{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T06:15:43Z","timestamp":1778652943018,"version":"3.51.4"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:00:00Z","timestamp":1778630400000},"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>Objective<\/jats:title>\n                    <jats:p>Critically ill patients with chronic kidney disease (CKD) are at high risk for New-Onset Atrial Fibrillation (NOAF), which significantly increases their risk of adverse events. Early detection of NOAF is crucial for prompt intervention and better outcomes. This study aims to develop and validate predictive models for the early identification and stratification of NOAF risk in this vulnerable population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We developed and validated a predictive model using a cohort of 6,476 critically ill patients with CKD from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. After performing feature selection via least absolute shrinkage and selection operator (Lasso) logistic regression, we trained six machine learning (ML) models. These algorithms included: Random Forest, Gradient Boosting, eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Multi-layer Perceptron (MLP), and Light Gradient Boosting Machine (LightGBM). The best-performing model was interpreted using SHAP to provide clinical insights. Its robustness and generalizability were confirmed through rigorous external validation on two distinct international cohorts: the US-based eICU-CRD (eICU Collaborative Research Database) (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f12,509) and a Chinese ICU database from Weifang People\u2019s Hospital (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f880).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Ultimately, 12 predictive features were ultimately selected: age, SOFA score, minimum heart rate, congestive heart failure, average heart rate, minimum systolic blood pressure (SBP), mechanical ventilation use, minimum oxygen saturation (SpO\n                      <jats:sub>2<\/jats:sub>\n                      ), average respiratory rate, minimum magnesium, SAPS II score, and maximum white blood cell (WBC) count. The Random Forest model demonstrated the best overall performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.855 in internal validation. The model\u2019s robustness was confirmed through external validation on two independent cohorts, yielding an AUC of 0.760 on the eICU-CRD and 0.740 on the Weifang People\u2019s Hospital database. According to the SHAP analysis, age, average heart rate, minimum heart rate, SOFA score, and SAPS II were the top five most influential predictors for NOAF.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed an interpretable machine learning model to predict NOAF in critically ill CKD patients, demonstrating strong generalizability through external validation on both a large US cohort (eICU-CRD) and a single-center Chinese cohort (Weifang People\u2019s Hospital). SHAP analysis enhanced model interpretability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1816221","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:56:09Z","timestamp":1778651769000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning to predict NOAF in ICU patients with CKD: validation in US and Chinese cohorts"],"prefix":"10.3389","volume":"13","author":[{"given":"Shujie","family":"Zhang","sequence":"first","affiliation":[{"name":"Clinical Medical School, Shandong Second Medical University","place":["Weifang, Shandong, China"]},{"name":"Department of Cardiology, Weifang People\u2019s Hospital, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Vascular Surgery, Weifang People\u2019s Hospital, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Weifang People\u2019s Hospital, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, Fuzhou University Provincial Affiliated Hospital","place":["Fuzhou, Fujian, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lujing","family":"Nie","sequence":"additional","affiliation":[{"name":"Clinical Medical School, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Clinical Medical School, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Nursing, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Weifang People\u2019s Hospital, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbo","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Weifang People\u2019s Hospital, Shandong Second Medical University","place":["Weifang, Shandong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e14535","DOI":"10.1111\/aas.14535","article-title":"Acute amiodarone-induced pulmonary toxicity in adult ICU patients with NOAF-a systematic review","volume":"69","author":"Ling-Vannerus","year":"2025","journal-title":"Acta Anaesthesiol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s40635-022-00490-3","article-title":"A deep learning model for the classification of atrial fibrillation in critically ill patients","volume":"11","author":"Chen","year":"2023","journal-title":"Intensive Care Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1093\/europace\/euab163","article-title":"NOAF in critically ill acute kidney injury patients on renal replacement therapy","volume":"24","author":"Hellman","year":"2022","journal-title":"EP Eur"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1111\/jce.15759","article-title":"Atrial fibrillation: epidemiology, pathophysiology, and clinical complications (literature review)","volume":"34","author":"Bizhanov","year":"2023","journal-title":"J Cardiovasc Electrophysiol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1097\/CCM.0000000000001166","article-title":"Atrial fibrillation is an independent predictor of mortality in critically ill patients","volume":"43","author":"Shaver","year":"2015","journal-title":"Crit Care Med"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e033941","DOI":"10.1161\/JAHA.123.033941","article-title":"Prevalence, characteristics, and treatment strategy of different types of heart failure in patients with nonvalvular atrial fibrillation","volume":"13","author":"Xia","year":"2024","journal-title":"J Am Heart Assoc"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e13745","DOI":"10.1111\/eci.13745","article-title":"Impact of renal impairment on atrial fibrillation: ESC-EHRA EORP-AF long-term general registry","volume":"52","author":"Ding","year":"2022","journal-title":"Eur J Clin Investig"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"S117","DOI":"10.1016\/j.kint.2023.10.018","article-title":"KDIGO 2024 clinical practice guideline for the evaluation and management of CKD","volume":"105","year":"2024","journal-title":"Kidney Int"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e13888","DOI":"10.1111\/apha.13888","article-title":"Uremic toxins in CKD highlight a fundamental gap in understanding their detrimental effects on cardiac electrophysiology and arrhythmogenesis","volume":"236","author":"van Ham","year":"2022","journal-title":"Acta Physiol Oxf Engl"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1097\/HJH.0b013e32833a7dfe","article-title":"CKD as an independent risk factor for NOAF in hypertensive patients","volume":"28","author":"Horio","year":"2010","journal-title":"J Hypertens"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1161\/CIRCULATIONAHA.111.020982","article-title":"CKD is associated with the incidence of atrial fibrillation: the atherosclerosis risk in communities (ARIC) study","volume":"123","author":"Alonso","year":"2011","journal-title":"Circulation"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.3390\/medicina60081309","article-title":"Atrial fibrillation prevalence rates and its association with cardiovascular-kidney-metabolic factors: SIMETAP-AF study","volume":"60","author":"Ruiz-Garc\u00eda","year":"2024","journal-title":"Medicina"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1016\/j.chest.2018.03.040","article-title":"Atrial fibrillation in the ICU","volume":"154","author":"Bosch","year":"2018","journal-title":"Chest"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s00059-024-05235-4","article-title":"Increased cardiovascular risk in patients with CKD","volume":"49","author":"Vondenhoff","year":"2024","journal-title":"Herz"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"101306","DOI":"10.1016\/j.ijcha.2023.101306","article-title":"Clinical outcomes and predictors of long-term mortality, hemorrhagic and thromboembolic events in atrial fibrillation patients at different stages of CKD: the CRAFT trial","volume":"49","author":"Styczkiewicz","year":"2023","journal-title":"Int J Cardiol Heart Vasc"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e13633","DOI":"10.1111\/eci.13633","article-title":"Predictive model for atrial fibrillation in hypertensive diabetic patients","volume":"51","author":"Abellana","year":"2021","journal-title":"Eur J Clin Investig"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for NOAF prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit Care Lond Engl"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"105086","DOI":"10.1016\/j.ijmedinf.2023.105086","article-title":"Generalizable calibrated machine learning models for real-time atrial fibrillation risk prediction in ICU patients","volume":"175","author":"Verhaeghe","year":"2023","journal-title":"Int J Med Inform"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1741","DOI":"10.1007\/s13246-025-01618-x","article-title":"Explainable hierarchical machine-learning approaches for multimodal prediction of conversion from mild cognitive impairment to Alzheimer\u2019s disease","volume":"48","author":"Zarei","year":"2025","journal-title":"Phys Eng Sci Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.2215\/CJN.01060121","article-title":"Prediction of incident atrial fibrillation in CKD: the chronic renal insufficiency cohort study","volume":"16","author":"Zelnick","year":"2021","journal-title":"Clin J Am Soc Nephrol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e62862","DOI":"10.2196\/62862","article-title":"Diagnostic prediction models for primary care, based on AI and electronic health records: systematic review","volume":"13","author":"Hunik","year":"2025","journal-title":"JMIR Med Inform"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1016\/j.ejvs.2024.11.357","article-title":"Prediction of two year survival following elective repair of abdominal aortic aneurysms at a single Centre using a random forest classification algorithm","volume":"69","author":"Thompson","year":"2025","journal-title":"Eur J Vasc Endovasc Surg"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.wneu.2024.10.075","article-title":"Random Forest prognostication of survival and 6-month outcome in Pediatric patients following decompressive craniectomy for traumatic brain injury","volume":"193","author":"Morgan","year":"2025","journal-title":"World Neurosurg"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e70283","DOI":"10.1111\/pai.70283","article-title":"Machine learning-based prediction of inborn errors of immunity in patients with low IgE levels","volume":"37","author":"\u015eahin","year":"2026","journal-title":"Pediatr Allergy Immunol"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e023583","DOI":"10.1161\/JAHA.121.023583","article-title":"Thirty-year trends in the incidence of atrial fibrillation: the ARIC study","volume":"11","author":"Ghelani","year":"2022","journal-title":"J Am Heart Assoc"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1093\/europace\/euac123","article-title":"EHRA expert consensus document on the Management of Arrhythmias in frailty syndrome, endorsed by the Heart Rhythm Society (HRS), Asia Pacific Heart Rhythm Society (APHRS), Latin America Heart Rhythm Society (LAHRS), and cardiac arrhythmia Society of Southern Africa (CASSA)","volume":"25","author":"Savelieva","year":"2023","journal-title":"Europace"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"25364","DOI":"10.31083\/RCM25364","article-title":"Autonomic nervous system activity before atrial fibrillation onset as assessed by heart rate variability","volume":"26","author":"Gr\u00e9goire","year":"2025","journal-title":"Rev Cardiovasc Med"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"968615","DOI":"10.3389\/fcvm.2022.968615","article-title":"Development and validation of a predictive model for NOAF in Sepsis based on clinical risk factors","volume":"9","author":"Li","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"5414","DOI":"10.21037\/jtd-23-704","article-title":"Proteomic sequencing analysis in a rat model of atrial fibrosis caused by chronic intermittent hypoxia","volume":"15","author":"Zhao","year":"2023","journal-title":"J Thorac Dis"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1614979","DOI":"10.3389\/fcvm.2025.1614979","article-title":"Identification of key genes associated with atrial fibrillation and hypoxia using WGCNA and machine learning technology","volume":"12","author":"Wang","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e0191736","DOI":"10.1371\/journal.pone.0191736","article-title":"Risk factors for heart failure hospitalizations among patients with atrial fibrillation","volume":"13","author":"Eggimann","year":"2018","journal-title":"PLoS One"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"223","DOI":"10.23736\/S0026-4806.25.09607-7","article-title":"Cardiovascular-kidney-metabolic syndrome and treatment advances: a narrative review","volume":"116","author":"Pena","year":"2025","journal-title":"Minerva Med"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.3904\/kjim.2020.142","article-title":"Atrial fibrillation in critically ill patients who received prolonged mechanical ventilation: a Nationwide inpatient report","volume":"36","author":"Lin","year":"2021","journal-title":"Korean J Intern Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1007\/s00134-019-05633-x","article-title":"NOAF in adult critically ill patients: a scoping review","volume":"45","author":"Wetterslev","year":"2019","journal-title":"Intensive Care Med"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1186\/s12864-024-10197-2","article-title":"Serum electrolyte concentrations and risk of atrial fibrillation: An observational and mendelian randomization study","volume":"25","author":"Wu","year":"2024","journal-title":"BMC Genomics"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1816221\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T05:56:10Z","timestamp":1778651770000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1816221\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":35,"alternative-id":["10.3389\/fmed.2026.1816221"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1816221","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"article-number":"1816221"}}