{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T06:49:42Z","timestamp":1792046982284,"version":"4.4.0"},"reference-count":39,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Acute kidney injury (AKI) is common in intensive care and is frequently recognized late. We aimed to develop an interpretable, dynamic early warning score (EWS) to predict incident AKI within the next 24 h in ICU adult patients and to test its transportability temporally and geographically. Methods: We performed a retrospective cohort multi-center study using hospitalized ICU patients from MIMIC-IV and eICU-CRD databases. The outcome was incident AKI (KDIGO stage 1\u20133). Gradient-boosted trees (XGBoost) were trained with 10-fold cross-validation. Predictors were prespecified from the literature and finalized as 61 routinely available EHR predictors selected using SHAP ranking (spanning demographics\/comorbidities, laboratory markers, vital-sign dynamics, and ICU therapies\/procedures). Prespecified validations included (i) temporal validation in the COVID-19 era and (ii) geographic validation in eICU Northeast hospitals. Results: The development cohort included 51,833 ICU stays; temporal and geographic cohorts included 3346 and 2993 stays, respectively. Discrimination was high in internal validation (AUC 0.88, 95% CI 0.84\u20130.90) and remained robust temporally (AUC 0.84, 0.80\u20130.87) and geographically (AUC 0.82, 0.81\u20130.84). At a prespecified threshold, sensitivity\/specificity were 0.76\/0.79 (temporal) and 0.73\/0.86 (geographic). Decision-curve analysis showed net benefit across clinically relevant thresholds. Key predictors reflected physiologic trajectories (e.g., mean arterial pressure dynamics), urine output, renal\/metabolic markers (e.g., creatinine and BUN trends), and oxygenation dynamics (SpO2). Conclusions: A routinely updated, explainable EHR-based EWS can predict ICU AKI up to 24 h in advance with stable performance across a pandemic-era temporal shift and external geographic validation.<\/jats:p>","DOI":"10.3390\/jcm15031191","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:46:11Z","timestamp":1770122771000},"page":"1191","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Forecasting ICU Acute Kidney Injury with Actionable Lead Time Using Interpretable Machine Learning: Development and Multi-Center Validation"],"prefix":"10.3390","volume":"15","author":[{"given":"Abdulla Zahi","family":"Hourani","sequence":"first","affiliation":[{"name":"Doctoral School, Medical University of Warsaw, 02-091 Warsaw, Poland"},{"name":"Department of Nephrology, Dialysis and Internal Medicine, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1713-3315","authenticated-orcid":false,"given":"Zuzanna","family":"Jakubowska","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Dialysis and Internal Medicine, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8701-8171","authenticated-orcid":false,"given":"Jolanta","family":"Ma\u0142yszko","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Dialysis and Internal Medicine, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.2215\/CJN.00710113","article-title":"World Incidence of Acute Kidney Injury: A Meta-analysis","volume":"8","author":"Susantitaphong","year":"2013","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1007\/s00134-015-3934-7","article-title":"Epidemiology of Acute Kidney Injury in Critically Ill Patients: The Multinational AKI-EPI Study","volume":"41","author":"Hoste","year":"2015","journal-title":"Intensive Care Med."},{"key":"ref_3","unstructured":"(2012). Kidney Disease: Improving Global Outcomes (KDIGO). KDIGO Clinical Practice Guideline for Acute Kidney Injury. Kidney Int. Suppl., 2, 1."},{"key":"ref_4","first-page":"297","article-title":"The Economic Consequences of Acute Kidney Injury","volume":"137","author":"Silver","year":"2017","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1681\/ASN.2016010105","article-title":"AKI and Long-Term Risk for Cardiovascular Events and Mortality: A Systematic Review and Meta-analysis","volume":"28","author":"Odutayo","year":"2017","journal-title":"J. Am. Soc. Nephrol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1038\/ki.2011.379","article-title":"Chronic Kidney Disease after Acute Kidney Injury: A Systematic Review and Meta-analysis","volume":"81","author":"Coca","year":"2012","journal-title":"Kidney Int."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"sfae231","DOI":"10.1093\/ckj\/sfae231","article-title":"Recognition patterns of acute kidney injury in hospitalized patients","volume":"17","author":"Esposito","year":"2024","journal-title":"Clin. Kidney J."},{"key":"ref_8","first-page":"e1063","article-title":"Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock 2021","volume":"49","author":"Evans","year":"2021","journal-title":"Intensive Care Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.1007\/s00467-020-04849-0","article-title":"Acute kidney injury and aging","volume":"36","year":"2021","journal-title":"Pediatr. Nephrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.semnephrol.2022.04.010","article-title":"Sex Differences in Acute Kidney Injury","volume":"42","author":"Neugarten","year":"2022","journal-title":"Semin. Nephrol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1093\/ckj\/sfz113","article-title":"The association of socioeconomic status with incidence and outcomes of acute kidney injury","volume":"13","author":"Hounkpatin","year":"2019","journal-title":"Clin. Kidney J."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Grant, C.H. (2025). Health inequalities and outcomes following acute kidney injury: A systematic review & meta-analyses of observational studies. BMC Nephrol., 26.","DOI":"10.1186\/s12882-025-04391-x"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"151466","DOI":"10.1016\/j.semnephrol.2023.151466","article-title":"Infections and Acute Kidney Injury: A Global Perspective","volume":"43","author":"Batte","year":"2023","journal-title":"Semin. Nephrol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wainstein, M., Flanagan, E., Johnson, D.W., and Shrapnel, S. (2023). Systematic Review of Externally Validated Machine Learning Models for Predicting Acute Kidney Injury in General Hospital Patients. Front. Nephrol., 3.","DOI":"10.3389\/fneph.2023.1220214"},{"key":"ref_15","unstructured":"NHS (2014). Acute Kidney Injury (AKI) e-Alert Algorithm Specification (Serum Creatinine-Based), NHS."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zimmerman, L.P., Reyfman, P.A., Smith, A.D.R., Zeng, Z., Kho, A., Sanchez-Pinto, L.N., and Luo, Y. (2019). Early Prediction of Acute Kidney Injury Following ICU Admission Using a Multivariate Panel of Physiological Measurements. BMC Med. Inform. Decis. Mak., 19.","DOI":"10.1186\/s12911-019-0733-z"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2266458","DOI":"10.1080\/07853890.2023.2266458","article-title":"Incorporating intraoperative blood pressure time-series variables to assist in prediction of acute kidney injury after type a acute aortic dissection repair: An interpretable machine learning model","volume":"55","author":"Dai","year":"2023","journal-title":"Ann. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e1004566","DOI":"10.1371\/journal.pmed.1004566","article-title":"A deep-learning algorithm using real-time collected intraoperative vital sign signals for predicting acute kidney injury after major non-cardiac surgeries: A modelling study","volume":"22","author":"Park","year":"2025","journal-title":"PLoS Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6677","DOI":"10.1016\/j.acra.2025.08.007","article-title":"Integrating Multi-Modal Imaging Features for Early Prediction of Acute Kidney Injury in Pneumonia Sepsis: A Multicenter Retrospective Study","volume":"32","author":"Gu","year":"2025","journal-title":"Acad. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sabaghian, T., Kharazmi, A.B., Ansari, A., Omidi, F., Kazemi, S.N., Hajikhani, B., Vaziri-Harami, R., Tajbakhsh, A., Omidi, S., and Haddadi, S. (2022). COVID-19 and Acute Kidney Injury: A Systematic Review. Front. Med., 9.","DOI":"10.3389\/fmed.2022.705908"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2205958","DOI":"10.1080\/0886022X.2023.2205958","article-title":"A modified renal angina index in critically ill patients with COVID-19","volume":"45","year":"2023","journal-title":"Ren. Fail."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD + AI: Updated Guidance for Reporting Clinical Prediction Models Developed or Validated Using Artificial Intelligence","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M18-1377","article-title":"PROBAST: A Tool to Assess Risk of Bias and Applicability of Prediction Model Studies","volume":"170","author":"Moons","year":"2019","journal-title":"Ann. Intern. Med."},{"key":"ref_24","unstructured":"American College of Radiology (2024). ACR Manual on Contrast Media, American College of Radiology. [2024 ed.]."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","article-title":"A Clinically Applicable Approach to Continuous Prediction of Future Acute Kidney Injury","volume":"572","author":"Glorot","year":"2019","journal-title":"Nature"},{"key":"ref_26","doi-asserted-by":"crossref","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":"ref_27","unstructured":"Johnson, A.E.W., Pollard, T.J., and Mark, R.G. (2025, December 01). MIMIC-IV (v3.1). Available online: https:\/\/physionet.org\/content\/mimiciv\/3.1\/."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center ICU database","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci. Data"},{"key":"ref_29","unstructured":"Pollard, T.J., Johnson, A.E.W., and Raffa, J.D. (2025, December 01). eICU Collaborative Research Database (v2.0). Available online: https:\/\/physionet.org\/content\/eicu-crd\/2.0\/."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201916), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Feretzakis, G., Sakagianni, A., Anastasiou, A., Kapogianni, I., Bazakidou, E., Koufopoulos, P., Koumpouros, Y., Koufopoulou, C., Kaldis, V., and Verykios, V.S. (2024). Integrating Shapley Values into Machine Learning Techniques for Enhanced Predictions of Hospital Admissions. Appl. Sci., 14.","DOI":"10.3390\/app14135925"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e496","DOI":"10.1016\/S2589-7500(20)30226-0","article-title":"Prediction models for COVID-19 clinical decision making","volume":"2","author":"Leeuwenberg","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tamargo, C., Hanouneh, M., and Cervantes, C.E. (2024). Treatment of Acute Kidney Injury: A Review of Current Approaches and Emerging Innovations. J. Clin. Med., 13.","DOI":"10.3390\/jcm13092455"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1038\/s42256-022-00563-8","article-title":"Generalizability of an acute kidney injury prediction model across health systems","volume":"4","author":"Cao","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/s41467-024-55629-5","article-title":"Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients","volume":"16","author":"Zhang","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1038\/s41581-023-00744-7","article-title":"Digital health and acute kidney injury: Consensus report of the 27th Acute Disease Quality Initiative workgroup","volume":"19","author":"Kashani","year":"2023","journal-title":"Nat. Rev. Nephrol."},{"key":"ref_38","unstructured":"Lundberg, S.M., and Lee, S.I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems 30 (NIPS 2017), Curran Associates Inc."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e2351710","DOI":"10.1001\/jamanetworkopen.2023.51710","article-title":"Automated Electronic Alert for the Care and Outcomes of Adults with Acute Kidney Injury: A Randomized Clinical Trial","volume":"7","author":"Li","year":"2024","journal-title":"JAMA Netw. Open"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/3\/1191\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T13:03:57Z","timestamp":1770123837000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/3\/1191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jcm15031191"],"URL":"https:\/\/doi.org\/10.3390\/jcm15031191","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]}}}