{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:30:30Z","timestamp":1764052230306,"version":"3.45.0"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"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>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study aimed to investigate the effect of gastrointestinal bleeding (GIB) on the short-term survival of hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF) patients, establish a prediction model for HBV-ACLF-related GIB via machine learning (ML) algorithms, and compare the predictive ability of various models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 583 HBV-ACLF patients from two medical centers were retrospectively enrolled, and patients from one of the centers were randomly divided into a training cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f360) and a test cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f153) at a 7:3 ratio. Patients from the other center composed the validation cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f70). Patients were divided into GIB and non-gastrointestinal bleeding (NGIB) groups according to whether they had GIB during hospitalization, and short-term survival rates were compared between the two groups. Least absolute shrinkage and selection operator (LASSO) regression was used to screen for features associated with GIB. On the basis of the screened features, we used five ML algorithms, namely, logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), and K-nearest neighbors (KNN), to build a prediction model for GIB. Six metrics, namely, accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were used to evaluate the predictive ability of these models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the training cohort, patients in the GIB group had significantly lower 30- and 90-day survival rates than did those in the NGIB group (48.72% versus 85.67% and 10.26% versus 64.80%, respectively), and similar results were obtained in the test cohort and the validation cohort. LASSO regression screened seven features associated with GIB, of which portal hypertension, electrolyte disturbance, and white blood cell counts were modeled features common to the five machine prediction models. The AUCs of the LR, SVM, DT, RF, and KNN models in the training cohort were 0.819, 0.924, 0.661, 1.000, and 0.865, respectively. Compared with the other four models, the LR model had the lowest PPV of 0.202 in the test cohort, the SVM model had the lowest AUC and sensitivity of 0.657 and 0.500 in the validation cohort, the DT model had the lowest sensitivity of 0.436 and 0.438 in the training and test cohorts, respectively, and the KNN model had the lowest PPV of 0.250 in the validation cohort. Notably, the RF model had the least fluctuations in accuracy, AUC, sensitivity, specificity, PPV, and NPV among the 3 cohorts, with good overall predictive ability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GIB has a significant effect on short-term survival in patients with HBV-ACLF. On this basis, five ML prediction models, LR, SVM, DT, RF, and KNN, were established to have better prediction ability for GIB, among which the RF model has the most robust prediction performance, which can help clinicians intervene in advance and improve the short-term survival rate of patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1516476","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:27:00Z","timestamp":1764052020000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting the gastrointestinal bleeding of HBV-related acute-on-chronic liver failure based on machine learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Jiwei","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyu","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyu","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuna","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1186\/s12916-020-01814-4","article-title":"The efficacy and safety of methylprednisolone in hepatitis B virus-related acute-on-chronic liver failure: a prospective multi-center clinical trial","volume":"18","author":"Jia","year":"2020","journal-title":"BMC Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/s12072-014-9580-2","article-title":"Acute-on-chronic liver failure: consensus recommendations of the Asian Pacific Association for the Study of the Liver (APASL) 2014","volume":"8","author":"Sarin","year":"2014","journal-title":"Hepatol Int"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1111\/jgh.12454","article-title":"Dexamethasone in outcome of patients with hepatitis B virus-related acute-on-chronic liver failure","volume":"29","author":"Chen","year":"2014","journal-title":"J Gastroenterol Hepatol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"487","DOI":"10.3350\/cmh.2020.0209","article-title":"Acute-on-chronic liver failure: a predictor of poor prognosis in patients with variceal bleeding or a risk factor for variceal bleeding?","volume":"26","author":"Heo","year":"2020","journal-title":"Clin Mol Hepatol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.3760\/cma.j.cn501113-20230604-00243","article-title":"Analysis of the prognosis and survival of patients with acute-on-chronic liver failure","volume":"31","author":"Ma","year":"2023","journal-title":"Zhonghua Gan Zang Bing Za Zhi"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"620","DOI":"10.5152\/tjg.2020.19307","article-title":"Risks and predicting factors of bleeding complications in hepatitis B virus-related acute-on-chronic liver failure","volume":"31","author":"Guo","year":"2020","journal-title":"Turk J Gastroenterol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1080\/17474124.2019.1567329","article-title":"Upper gastrointestinal hemorrhage in acute-on-chronic liver failure: prevalence, characteristics, and impact on prognosis","volume":"13","author":"Zhao","year":"2019","journal-title":"Expert Rev Gastroenterol Hepatol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1055\/a-2107-0576","article-title":"To TIPS or not to TIPS in high risk of variceal rebleeding and acute-on-chronic liver failure","volume":"43","author":"Gu","year":"2023","journal-title":"Semin Liver Dis"},{"key":"ref9","first-page":"3046","article-title":"A clinical prediction model and its application for bleeding in chronic liver failure patients with esophageal varices","volume":"17","author":"Wang","year":"2013","journal-title":"Eur Rev Med Pharmacol Sci"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"E1351","DOI":"10.1503\/cmaj.202434","article-title":"Implementing machine learning in medicine","volume":"193","author":"Verma","year":"2021","journal-title":"CMAJ"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2095","DOI":"10.1016\/j.dld.2024.06.029","article-title":"Predicting the 28-day prognosis of acute-on-chronic liver failure patients based on machine learning","volume":"56","author":"Qiu","year":"2024","journal-title":"Dig Liver Dis"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1908","DOI":"10.1016\/j.ajt.2023.08.022","article-title":"Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using expert-augmented machine learning","volume":"23","author":"Ge","year":"2023","journal-title":"Am J Transplant"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.cmpb.2019.04.012","article-title":"Predicting daily outcomes in acetaminophen-induced acute liver failure patients with machine learning techniques","volume":"175","author":"Speiser","year":"2019","journal-title":"Comput Methods Prog Biomed"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.2147\/JHC.S451025","article-title":"Utility of machine learning in the prediction of post-hepatectomy liver failure in liver cancer","volume":"11","author":"Tashiro","year":"2024","journal-title":"J Hepatocell Carcinoma"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1016\/j.jhep.2023.04.018","article-title":"Biomolecular map of albumin identifies signatures of severity and early mortality in acute liver failure","volume":"79","author":"Sharma","year":"2023","journal-title":"J Hepatol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e0095","DOI":"10.1097\/HC9.0000000000000095","article-title":"Acute on chronic liver failure: prognostic models and artificial intelligence applications","volume":"7","author":"Gary","year":"2023","journal-title":"Hepatol Commun"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s12072-019-09946-3","article-title":"Acute-on-chronic liver failure: consensus recommendations of the Asian Pacific association for the study of the liver (APASL): an update","volume":"13","author":"Sarin","year":"2019","journal-title":"Hepatol Int"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1007\/s00134-022-06802-1","article-title":"Artificial liver support in patients with liver failure: a modified DELPHI consensus of international experts","volume":"48","author":"Saliba","year":"2022","journal-title":"Intensive Care Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"7253","DOI":"10.1109\/TPAMI.2021.3092177","article-title":"Support vector machine classifier via L(0\/1) soft-margin loss","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"121152","DOI":"10.1016\/j.jenvman.2024.121152","article-title":"Decision tree-based approach to extrapolate life cycle inventory data of manufacturing processes","volume":"360","author":"Saad","year":"2024","journal-title":"J Environ Manag"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","first-page":"1774","DOI":"10.1109\/TNNLS.2017.2673241","article-title":"Efficient kNN classification with different numbers of nearest neighbors","volume":"29","author":"Zhang","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.ijrobp.2021.08.007","article-title":"Logistic regression in clinical studies","volume":"112","author":"Zabor","year":"2022","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1111\/liv.12257","article-title":"Cerebral oedema is rare in acute-on-chronic liver failure patients presenting with high-grade hepatic encephalopathy","volume":"34","author":"Joshi","year":"2014","journal-title":"Liver Int"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1016\/j.jhep.2020.04.024","article-title":"Rebleeding and mortality risk are increased by ACLF but reduced by pre-emptive TIPS","volume":"73","author":"Trebicka","year":"2020","journal-title":"J Hepatol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"540","DOI":"10.3350\/cmh.2020.0034","article-title":"Acute-on-chronic liver failure as a major predictive factor for mortality in patients with variceal bleeding","volume":"26","author":"Shin","year":"2020","journal-title":"Clin Mol Hepatol"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","first-page":"863","DOI":"10.17219\/acem\/147464","article-title":"Gastrointestinal hemorrhage as an acute-on-chronic liver failure trigger in cirrhotic patients","volume":"31","author":"Rogalski","year":"2022","journal-title":"Adv Clin Exp Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1186\/s12876-023-02768-6","article-title":"Risk stratification based on acute-on-chronic liver failure in cirrhotic patients hospitalized for acute variceal bleeding","volume":"23","author":"Zhu","year":"2023","journal-title":"BMC Gastroenterol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"349","DOI":"10.3892\/br.2016.727","article-title":"Low hemoglobin levels are associated with upper gastrointestinal bleeding","volume":"5","author":"Tomizawa","year":"2016","journal-title":"Biomed Rep"},{"key":"ref31","first-page":"3385","article-title":"Retrospective analysis of risk factors for non-variceal upper gastrointestinal bleeding and construction of a nomogram prediction model","volume":"15","author":"Yin","year":"2023","journal-title":"Am J Transl Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7754\/Clin.Lab.2019.190927","article-title":"Diagnostic values of blood count values and ratios in distinguishing between peptic ulcer bleeding and esophagogastric variceal bleeding","volume":"66","author":"Zhang","year":"2020","journal-title":"Clin Lab"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"5035","DOI":"10.3748\/wjg.v19.i31.5035","article-title":"Portal hypertension and gastrointestinal bleeding: diagnosis, prevention and management","volume":"19","author":"Biecker","year":"2013","journal-title":"World J Gastroenterol"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1007\/s00330-022-09107-5","article-title":"A novel model based on liver\/spleen volumes and portal vein diameter on MRI to predict variceal bleeding in HBV cirrhosis","volume":"33","author":"Tan","year":"2023","journal-title":"Eur Radiol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.3748\/wjg.v17.i29.3448","article-title":"Survival and prognostic factors in hepatitis B virus-related acute-on-chronic liver failure","volume":"17","author":"Huang","year":"2011","journal-title":"World J Gastroenterol"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1515\/BC.2008.113","article-title":"How Na+ activates thrombin--a review of the functional and structural data","volume":"389","author":"Huntington","year":"2008","journal-title":"Biol Chem"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"101458","DOI":"10.1016\/j.jbc.2021.101458","article-title":"The active site region plays a critical role in Na(+) binding to thrombin","volume":"298","author":"Pelc","year":"2022","journal-title":"J Biol Chem"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1080\/09205063.2018.1481585","article-title":"Calcium content mediated hemostasis of calcium-modified oxidized microporous starch","volume":"29","author":"Yu","year":"2018","journal-title":"J Biomater Sci Polym Ed"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1080\/09537104.2021.1904135","article-title":"Why do platelets express K(+) channels?","volume":"32","author":"Wright","year":"2021","journal-title":"Platelets"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1186\/s12876-025-03677-6","article-title":"Development and evaluation of a predictive model of upper gastrointestinal bleeding in liver cirrhosis","volume":"25","author":"Peng","year":"2025","journal-title":"BMC Gastroenterol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/s12072-020-10053-x","article-title":"Plasma perfusion combined with plasma exchange in chronic hepatitis B-related acute-on-chronic liver failure patients","volume":"14","author":"Yang","year":"2020","journal-title":"Hepatol Int"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1053\/bega.2000.0142","article-title":"Diagnosis, treatment and prevention of spontaneous bacterial peritonitis","volume":"14","author":"Fern\u00e1ndez","year":"2000","journal-title":"Baillieres Best Pract Res Clin Gastroenterol"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"39","DOI":"10.15403\/jgld-4618","article-title":"Outcomes, mortality, and cost burden of acute kidney injury and hepatorenal syndrome in patients with cirrhosis","volume":"32","author":"Patel","year":"2023","journal-title":"J Gastrointestin Liver Dis"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1097\/DCR.0b013e3182837e5b","article-title":"Clinical prediction of pathological complete response after preoperative chemoradiotherapy for rectal cancer","volume":"56","author":"Huh","year":"2013","journal-title":"Dis Colon Rectum"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"16208","DOI":"10.1038\/s41598-024-66979-x","article-title":"Comparative assessment of the capability of machine learning-based radiomic models for predicting omental metastasis in locally advanced gastric cancer","volume":"14","author":"Wu","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1516476\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:27:04Z","timestamp":1764052024000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1516476\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":45,"alternative-id":["10.3389\/fmed.2025.1516476"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1516476","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,25]]},"article-number":"1516476"}}