{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:57:37Z","timestamp":1793321857222,"version":"4.5.0"},"reference-count":60,"publisher":"SAGE Publications","issue":"7","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Medical Research Future Fund Grant","award":["MRF2017597"],"award-info":[{"award-number":["MRF2017597"]}]},{"name":"National Health and Medical Research Council Ideas Grant","award":["GNT2013757"],"award-info":[{"award-number":["GNT2013757"]}]},{"DOI":"10.13039\/501100005230","name":"Chongqing Natural Science Foundation","doi-asserted-by":"crossref","award":["Grant No. cstc2020jcyj-msxmX0584"],"award-info":[{"award-number":["Grant No. cstc2020jcyj-msxmX0584"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["J Intensive Care Med"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>\n                    <jats:bold>Background:<\/jats:bold>\n                    Acute Kidney Injury (AKI), a leading organ failure cause in critical patients, demands early high-risk identification to enhance outcomes. Yet comparative analyses of diagnostic and prognostic machine learning (ML) models across multiple post-admission timeframes are lacking.\n                    <jats:bold>Methods:<\/jats:bold>\n                    Using MIMIC-IV, we carried out using the Boruta algorithm for feature selection, developing and comparing six ML models to predict AKI risk at 0-24, 24-48, 48-72, 0-48, and 0-72\u2005h post-ICU admission. Model performance was evaluated using the Area Under the Curve (AUC) and confusion matrix. Decision Curve and calibration analyses assessed clinical applicability. We compared models with Sequential Organ Failure Assessment (SOFA) and SAPSII scores to evaluate the accuracy of the ML models. Finally, Shapley Additive Explanations (SHAP) values interpreted and visualized key features of the optimal model.\n                    <jats:bold>Results:<\/jats:bold>\n                    Our study involved 2092 trauma Intensive Care Unit (ICU) patients. Using the 17 selected out of the 48 features among trauma patients 24\u2005h after ICU admissions, among the six ML models and two scoring systems, all ML models outperformed SOFA and SAPS II, and the extreme gradient boosting (XGBoost) exhibited the best performance, achieving an AUC of 0.948 (95% CI [0.929-0.966]) for AKI prediction within 24\u2005h of admission, with an AUC of 0.941 ([0.892-0.917]) and 0.878 ([0.863-0.892]) at 0-48 and 0-72\u2005h period, respectively. However, their predictive accuracies were very limited at 24-48\u2005h (AUC 0.602 [0.562-0.643]) and 48-72\u2005h (AUC 0.490 [0.429-0.551]), respectively. Urine output per kilogram per hour at 6 and 12\u2005h and age were the most important features identified through SHAP analysis.\n                    <jats:bold>Conclusions:<\/jats:bold>\n                    Our study found ML models excel in diagnosing AKI risk in ICU trauma patients but have limited prognostic accuracy at 24-48 and 48-72\u2005h post-admission. Further research is needed to improve this using time-series ML models with optimal windows.\n                  <\/jats:p>","DOI":"10.1177\/08850666251390848","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:13:16Z","timestamp":1761757996000},"page":"630-642","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["An Interpretable Machine Learning Model for Early Multitemporal Prediction of Onset of Acute Kidney Injury in Intensive Care Unit Patients with Severe Trauma"],"prefix":"10.1177","volume":"41","author":[{"given":"Bingrui","family":"Gao","sequence":"first","affiliation":[{"name":"First Affiliated Hospital, Chongqing Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Jin","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital, Chongqing Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital, Chongqing Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4693-5234","authenticated-orcid":false,"given":"Jack","family":"Chen","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital, Chongqing Medical University"},{"name":"University of New South Wales"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"issue":"2","key":"e_1_3_4_2_2","first-page":"157","article-title":"Trauma registry \u2013 a necessity of modern clinical practice","volume":"109","author":"Beuran M","year":"2014","unstructured":"Beuran M, Stoica B, Negoi I, et al. Trauma registry \u2013 a necessity of modern clinical practice. Chirurgia (Bucur). 2014;109(2):157-160.","journal-title":"Chirurgia (Bucur)"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/mcc.0000000000000655"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1097\/ta.0000000000002085"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1097\/ta.0000000000000727"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0301014"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-019-05535-y"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1080\/08860220802134649"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0077376"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-015-3934-7"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1161\/circinterventions.110.955310"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjcc.2015.05.007"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1161\/circinterventions.110.958389"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-62479-w"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103653"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.2147\/ijgm.S289671"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-023-00248-5"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-021-03724-0"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000016867"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.2215\/cjn.04100318"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1080\/0886022X.2024.2380748"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xkme.2024.100936"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-21929-2"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1097\/md.0000000000034847"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2022.08.007"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12028-022-01606-z"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2021.06.028"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02537-9"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2024.119705"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00346-8"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.2196\/52786"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2024-087427"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dld.2024.09.012"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.13359"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1097\/mcc.0000000000000887"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf065"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1053\/j.ackd.2022.06.005"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.2196\/66733"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(19)32563-2"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-024-05544-6"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-57083-6"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104176"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-020-02620-5"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05138-0"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0246306"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1080\/0886022x.2024.2316267"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1165129"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.5935\/0101-2800.20130021"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1053\/j.ajkd.2016.03.419"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.7150\/thno.71064"},{"key":"e_1_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1097\/ccm.0000000000004145"},{"key":"e_1_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40620-021-01046-6"},{"key":"e_1_3_4_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ekir.2021.02.031"},{"key":"e_1_3_4_54_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-21428-5"},{"key":"e_1_3_4_55_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01245-4"},{"key":"e_1_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0733-z"},{"key":"e_1_3_4_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2019.02.009"},{"key":"e_1_3_4_58_2","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.01.60"},{"key":"e_1_3_4_59_2","doi-asserted-by":"publisher","DOI":"10.1177\/2054358118776326"},{"key":"e_1_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1080\/0886022x.2022.2036619"},{"key":"e_1_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.injury.2017.08.022"}],"container-title":["Journal of Intensive Care Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08850666251390848","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/08850666251390848","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08850666251390848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T22:46:26Z","timestamp":1780094786000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/08850666251390848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":60,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1177\/08850666251390848"],"URL":"https:\/\/doi.org\/10.1177\/08850666251390848","relation":{},"ISSN":["0885-0666","1525-1489"],"issn-type":[{"value":"0885-0666","type":"print"},{"value":"1525-1489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]}}}