{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T19:58:32Z","timestamp":1772999912827,"version":"3.50.1"},"reference-count":28,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T00:00:00Z","timestamp":1759449600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Eur J Clin Investigation"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute kidney injury (AKI) is common and linked to poor outcomes, but early detection remains challenging. Previous research identified urinary trace elements (TE) as early AKI biomarkers in intensive care unit (ICU) or cardiac surgery patients. We aimed to explore whether urinary TE enhance machine learning (ML) models for AKI prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We constructed ML models using the ICU cohort. We filtered the variables and optimized hyperparameters before predicting Kidney Disease: Improving Global Outcomes stage 2\u20133 AKI using eight ML classifiers: light gradient boosting machine (LightGBM), random forest (RF), ML logistic regression, support vector machine, multilayer perceptron, eXtreme gradient boosting (XGBoost), Gaussian Naive Bayes and k\u2010nearest neighbors. External validation was performed in the cardiac surgery cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 149 ICU patients (median age 56.0 [interquartile range (IQR): 43.5\u201367.0], 63.1% male), 25 developed stage 2\u20133 AKI; among 144 cardiac surgery patients (median age 70.0 [IQR: 62.0\u201376.0], 72.9% male), 12 developed stage 2\u20133 AKI. Each ML in the internal validation had area under the curve (AUC) above .7, with XGBoost having the highest (.813); LightGBM had the second highest AUC (.799), highest G\u2010mean (.567) and F1\u2010score (.545). In external validation, RF had the highest AUC (.740), XGBoost had the highest G\u2010mean (.289) and F1\u2010score (.286). Age, strontium and boron were consistently ranked among the top five most important features in LightGBM, RF and XGBoost.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML models primarily based on urinary TE can identify AKI risk in both clinical groups (ICU and cardiac surgery), with LightGBM, RF and XGBoost serving as high\u2010performance models for early prediction of stage 2\u20133 AKI.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/eci.70131","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T11:43:44Z","timestamp":1759491824000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning prediction of moderate\u2010to\u2010severe acute kidney injury after\n                    <scp>ICU<\/scp>\n                    admission and cardiac surgery with urine trace elements"],"prefix":"10.1111","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2808-6286","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"first","affiliation":[{"name":"Liverpool Centre for Cardiovascular Science, at University of Liverpool Liverpool John Moores University and Liverpool Heart &amp; Chest Hospital  Liverpool UK"},{"name":"Department of Cardiovascular and Metabolic Medicine, Institute of Life Course and Medical Sciences University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Gue","sequence":"additional","affiliation":[{"name":"Liverpool Centre for Cardiovascular Science, at University of Liverpool Liverpool John Moores University and Liverpool Heart &amp; Chest Hospital  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory Y. H.","family":"Lip","sequence":"additional","affiliation":[{"name":"Liverpool Centre for Cardiovascular Science, at University of Liverpool Liverpool John Moores University and Liverpool Heart &amp; Chest Hospital  Liverpool UK"},{"name":"Danish Center for Health Services Research, Department of Clinical Medicine Aalborg University  Aalborg Denmark"},{"name":"Medical University of Bialystok  Bialystok Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David S.","family":"Gardner","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health Sciences, School of Veterinary Medicine and Science University of Nottingham  Nottingham UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark A. J.","family":"Devonald","sequence":"additional","affiliation":[{"name":"Liverpool Centre for Cardiovascular Science, at University of Liverpool Liverpool John Moores University and Liverpool Heart &amp; Chest Hospital  Liverpool UK"},{"name":"Renal and Transplant Unit Liverpool University Hospitals NHS Foundation Trust  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,10,3]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.2215\/CJN.00710113"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/ndt\/gfu016"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrneph.2017.2"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1681\/ASN.2017080882"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-022-02428-8"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ekir.2022.04.085"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.944790"},{"issue":"23","key":"e_1_2_10_9_1","first-page":"1805","article-title":"Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges","volume":"38","author":"Goldstein BA","year":"2017","journal-title":"Eur Heart J"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/eci.70017"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/eci.14364"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02521-7"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-024-02538-y"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/eci.14371"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.redox.2025.103588"},{"key":"e_1_2_10_16_1","unstructured":"Surveillance report 2017 \u2013 Acute kidney injury: prevention detection and management (2013) NICE guideline CG169. London: National Institute for Health and Care Excellence (UK) Copyright \u00a9 NICE 2017.2017."},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12882-019-1678-2"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/ki.2014.328"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-130-6-199903160-00002"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-145-4-200608150-00004"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/ndt\/gfq454"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrc.2023.154278"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm7100322"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-010-1957-7"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.19776"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.951881"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemosphere.2019.03.171"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/toxsci\/60.2.252"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00394-021-02702-0"}],"container-title":["European Journal of Clinical Investigation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eci.70131","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/eci.70131","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eci.70131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:25:19Z","timestamp":1772990719000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/eci.70131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,3]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1111\/eci.70131"],"URL":"https:\/\/doi.org\/10.1111\/eci.70131","archive":["Portico"],"relation":{},"ISSN":["0014-2972","1365-2362"],"issn-type":[{"value":"0014-2972","type":"print"},{"value":"1365-2362","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,3]]},"assertion":[{"value":"2025-04-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70131"}}