-title":"Am J Emerg Med"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"4219","DOI":"10.3748\/wjg.v22.i16.4219","article-title":"Predictors of poor outcome in gastrointestinal bleeding in emergency department","volume":"22","author":"Kaya","year":"2016","journal-title":"World J Gastroenterol"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1016\/j.gie.2011.06.024","article-title":"A simple risk score accurately predicts in-hospital mortality, length of stay, and cost in acute upper Gi bleeding","volume":"74","author":"Saltzman","year":"2011","journal-title":"Gastrointest Endosc"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1186\/s12876-019-1051-8","article-title":"Aims65 scoring system is comparable to Glasgow-Blatchford score or Rockall score for prediction of clinical outcomes for non-variceal upper gastrointestinal bleeding","volume":"19","author":"Kim","year":"2019","journal-title":"BMC Gastroenterol"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"542","DOI":"10.14309\/ajg.0000000000001627","article-title":"American College of Gastroenterology-Canadian Association of Gastroenterology clinical practice guideline: Management of Anticoagulants and Antiplatelets during Acute Gastrointestinal Bleeding and the Periendoscopic period","volume":"117","author":"Abraham","year":"2022","journal-title":"Am J Gastroenterol"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1186\/s12871-022-01933-w","article-title":"In-hospital mortality and SpO2 incritical care patients with cerebral injury: data from the Mimic-iv database","volume":"22","author":"Yin","year":"2022","journal-title":"BMC Anesthesiol"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1016\/S0735-6757(97)90178-9","article-title":"Arterial oxygen desaturation during emergent nonsedated upper gastrointestinal endoscopy in the emergency department","volume":"15","author":"Yen","year":"1997","journal-title":"Am J Emerg Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1580094\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T05:20:17Z","timestamp":1747372817000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1580094\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,16]]},"references-count":51,"alternative-id":["10.3389\/fmed.2025.1580094"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1580094","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,16]]},"article-number":"1580094"}}