{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:54:34Z","timestamp":1790790874886,"version":"4.1.0"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"vor","delay-in-days":20,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>Acute kidney injury (AKI) is a frequent and severe complication in critically ill patients with cardiovascular instability. Current risk scores rely on delayed renal biomarkers such as serum creatinine (sCr) and blood urea nitrogen (BUN). We aimed to develop and validate machine learning (ML) models predicting AKI and major adverse kidney events (MAKE) exclusively from systemic physiological and haemodynamic data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>Two ML models were trained on the MIMIC-IV database: one including (sCr+\/BUN+) and one excluding (sCr\u2212\/BUN\u2212) renal parameters. External validation was performed in the eICU database and in a cohort of burn ICU patients from AP-HP. Model performance was assessed for early AKI and MAKE prediction up to 100\u2005h before diagnosis. Systemic haemodynamic and physiological variables were the strongest predictors of AKI. In MIMIC-IV, the sCr\u2212\/BUN\u2212 model achieved auROC 0.78 at 72\u2005h, approaching the sCr+\/BUN+ model. In eICU, it outperformed the biomarker-based model at later time points (auROC 0.73). In the burn ICU cohort\u2014representing a high-stress systemic environment\u2014it maintained robust accuracy (auROC 0.75 at 24\u2005h, 0.77 at 72\u2005h). For MAKE prediction, the sCr\u2212\/BUN\u2212 model achieved auROC 0.87 (burn cohort), 0.67 (eICU), and 0.77 (MIMIC-IV). Median lead time for AKI prediction exceeded 70\u2005h.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI models based solely on non-renal parameters can accurately predict AKI and MAKE, even under extreme systemic stress such as severe burns. Haemodynamic signatures carry sufficient information to anticipate kidney dysfunction well in advance, opening the way to real-time, proactive cardio-renal risk stratification in ICU patients with acute heart failure, cardiogenic shock, and after cardiac surgery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztaf150","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:38:42Z","timestamp":1768394322000},"source":"Crossref","is-referenced-by-count":2,"title":["From haemodynamics to kidney risk: AI-based early prediction validated in general and burn ICU populations"],"prefix":"10.1093","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6711-4545","authenticated-orcid":false,"given":"Louis","family":"Boutin","sequence":"first","affiliation":[{"name":"Department of Anaesthesiology and Intensive Care, Universit\u00e9 Paris Cit\u00e9, H\u00f4pital Europ\u00e9en Georges Pompidou, AP-HP , 20 rue Leblanc, Paris 75015 ,","place":["France"]},{"name":"INSERM, UMR 942, MASCOT: Cardiovascular Marker in Stress Condition, Universit\u00e9 Paris Cit\u00e9, Lariboisie\u0300re Hospital, 43 bld de la chapelle , 75010 Paris ,","place":["France"]},{"name":"INSERM, UMRS 1155, CORAKID, Sorbonne Universit\u00e9 , Tenon Hospital, 4 rue de la chine, 75020 Paris ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fedi","family":"Kadri","sequence":"additional","affiliation":[{"name":"Precisia Care SA, 8 route de la corniche, 1066, Lausanne ,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arij","family":"Chaftar","sequence":"additional","affiliation":[{"name":"Precisia Care SA, 8 route de la corniche, 1066, Lausanne ,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5879-6369","authenticated-orcid":false,"given":"Benjamin","family":"Deniau","sequence":"additional","affiliation":[{"name":"INSERM, UMR 942, MASCOT: Cardiovascular Marker in Stress Condition, Universit\u00e9 Paris Cit\u00e9, Lariboisie\u0300re Hospital, 43 bld de la chapelle , 75010 Paris ,","place":["France"]},{"name":"Department of Anaesthesiology, Critical Care Medicine and Burn Unit, AP-HP, Saint-Louis Hospital, DMU Parabol, FHU PROMICE, Universite\u0301 de Paris , Paris 75010 ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sakura","family":"Minani","sequence":"additional","affiliation":[{"name":"INSERM, UMR 942, MASCOT: Cardiovascular Marker in Stress Condition, Universit\u00e9 Paris Cit\u00e9, Lariboisie\u0300re Hospital, 43 bld de la chapelle , 75010 Paris ,","place":["France"]},{"name":"Department of Anaesthesiology, Critical Care Medicine and Burn Unit, AP-HP, Saint-Louis Hospital, DMU Parabol, FHU PROMICE, Universite\u0301 de Paris , Paris 75010 ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanny M","family":"Figueroa","sequence":"additional","affiliation":[{"name":"INSERM, UMRS 1155, CORAKID, Sorbonne Universit\u00e9 , Tenon Hospital, 4 rue de la chine, 75020 Paris ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christos E","family":"Chadjichristos","sequence":"additional","affiliation":[{"name":"INSERM, UMRS 1155, CORAKID, Sorbonne Universit\u00e9 , Tenon Hospital, 4 rue de la chine, 75020 Paris ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anis","family":"Ghorbel","sequence":"additional","affiliation":[{"name":"Precisia Care SA, 8 route de la corniche, 1066, Lausanne ,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8715-7753","authenticated-orcid":false,"given":"Alexandre","family":"Mebazaa","sequence":"additional","affiliation":[{"name":"INSERM, UMR 942, MASCOT: Cardiovascular Marker in Stress Condition, Universit\u00e9 Paris Cit\u00e9, Lariboisie\u0300re Hospital, 43 bld de la chapelle , 75010 Paris ,","place":["France"]},{"name":"Department of Anaesthesiology, Critical Care Medicine and Burn Unit, AP-HP, Saint-Louis Hospital, DMU Parabol, FHU PROMICE, Universite\u0301 de Paris , Paris 75010 ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"D\u00e9pret","sequence":"additional","affiliation":[{"name":"INSERM, UMR 942, MASCOT: Cardiovascular Marker in Stress Condition, Universit\u00e9 Paris Cit\u00e9, Lariboisie\u0300re Hospital, 43 bld de la chapelle , 75010 Paris ,","place":["France"]},{"name":"Department of Anaesthesiology, Critical Care Medicine and Burn Unit, AP-HP, Saint-Louis Hospital, DMU Parabol, FHU PROMICE, Universite\u0301 de Paris , Paris 75010 ,","place":["France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,1,21]]},"reference":[{"key":"2026012112275363300_ztaf150-B1","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1007\/s00134-021-06454-7","article-title":"Acute kidney injury in the critically ill: an updated review on pathophysiology and management","volume":"47","author":"Pickkers","year":"2021","journal-title":"Intensive Care Med"},{"key":"2026012112275363300_ztaf150-B2","doi-asserted-by":"crossref","first-page":"e2019209","DOI":"10.1001\/jamanetworkopen.2020.19209","article-title":"Recommendations on acute kidney injury biomarkers from the acute disease quality initiative consensus conference: a consensus statement","volume":"3","author":"Ostermann","year":"2020","journal-title":"JAMA Netw Open"},{"key":"2026012112275363300_ztaf150-B3","first-page":"1","article-title":"Kidney disease: improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury","volume":"2","author":"Kellum","year":"2012","journal-title":"Kidney Int Suppl"},{"key":"2026012112275363300_ztaf150-B4","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1007\/s00134-017-4832-y","article-title":"Prevention of acute kidney injury and protection of renal function in the intensive care unit: update 2017: expert opinion of the Working Group on Prevention, AKI section, European Society of Intensive Care Medicine","volume":"43","author":"Joannidis","year":"2017","journal-title":"Intensive Care Med"},{"key":"2026012112275363300_ztaf150-B5","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0140-6736(24)02385-7","article-title":"Acute kidney injury","volume":"405","author":"Ostermann","year":"2025","journal-title":"Lancet"},{"key":"2026012112275363300_ztaf150-B6","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41581-021-00410-w","article-title":"Conceptual advances and evolving terminology in acute kidney disease","volume":"17","author":"Kellum","year":"2021","journal-title":"Nat Rev Nephrol"},{"key":"2026012112275363300_ztaf150-B7","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1038\/s41572-021-00284-z","article-title":"Acute kidney injury","volume":"7","author":"Kellum","year":"2021","journal-title":"Nat Rev Dis Primers"},{"key":"2026012112275363300_ztaf150-B8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1186\/s12882-025-04040-3","article-title":"Advances in the diagnosis of early biomarkers for acute kidney injury: a literature review","volume":"26","author":"Yang","year":"2025","journal-title":"BMC Nephrol"},{"key":"2026012112275363300_ztaf150-B9","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1186\/s13613-024-01360-9","article-title":"Biomarkers in acute kidney injury","volume":"14","author":"Ostermann","year":"2024","journal-title":"Ann Intensive Care"},{"key":"2026012112275363300_ztaf150-B10","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1186\/s12882-024-03793-7","article-title":"Artificial intelligence and predictive models for early detection of acute kidney injury: transforming clinical practice","volume":"25","author":"Tran","year":"2024","journal-title":"BMC Nephrol"},{"key":"2026012112275363300_ztaf150-B11","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1681\/ASN.0000000702","article-title":"Systematic review and meta-analysis of machine learning models for acute kidney injury risk classification","volume":"36","author":"Cama-Olivares","year":"2025","journal-title":"J Am Soc Nephrol"},{"key":"2026012112275363300_ztaf150-B12","first-page":"1869","article-title":"Artificial intelligence\/machine learning externally validated models for AKI risk-classification: a systematic review and meta-analysis","volume":"36","author":"Cama-Olivares","year":"2024","journal-title":"J Am Soc Nephrol"},{"key":"2026012112275363300_ztaf150-B13","doi-asserted-by":"crossref","unstructured":"Johnson AEW, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, et al \u00a0MIMIC-IV, a freely accessible electronic health record dataset. Sci Data \u00a02023;10:1\u20139.","DOI":"10.1038\/s41597-023-01945-2"},{"key":"2026012112275363300_ztaf150-B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU collaborative research database, a freely available multi-center database for critical care research","volume":"5","author":"Pollard","year":"2018","journal-title":"Sci Data"},{"key":"2026012112275363300_ztaf150-B15","doi-asserted-by":"publisher","author":"Chen","DOI":"10.48550\/arXiv.2502.17978"},{"key":"2026012112275363300_ztaf150-B16","doi-asserted-by":"crossref","first-page":"100936","DOI":"10.1016\/j.xkme.2024.100936","article-title":"Acute kidney injury prognosis prediction using machine learning methods: a systematic review","volume":"7","author":"Lin","year":"2025","journal-title":"Kidney Med"},{"key":"2026012112275363300_ztaf150-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-024-02758-y","article-title":"Exploring the role of artificial intelligence in acute kidney injury management: a comprehensive review and future research agenda","volume":"24","author":"Al-Absi","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026012112275363300_ztaf150-B18","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/ckj\/sfaa188","article-title":"External validation of prognostic models: what, why, how, when and where?","volume":"14","author":"Ramspek","year":"2021","journal-title":"Clin Kidney J"},{"key":"2026012112275363300_ztaf150-B19","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1681\/ASN.2008060617","article-title":"Reduced production of creatinine limits its use as marker of kidney injury in sepsis","volume":"20","author":"Doi","year":"2009","journal-title":"J Am Soc Nephrol"},{"key":"2026012112275363300_ztaf150-B20","doi-asserted-by":"crossref","first-page":"3304","DOI":"10.3390\/jcm10153304","article-title":"Optimization of acute kidney injury (AKI) time definitions using the electronic health record: a first step in automating in-hospital AKI detection","volume":"10","author":"Swan","year":"2021","journal-title":"J Clin Med"},{"key":"2026012112275363300_ztaf150-B21","doi-asserted-by":"crossref","first-page":"e2430401","DOI":"10.1001\/jamanetworkopen.2024.30401","article-title":"Electronic alert systems for patients with acute kidney injury: a systematic review and meta-analysis","volume":"7","author":"Chen","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026012112275363300_ztaf150-B22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13054-025-05402-x","article-title":"The influence of electronic AKI alert on prognosis of adult hospitalized patients: a systematic review and meta-analysis","volume":"29","author":"Wang","year":"2025","journal-title":"Crit Care"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/1\/ztaf150\/66519271\/ztaf150.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/1\/ztaf150\/66519271\/ztaf150.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T17:28:02Z","timestamp":1769016482000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/doi\/10.1093\/ehjdh\/ztaf150\/8435678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,21]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztaf150","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2026,1]]},"article-number":"ztaf150"}}