{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T06:12:36Z","timestamp":1788502356835,"version":"build-2803163510"},"reference-count":50,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"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. Cardiovasc. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early risk stratification for in-hospital mortality remains challenging in intensive care unit (ICU) patients with heart failure (HF) because of substantial clinical heterogeneity and complex pathophysiological interactions. Explainable machine learning (ML) may offer a practical and transparent approach to prognostic assessment in this high-risk population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective dual-cohort study included 18,526 ICU patients with HF from the MIMIC-IV database (2008\u20132022) as the development cohort and 314 consecutive ICU patients with HF from an independent hospital-based cohort from August 1, 2023, to May 31, 2026, as the external validation cohort. Candidate predictors available within 24\u2005h of ICU admission were screened using the Boruta algorithm and least absolute shrinkage and selection operator regression. Five ML algorithms were developed in the development cohort and compared using 5-fold nested cross-validation for internal validation. Model interpretability was assessed using Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Nine routinely available predictors were retained for final model development. Among the candidate algorithms, Extreme Gradient Boosting (XGBoost) showed the most balanced overall performance and was selected as the final model. In internal validation using nested cross-validation, the XGBoost model achieved the highest validation area under the receiver operating characteristic curve (AUC), at 0.704 (95% CI 0.682\u20130.726). In the external validation cohort, the final model achieved an AUC of 0.877 (95% CI 0.820\u20130.933) and a Brier score of 0.079 (95% CI 0.061\u20130.099). However, this apparently stronger discrimination should be interpreted cautiously in light of cohort differences and the limited number of external events. SHAP analysis identified blood urea nitrogen, age, and white blood cell count as the most influential predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An explainable XGBoost-based model using nine routinely available early clinical variables showed promising performance for predicting in-hospital all-cause mortality in ICU patients with HF. This interpretable tool may support early risk stratification and individualized clinical management in critically ill patients with HF. Further large multicenter external validation is warranted.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2026.1942393","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T05:29:31Z","timestamp":1788499771000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and external validation of an explainable machine learning model for in-hospital mortality risk stratification in intensive care unit patients with heart failure"],"prefix":"10.3389","volume":"13","author":[{"given":"Liusheng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory, The Second People\u2019s Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Urology, The Second People\u2019s Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zefan","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Reproductive Medicine, Medical School, Nantong University","place":["Nantong, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kefeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The Second People\u2019s Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Fang","sequence":"additional","affiliation":[{"name":"The First Clinical College, Xuzhou Medical University","place":["Xuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, The Affiliated Hospital of Jiangsu University","place":["Zhenjiang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The Second People\u2019s Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongbao","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, The Second People\u2019s Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University","place":["Changzhou, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3272","DOI":"10.1093\/cvr\/cvac013","article-title":"Global burden of heart failure: a comprehensive and updated review of epidemiology","volume":"118","author":"Savarese","year":"2023","journal-title":"Cardiovasc Res"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3627","DOI":"10.1093\/eurheartj\/ehad195","article-title":"2023 Focused update of the 2021 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure","volume":"44","author":"McDonagh","year":"2023","journal-title":"Eur Heart J"},{"key":"B3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s12933-025-02577-z","article-title":"Predicting 28-day all-cause mortality in patients admitted to intensive care units with Pre-existing chronic heart failure using the stress hyperglycemia ratio: a machine learning-driven retrospective cohort analysis","volume":"24","author":"Li","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s00125-021-05637-7","article-title":"Metabolic, structural and biochemical changes in diabetes and the development of heart failure","volume":"65","author":"Ho","year":"2022","journal-title":"Diabetologia"},{"key":"B5","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s00395-025-01153-6","article-title":"From kidney injury to cardiac dysfunction: the central role of oxidative stress in diabetes and Ckd","volume":"121","author":"Sen","year":"2026","journal-title":"Basic Res Cardiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1186\/s12872-026-05943-1","article-title":"Early prediction of in-hospital mortality in ICU patients with heart failure using an interpretable machine learning model: a retrospective study based on MIMIC-IV","volume":"26","author":"Sun","year":"2026","journal-title":"BMC Cardiovasc Disord"},{"key":"B7","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1186\/s12933-024-02503-9","article-title":"Machine learning for predicting in-hospital mortality in elderly patients with heart failure combined with hypertension: a multicenter retrospective study","volume":"23","author":"Liu","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"994359","DOI":"10.3389\/fcvm.2022.994359","article-title":"Interpretable machine learning for 28-day all-cause in-hospital mortality prediction in critically ill patients with heart failure combined with hypertension: a retrospective cohort study based on medical information mart for intensive care database-iv and eicu databases","volume":"9","author":"Peng","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1002\/ejhf.3347","article-title":"Diabetic myocardial disorder. A clinical consensus statement of the Heart Failure Association of the ESC and the ESC Working Group on myocardial & pericardial diseases","volume":"26","author":"Seferovi\u0107","year":"2024","journal-title":"Eur J Heart Fail"},{"key":"B10","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1146\/annurev-pathmechdis-111523-023405","article-title":"Contributions of inflammation to cardiometabolic heart failure with preserved ejection fraction","volume":"20","author":"Thorp","year":"2025","journal-title":"Annu Rev Pathol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"3444","DOI":"10.1002\/ehf2.15361","article-title":"Immuno-Haemostatic dysregulation in heart failure with preserved ejection fraction","volume":"12","author":"D'Italia","year":"2025","journal-title":"ESC Heart Fail"},{"key":"B12","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1186\/s12933-023-02047-4","article-title":"Association between triglyceride glucose-body mass and one-year all-cause mortality of patients with heart failure: a retrospective study utilizing the MIMIC-IV database","volume":"22","author":"Dou","year":"2023","journal-title":"Cardiovasc Diabetol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e029124","DOI":"10.1161\/JAHA.122.029124","article-title":"Machine learning for mortality prediction in patients with heart failure with mildly reduced ejection fraction","volume":"12","author":"Tian","year":"2023","journal-title":"J Am Heart Assoc"},{"key":"B14","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1093\/eurjpc\/zwaf081","article-title":"Advanced prediction of heart failure risk in elderly diabetic and hypertensive patients using nine machine learning models and novel composite indices: insights from nhanes 2003\u20132016","volume":"33","author":"Bai","year":"2026","journal-title":"Eur J Prev Cardiol"},{"key":"B15","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":"B16","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1038\/s41746-025-02296-5","article-title":"A transformer-based survival model for prediction of all-cause mortality in patients with heart failure: a multi-cohort study","volume":"9","author":"Rao","year":"2026","journal-title":"NPJ Digit Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"812276","DOI":"10.3389\/fcvm.2022.812276","article-title":"Comparing machine learning models and statistical models for predicting heart failure events: a systematic review and meta-analysis","volume":"9","author":"Sun","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"950338","DOI":"10.3389\/fnut.2022.950338","article-title":"Triglyceride glucose Index and its combination with the get with the guidelines-heart failure score in predicting the prognosis in patients with heart failure","volume":"9","author":"Han","year":"2022","journal-title":"Front Nutr"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e046156","DOI":"10.1161\/JAHA.125.046156","article-title":"Development and validation of a machine learning model for incident heart failure prediction in chronic kidney disease: a multicenter cohort study","volume":"15","author":"Lu","year":"2026","journal-title":"J Am Heart Assoc"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e370","DOI":"10.1016\/S2589-7500(23)00065-1","article-title":"Identifying subtypes of heart failure from three electronic health record sources with machine learning: an external, prognostic, and genetic validation study","volume":"5","author":"Banerjee","year":"2023","journal-title":"Lancet Digit Health"},{"key":"B21","doi-asserted-by":"publisher","first-page":"18671","DOI":"10.1038\/s41598-023-45925-3","article-title":"Machine learning based readmission and mortality prediction in heart failure patients","volume":"13","author":"Sabouri","year":"2023","journal-title":"Sci Rep"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1805016","DOI":"10.3389\/fnut.2026.1805016","article-title":"The cholesterol, high-density lipoprotein, and glucose Index as a metabolic-nutritional biomarker for risk stratification in hospitalized heart failure patients","volume":"13","author":"Huang","year":"2026","journal-title":"Front Nutr"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1097\/JS9.0000000000003560","article-title":"The C-reactive protein-triglyceride glucose Index (cti) predicts mortality in cardiovascular-kidney-metabolic syndrome: a dual-cohort study with machine learning validation","volume":"112","author":"Song","year":"2026","journal-title":"Int J Surg"},{"key":"B24","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1186\/s12931-026-03711-5","article-title":"Development and external validation of an interpretable machine-learning model for hfpef comorbidity risk in copd patients","volume":"27","author":"Cao","year":"2026","journal-title":"Respir Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"e013823","DOI":"10.1161\/CIRCHEARTFAILURE.125.013823","article-title":"Big data and trustworthy ai for heart failure: a review","volume":"19","author":"Perramon-Lluss\u00e0","year":"2026","journal-title":"Circ Heart Fail"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"Tripod+ai statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"Br Med J"},{"key":"B27","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":"B28","doi-asserted-by":"publisher","first-page":"e009078","DOI":"10.1161\/CIRCOUTCOMES.122.009078","article-title":"Validity of international classification of diseases (icd)-10 diagnosis codes for identification of acute heart failure hospitalization and heart failure with reduced versus preserved ejection fraction in a national medicare sample","volume":"16","author":"Bates","year":"2023","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e026528","DOI":"10.1161\/JAHA.122.026528","article-title":"Stroke-Heart syndrome: recent advances and challenges","volume":"11","author":"Scheitz","year":"2022","journal-title":"J Am Heart Assoc"},{"key":"B30","doi-asserted-by":"publisher","first-page":"23107","DOI":"10.1038\/s41598-026-52487-7","article-title":"Multicenter machine learning model for assessing the impact of malignancy on in-hospital mortality in heart failure patients: a clinical decision support system with interpretable artificial intelligence","volume":"16","author":"Zhang","year":"2026","journal-title":"Sci Rep"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1016\/j.jchf.2024.04.016","article-title":"Autoimmune disorders in heart failure with preserved ejection fraction","volume":"12","author":"Tada","year":"2024","journal-title":"JACC Heart Fail"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/ehjdh\/ztaf118","article-title":"High-Dimensional machine learning models for prediction of heart failure in more than 400 000 men and women from the UK biobank","volume":"6","author":"Kok","year":"2025","journal-title":"Eur Heart J Digit Health"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1590367","DOI":"10.3389\/fcvm.2025.1590367","article-title":"Predicting icu mortality in heart failure patients based on blood tests and vital signs","volume":"12","author":"Wang","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e79307","DOI":"10.2196\/79307","article-title":"Methods for addressing missingness in electronic health record data for clinical prediction models: comparative evaluation","volume":"13","author":"Digitale","year":"2025","journal-title":"JMIR Med Inform"},{"key":"B35","doi-asserted-by":"publisher","first-page":"104800","DOI":"10.1016\/j.jbi.2025.104800","article-title":"Enhanced heart failure mortality prediction through model-independent hybrid feature selection and explainable machine learning","volume":"163","author":"Petmezas","year":"2025","journal-title":"J Biomed Inform"},{"key":"B36","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13040-023-00330-4","article-title":"A self-inspected adaptive smote algorithm (sasmote) for highly imbalanced data classification in healthcare","volume":"16","author":"Kosolwattana","year":"2023","journal-title":"BioData Min"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cjca.2026.03.006","article-title":"Temporal validation of a machine learning readmission model in patients with heart failure with preserved ejection fraction and chronic kidney disease","author":"Deng","year":"2026","journal-title":"Can J Cardiol"},{"key":"B38","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.jclinepi.2014.06.018","article-title":"A new framework to enhance the interpretation of external validation studies of clinical prediction models","volume":"68","author":"Debray","year":"2014","journal-title":"J Clin Epidemiol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"i3140","DOI":"10.1136\/bmj.i3140","article-title":"External validation of clinical prediction models using big datasets from E-health records or ipd meta-analysis: opportunities and challenges","volume":"353","author":"Riley","year":"2016","journal-title":"Br Med J"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjcc.2026.02.008","article-title":"Prognostic significance of blood urea nitrogen-to-albumin ratio in heart failure: from baseline and age-specific risk stratification to one-year dynamic changes","author":"Yano","year":"2026","journal-title":"J Cardiol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1189884","DOI":"10.3389\/fcvm.2023.1189884","article-title":"Predictive value of blood urea nitrogen in heart failure: a systematic review and meta-analysis","volume":"10","author":"Duan","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"B42","doi-asserted-by":"publisher","first-page":"156460","DOI":"10.1016\/j.metabol.2025.156460","article-title":"Aging and metabolism in hfpef: pathophysiology and therapeutic implications","volume":"176","author":"Ye","year":"2026","journal-title":"Metab Clin Exp"},{"key":"B43","doi-asserted-by":"publisher","first-page":"101808","DOI":"10.1016\/j.lanwpc.2026.101808","article-title":"Machine learning prediction of 1-year mortality in older patients with heart failure: a nationwide, multicenter, prospective cohort study","volume":"67","author":"Yamada","year":"2026","journal-title":"Lancet Reg Health West Pac"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1016\/j.jacc.2019.12.069","article-title":"Multiple plasma biomarkers for risk stratification in patients with heart failure and preserved ejection fraction","volume":"75","author":"Chirinos","year":"2020","journal-title":"J Am Coll Cardiol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"e156453","DOI":"10.1172\/JCI156453","article-title":"Neutrophil extracellular traps in cardiac hypertrophy: a Klf2 perspective","volume":"132","author":"Riascos-Bernal","year":"2022","journal-title":"J Clin Invest"},{"key":"B46","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1186\/s12933-023-01895-4","article-title":"Association between the triglyceride-glucose Index and the risk of mortality among patients with chronic heart failure: results from a retrospective cohort study in China","volume":"22","author":"Zhou","year":"2023","journal-title":"Cardiovasc Diabetol"},{"key":"B47","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12937-023-00888-z","article-title":"Potassium levels and the risk of all-cause and cardiovascular mortality among patients with cardiovascular diseases: a meta-analysis of cohort studies","volume":"23","author":"Fan","year":"2024","journal-title":"Nutr J"},{"key":"B48","doi-asserted-by":"publisher","first-page":"S424","DOI":"10.1016\/j.jacr.2025.02.021","article-title":"Acr appropriateness criteria\u00ae suspected and known heart failure: 2024 update","volume":"22","author":"Roberts","year":"2025","journal-title":"J Am Coll Radiol"},{"key":"B49","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1002\/ejhf.2522","article-title":"Cardiac remodelling - part 2: clinical, imaging and laboratory findings. A review from the study group on biomarkers of the heart failure association of the European Society of Cardiology","volume":"24","author":"Aimo","year":"2022","journal-title":"Eur J Heart Fail"},{"key":"B50","doi-asserted-by":"publisher","first-page":"761170","DOI":"10.3389\/fnut.2021.761170","article-title":"Dietary strategies to improve cardiovascular health: focus on increasing high-density lipoprotein functionality","volume":"8","author":"Stadler","year":"2021","journal-title":"Front Nutr"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1942393\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T05:29:32Z","timestamp":1788499772000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1942393\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,4]]},"references-count":50,"alternative-id":["10.3389\/fcvm.2026.1942393"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2026.1942393","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,4]]},"article-number":"1942393"}}