{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:31:02Z","timestamp":1786681862339,"version":"build-2736575974"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"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. Nutr."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study systematically examines the clinical factors associated with enteral nutrition-related diarrhea (ENAD) in patients with severe stroke and uses interpretable machine learning methods to assess the strength of these associations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 766 patients with severe stroke from two hospitals between January 2021 and December 2025; data were sourced from electronic medical records and nursing notes. The study compared eight machine learning algorithms: logistic regression (Logistic), support vector machines (SVM), random forests (RF), extreme gradient boosting (XGBoost), lightweight gradient boosting (LightGBM), classification gradient boosting (CatBoost), k-nearest neighbors (KNN), and decision trees (DT); model performance was evaluated using 10-fold cross-validation (CV); The optimal model was selected, with SHAP (Shapley Additive exPlanations) analysis used to provide feature importance and the Delong test for feature selection; the final model was evaluated and validated using metrics from calibration curves, decision curve analysis curves, and the model confusion matrix; SHAP analysis was used to interpret the final model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 292 patients (38.1%) in the study cohort developed diarrhea. The random forest model was identified as the optimal model and served as the feature selection model. Following the Delong test, 10 variables most closely associated with ENAD were ultimately included: duration of mechanical ventilation, number of days on enteral nutrition (EN) and formula type, C-reactive protein, white blood cell count, hemoglobin, blood urea nitrogen, room temperature, prokinetic agents, and oral potassium supplements. The model performed as follows in terms of retrospective discriminatory power: The AUC was 0.873 (95% CI: 0.826\u20130.920), with an accuracy of 0.836 (0.790\u20130.882) and a precision of 0.787 (0.697\u20130.875). A recall of 0.720 (0.622\u20130.819), an F1 score of 0.752 (0.672\u20130.825), and a negative predictive value of 0.859 (0.805\u20130.912). SHAP analysis revealed a non-linear relationship between the aforementioned features and the risk of ENAD. It should be noted that because some variables (such as duration of mechanical ventilation and number of days on enteral nutrition) reflect cumulative exposure over the entire ICU stay, reported metrics such as AUC may be overestimated and should not be directly interpreted as indicative of predictive performance. The SHAP analysis revealed patterns of association between these characteristics and the risk of ENAD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Based on interpretable machine learning methods, this study identified 10 factors\u2014including duration of mechanical ventilation, number of days on enteral nutrition, and C-reactive protein levels\u2014that were most strongly associated with ENAD in the model output in patients with severe stroke. The results suggest that, in addition to focusing on the patients' clinical condition and nutritional interventions themselves, clinicians should also pay attention to the regulation of ward temperature and the proper management of relevant medications. The clinical predictive value of these associations requires further validation through prospective, time-dependent studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1893280","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:23:35Z","timestamp":1786681415000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An evaluation based on explainable machine learning: analysis of risk factors for enteral nutrition-related diarrhea in patients with severe stroke"],"prefix":"10.3389","volume":"13","author":[{"given":"Caiyue","family":"Xu","sequence":"first","affiliation":[{"name":"School of Nursing, Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Nursing, People's Hospital of Shangrao","place":["Shangrao, Jiangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Nursing, Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Nursing, Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengzhi","family":"Chai","sequence":"additional","affiliation":[{"name":"School of Nursing, Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfan","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Nursing, Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Li","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital of Jinzhou Medical University","place":["Jinzhou, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1016\/S0140-6736(24)00757-8","article-title":"Global incidence, prevalence, years lived with disability (YLDs), disability-adjusted life-years (DALYs), and healthy life expectancy (HALE) for 371 diseases and injuries in 204 countries and territories and 811 subnational locations, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"403","year":"2024","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1016\/S1474-4422(24)00369-7","article-title":"Global, regional, and national burden of stroke and its risk factors, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"23","author":"GBD","year":"2024","journal-title":"Lancet Neurol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1016\/S0140-6736(24)00367-2","article-title":"Global burden of 288 causes of death and life expectancy decomposition in 204 countries and territories and 811 subnational locations, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"403","year":"2024","journal-title":"Lancet"},{"key":"B4","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1002\/jpen.2707","article-title":"The ASPEN rhoads research foundation: supporting and advancing clinical nutrition research","volume":"49","author":"Winkler","year":"2025","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B5","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.clnu.2018.08.037","article-title":"ESPEN guideline on clinical nutrition in the intensive care unit","volume":"38","author":"Singer","year":"2019","journal-title":"Clin Nutr."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1016\/j.clnu.2023.07.011","article-title":"ESPEN practical and partially revised guideline: clinical nutrition in the intensive care unit","volume":"42","author":"Singer","year":"2023","journal-title":"Clin Nutr."},{"key":"B7","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1002\/jpen.2501","article-title":"Development and validation of a predictive model for diarrhea in ICU patients with enteral nutrition","volume":"47","author":"Chen","year":"2023","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1584717","DOI":"10.3389\/fnut.2025.1584717","article-title":"Machine learning-based predictive model for enteral nutrition-associated diarrhea in ICU patients and its nursing applications","volume":"12","author":"Liao","year":"2025","journal-title":"Front Nutr."},{"key":"B9","doi-asserted-by":"publisher","first-page":"24691","DOI":"10.1038\/srep24691","article-title":"Diarrhoea in the critically ill is common, associated with poor outcome, and rarely due to Clostridium difficile","volume":"6","author":"Tirlapur","year":"2016","journal-title":"Sci Rep"},{"key":"B10","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.clnesp.2023.07.007","article-title":"Diarrhoea and constipation during artificial nutrition in intensive care unit: a prospective observational study","volume":"57","author":"Danielis","year":"2023","journal-title":"Clin Nutr ESPEN."},{"key":"B11","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.clnu.2017.09.003","article-title":"ESPEN guideline clinical nutrition in neurology","volume":"37","author":"Burgos","year":"2018","journal-title":"Clin Nutr."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1177\/23969873211039721","article-title":"European Stroke Organisation and European Society for Swallowing Disorders guideline for the diagnosis and treatment of post-stroke dysphagia","author":"Dziewas","year":"2021","journal-title":"Eur Stroke J"},{"key":"B13","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1186\/s12876-025-03837-8","article-title":"Risk factors for enteral feeding intolerance in critically ill patients: an updated systematic review and meta-analysis","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Gastroenterol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1152\/physrev.00018.2018","article-title":"The microbiota-gut-brain axis","volume":"99","author":"Cryan","year":"2019","journal-title":"Physiol Rev."},{"key":"B15","doi-asserted-by":"publisher","first-page":"598","DOI":"10.3389\/fneur.2020.00598","article-title":"Gut microbiota in acute ischemic stroke: from pathophysiology to therapeutic implications","volume":"11","author":"Battaglini","year":"2020","journal-title":"Front Neurol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/s41575-024-01023-x","article-title":"Antibiotic-perturbed microbiota and the role of probiotics","volume":"22","author":"Szajewska","year":"2025","journal-title":"Nat Rev Gastroenterol Hepatol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"100589","DOI":"10.3748\/wjg.v31.i2.100589","article-title":"Bowel preparation before colonoscopy: Consequences, mechanisms, and treatment of intestinal dysbiosis","volume":"31","author":"Zheng","year":"2025","journal-title":"World J Gastroenterol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"32","DOI":"10.4103\/sjg.sjg_286_21","article-title":"Development and validation of a predictive model for feeding intolerance in intensive care unit patients with sepsis","volume":"28","author":"Hu","year":"2022","journal-title":"Saudi J Gastroenterol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.3390\/nu15122705","article-title":"Using machine-learning to assess the prognostic value of early enteral feeding intolerance in critically ill patients: a retrospective study","volume":"15","author":"Raphaeli","year":"2023","journal-title":"Nutrients."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1600319","DOI":"10.3389\/fnut.2025.1600319","article-title":"Construction and evaluation of a machine learning-based predictive model for enteral nutrition feeding intolerance risk in ICU patients","volume":"12","author":"Wang","year":"2025","journal-title":"Front Nutr."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1481279","DOI":"10.3389\/fnut.2024.1481279","article-title":"Development and validation of a risk prediction model for feeding intolerance in neurocritical patients with enteral nutrition","volume":"11","author":"Yuan","year":"2024","journal-title":"Front Nutr."},{"key":"B22","doi-asserted-by":"publisher","first-page":"7341","DOI":"10.2147\/IJGM.S567157","article-title":"Predicting early dysphagia in acute ischemic stroke using an explainable machine learning model","volume":"18","author":"Li","year":"2025","journal-title":"Int J Gen Med."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1234046","DOI":"10.3389\/fneur.2023.1234046","article-title":"Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke","volume":"14","author":"Lee","year":"2023","journal-title":"Front Neurol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1016\/S0895-4356(96)00236-3","article-title":"A simulation study of the number of events per variable in logistic regression analysis","volume":"49","author":"Peduzzi","year":"1996","journal-title":"J Clin Epidemiol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"e0224365","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"Vabalas","year":"2019","journal-title":"PLoS ONE."},{"key":"B26","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1177\/0148607115621863","article-title":"et al. Guidelines for the provision and assessment of nutrition support therapy in the adult critically ill patient: Society of Critical Care Medicine (SCCM) and American Society for Parenteral and Enteral Nutrition (A.S.P.E.N.)","volume":"40","author":"McClave","year":"2016","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B27","doi-asserted-by":"publisher","first-page":"920","DOI":"10.3109\/00365529709011203","article-title":"Stool form scale as a useful guide to intestinal transit time","volume":"32","author":"Lewis","year":"1997","journal-title":"Scand J Gastroenterol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1097\/CCM.0000000000004712","article-title":"Incidence, risk factors, and clinical consequence of enteral feeding intolerance in the mechanically ventilated critically ill: an analysis of a multicenter, multiyear database","volume":"49","author":"Heyland","year":"2021","journal-title":"Crit Care Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"e1247","DOI":"10.1097\/CCM.0000000000006667","article-title":"Diarrhea in mechanically ventilated patients: a nested multicenter substudy","volume":"53","author":"Dionne","year":"2025","journal-title":"Crit Care Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"e2247","DOI":"10.1002\/nop2.2247","article-title":"The incidence and risk factors of gastrointestinal dysfunction during enteral nutrition in mechanically ventilated critically ill patients","volume":"11","author":"Shi","year":"2024","journal-title":"Nurs Open."},{"key":"B31","doi-asserted-by":"publisher","first-page":"e00199","DOI":"10.1128\/mSphere.00199-16","article-title":"Extreme dysbiosis of the microbiome in critical illness","volume":"1","author":"McDonald","year":"2016","journal-title":"mSphere."},{"key":"B32","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1164\/rccm.201002-0210CI","article-title":"Chronic critical illness","volume":"182","author":"Nelson","year":"2010","journal-title":"Am J Respir Crit Care Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2527","DOI":"10.1097\/01.CCM.0000186898.58709.AA","article-title":"Impact of tracheotomy on sedative administration, sedation level, and comfort of mechanically ventilated intensive care unit patients","volume":"33","author":"Nieszkowska","year":"2005","journal-title":"Crit Care Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"770323","DOI":"10.3389\/fmicb.2021.770323","article-title":"Hi-C metagenomics in the ICU: exploring clinically relevant features of gut microbiome in chronically critically ill patients","volume":"12","author":"Ivanova","year":"2021","journal-title":"Front Microbiol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/s12975-023-01211-y","article-title":"Sympathetic-mediated intestinal cell death contributes to gut barrier impairment after stroke","volume":"16","author":"Prame Kumar","year":"2025","journal-title":"Transl Stroke Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1002\/ncp.10599","article-title":"Enteral feeding intolerance: updates in definitions and pathophysiology","volume":"36","author":"Reintam Blaser","year":"2021","journal-title":"Nutr Clin Pract."},{"key":"B37","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/s00134-011-2459-y","article-title":"Gastrointestinal function in intensive care patients: terminology, definitions and management. Recommendations of the ESICM working group on abdominal problems","volume":"38","author":"Reintam Blaser","year":"2012","journal-title":"Intensive Care Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1177\/2042098611415567","article-title":"Current issues on safety of prokinetics in critically ill patients with feed intolerance","volume":"2","author":"Nguyen","year":"2011","journal-title":"Ther Adv Drug Saf."},{"key":"B39","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s00134-007-0834-5","article-title":"Risk of Clostridium difficile diarrhoea in critically ill patients treated with erythromycin-based prokinetic therapy for feed intolerance","volume":"34","author":"Nguyen","year":"2008","journal-title":"Intensive Care Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"e0245317","DOI":"10.1371\/journal.pone.0245317","article-title":"The efficacy and safety of prokinetics in critically ill adults receiving gastric feeding tubes: a systematic review and meta-analysis","volume":"16","author":"Peng","year":"2021","journal-title":"PLoS One."},{"key":"B41","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1177\/0148607112471560","article-title":"Osmolality, pH, and compatibility of selected oral liquid medications with an enteral nutrition product","volume":"37","author":"Klang","year":"2013","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B42","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1177\/0148607116673053","article-title":"ASPEN safe practices for enteral nutrition therap","volume":"41","author":"Boullata","year":"2017","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B43","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.2146\/ajhp080155","article-title":"Medication administration through enteral feeding tubes","volume":"65","author":"Williams","year":"2008","journal-title":"Am J Health Syst Pharm."},{"key":"B44","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1177\/0148607183007004387","article-title":"Gastrointestinal disorders caused by medication and electrolyte solution osmolality during enteral nutrition","volume":"7","author":"Niemiec PW","year":"1983","journal-title":"JPEN J Parenter Enteral Nutr."},{"key":"B45","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.3390\/biomedicines12122781","article-title":"Gut microbiota, bacterial translocation, and stroke: current knowledge and future directions","volume":"12","author":"Granados-Martinez","year":"2024","journal-title":"Biomedicines"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1161\/STROKEAHA.123.042755","article-title":"Poststroke lung infection by opportunistic commensal bacteria is not mediated by their expansion in the gut microbiota","volume":"54","author":"D\u00edaz-Marugan","year":"2023","journal-title":"Stroke."},{"key":"B47","doi-asserted-by":"publisher","first-page":"577","DOI":"10.6133\/apjcn.202508_34(4).0009","article-title":"Systematic evaluation of risk prediction models for feeding intolerance in ICU patients during enteral nutrition","volume":"34","author":"Huang","year":"2025","journal-title":"Asia Pac J Clin Nutr."},{"key":"B48","doi-asserted-by":"publisher","first-page":"1781944","DOI":"10.3389\/fnut.2026.1781944","article-title":"Impact of enteral feeding strategies on nosocomial Clostridioides difficile infection-induced diarrhea","volume":"13","author":"Alasbly","year":"2026","journal-title":"Front Nutr."},{"key":"B49","doi-asserted-by":"publisher","first-page":"4410","DOI":"10.12998\/wjcc.v8.i19.4410","article-title":"Optimal hang time of enteral formula at standard room temperature and high temperature","volume":"8","author":"Lakananurak","year":"2020","journal-title":"World J Clin Cases."},{"key":"B50","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1378\/chest.119.4.1222","article-title":"GI complications in patients receiving mechanical ventilation","volume":"119","author":"Mutlu","year":"2001","journal-title":"Chest"},{"key":"B51","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1177\/0884533614541680","article-title":"Microbial contamination of enteral feeding products in thermoneutral and hyperthermal ICU environments","volume":"30","author":"Perry","year":"2015","journal-title":"Nutr Clin Pract."},{"key":"B52","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1159\/000515061","article-title":"Bacterial contamination during continuous administration of liquid enteral nutrition formula in a sterile sealed bag: a prospective interventional study","volume":"77","author":"Hatakeyama","year":"2021","journal-title":"Ann Nutr Metab."},{"key":"B53","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1038\/s41430-025-01683-1","article-title":"Early prediction of enteral nutrition feeding intolerance risk in neurocritical patients and development of a simplified risk scoring tables","volume":"80","author":"Yuan","year":"2026","journal-title":"Eur J Clin Nutr."},{"key":"B54","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1016\/j.clnu.2021.10.018","article-title":"ESPEN practical guideline: home enteral nutrition","volume":"41","author":"Bischoff","year":"2022","journal-title":"Clin Nutr."},{"key":"B55","volume-title":"Healthcare-Associated Infections: Prevention and Control in Primary and Community Care","year":"2012"},{"key":"B56","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3390\/nu18010110","article-title":"AI-enabled precision nutrition in the ICU: a narrative review and implementation roadmap","volume":"18","author":"Briassoulis","year":"2025","journal-title":"Nutrients."}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1893280\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:23:37Z","timestamp":1786681417000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1893280\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":56,"alternative-id":["10.3389\/fnut.2026.1893280"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1893280","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]},"article-number":"1893280"}}