{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:21:47Z","timestamp":1793380907372,"version":"4.5.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["ICMx"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute kidney injury (AKI) is a major complication in critically ill patients, burdening both patients and healthcare systems. We previously introduced an AI-based model for early and continuous prediction of ICU-acquired AKI (ICU-A-AKI-2\/3). In this study, we enhanced the model to better handle missing data, a common challenge in clinical settings. The upgraded model was validated in both retrospective and prospective cohorts, demonstrating improved robustness and predictive performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The model was validated in retrospective cohorts from three countries (US, Netherlands, Italy; N\u2009=\u200970,107 ICU admissions) across 176 ICUs. It was then prospectively validated in three European hospitals (Italy, Spain; N\u2009=\u2009329) from May to October 2023. Using an XGBoost classifier, the model analyzes clinical data from ICU patients to predict hourly risk probabilities for AKI stages 2 and 3, as defined by KDIGO.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In retrospective cohorts, the AI model achieved an auROC greater than 0.89 for early detection of ICU-A-AKI-2\/3. Prospective validation showed auROCs between 0.82 (95% CI 0.73\u20130.92) and 0.96 (95% CI 0.92\u20130.99) across hospitals, with a mean lead time of approximately 14\u00a0h.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This enhanced AI model offers timely prediction of ICU-A-AKI-2\/3 episodes, as demonstrated across diverse cohorts. Its high predictive performance represents a significant advancement in integrating AI into clinical workflows, enhancing AKI management and improving clinical outcomes in ICU settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40635-026-00928-y","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:14:45Z","timestamp":1781075685000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Prospective and external evaluation of an AI model for continuous and early prediction of moderate and severe AKI in critically ill patients"],"prefix":"10.1186","volume":"14","author":[{"given":"Francesca","family":"Alfieri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Zappal\u00e0","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Bacci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"Cauda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Basso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaia","family":"Musso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Cochelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carmine Domenico","family":"Votta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Mariconti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Maderna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianluca","family":"Russo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josep","family":"Gomez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Esteban-Reboll","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mari Carmen","family":"Gilavert Cuevas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Bod\u00ec","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Finazzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kianoush","family":"Kashani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Ancona","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"928_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2018.09.005","author":"NM Selby","year":"2019","unstructured":"Selby NM, Taal MW (2019) Long-term outcomes after AKI\u2014a major unmet clinical need. Kidney Int. https:\/\/doi.org\/10.1016\/j.kint.2018.09.005","journal-title":"Kidney Int"},{"key":"928_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41581-018-0052-0","author":"EAJ Hoste","year":"2018","unstructured":"Hoste EAJ et al (2018) Global epidemiology and outcomes of acute kidney injury. Nat Rev Nephrol. https:\/\/doi.org\/10.1038\/s41581-018-0052-0","journal-title":"Nat Rev Nephrol"},{"issue":"6","key":"928_CR3","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.2215\/CJN.07920713","volume":"9","author":"A Wonnacott","year":"2014","unstructured":"Wonnacott A, Meran S, Amphlett B, Talabani B, Phillips A (2014) Epidemiology and outcomes in community-acquired versus hospital-acquired aki. Clin J Am Soc Nephrol 9(6):1007\u20131014. https:\/\/doi.org\/10.2215\/CJN.07920713","journal-title":"Clin J Am Soc Nephrol"},{"key":"928_CR4","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.33094","author":"NA Bianchi","year":"2021","unstructured":"Bianchi NA, Stavart LL, Altarelli M, Kelevina T, Faouzi M, Schneider AG (2021) Association of oliguria with acute kidney injury diagnosis, severity assessment, and mortality among patients with critical illness. JAMA Netw Open. https:\/\/doi.org\/10.1001\/jamanetworkopen.2021.33094","journal-title":"JAMA Netw Open"},{"issue":"3","key":"928_CR5","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1016\/j.ekir.2020.12.004","volume":"6","author":"NM Selby","year":"2021","unstructured":"Selby NM et al (2021) Randomized controlled trial evidence of cost-effectiveness of a multifaceted AKI intervention approach. Kidney Int Rep 6(3):636\u2013644. https:\/\/doi.org\/10.1016\/j.ekir.2020.12.004","journal-title":"Kidney Int Rep"},{"key":"928_CR6","doi-asserted-by":"publisher","DOI":"10.1179\/acb.2007.077","author":"DM Vandijck","year":"2007","unstructured":"Vandijck DM, Oeyen S, Decruyenaere JM, Annemans L, Hoste EA (2007) Acute kidney injury, length of stay, and costs in patients hospitalized in the intensive care unit. Acta Clin Belg. https:\/\/doi.org\/10.1179\/acb.2007.077","journal-title":"Acta Clin Belg"},{"issue":"6","key":"928_CR7","doi-asserted-by":"publisher","first-page":"417","DOI":"10.5414\/CN108072","volume":"80","author":"FP Wilson","year":"2013","unstructured":"Wilson FP et al (2013) The impact of documentation of severe acute kidney injury on mortality. Clin Nephrol 80(6):417\u2013425. https:\/\/doi.org\/10.5414\/CN108072","journal-title":"Clin Nephrol"},{"key":"928_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)60126-X","author":"RL Mehta","year":"2015","unstructured":"Mehta RL et al (2015) International Society of Nephrology\u2019s 0by25 initiative for acute kidney injury (zero preventable deaths by 2025): a human rights case for nephrology. Lancet. https:\/\/doi.org\/10.1016\/S0140-6736(15)60126-X","journal-title":"Lancet"},{"key":"928_CR9","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/B978-0-12-818438-7.00002-2","volume-title":"Artificial intelligence in healthcare","author":"A Bohr","year":"2020","unstructured":"Bohr A, Memarzadeh K (2020) The rise of artificial intelligence in healthcare applications. Artificial intelligence in healthcare. Elsevier, pp 25\u201360. https:\/\/doi.org\/10.1016\/B978-0-12-818438-7.00002-2"},{"issue":"2","key":"928_CR10","doi-asserted-by":"publisher","first-page":"376","DOI":"10.34067\/kid.0003472021","volume":"3","author":"DE Soranno","year":"2022","unstructured":"Soranno DE et al (2022) Artificial intelligence for AKI!Now: let\u2019s not await Plato\u2019s Utopian Republic. Kidney360 3(2):376\u2013381. https:\/\/doi.org\/10.34067\/kid.0003472021","journal-title":"Kidney360"},{"issue":"6","key":"928_CR11","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1007\/s40620-021-01046-6","volume":"34","author":"F Alfieri","year":"2021","unstructured":"Alfieri F et al (2021) A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients. J Nephrol 34(6):1875\u20131886. https:\/\/doi.org\/10.1007\/s40620-021-01046-6","journal-title":"J Nephrol"},{"issue":"8","key":"928_CR12","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.1007\/s40620-022-01335-8","volume":"35","author":"F Alfieri","year":"2022","unstructured":"Alfieri F et al (2022) External validation of a deep-learning model to predict severe acute kidney injury based on urine output changes in critically ill patients. J Nephrol 35(8):2047\u20132056. https:\/\/doi.org\/10.1007\/s40620-022-01335-8","journal-title":"J Nephrol"},{"key":"928_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0287398","author":"F Alfieri","year":"2023","unstructured":"Alfieri F et al (2023) Continuous and early prediction of future moderate and severe acute kidney injury in critically ill patients: development and multi-centric, multi-national external validation of a machine-learning model. PLoS ONE. https:\/\/doi.org\/10.1371\/journal.pone.0287398","journal-title":"PLoS ONE"},{"key":"928_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","author":"AEW Johnson","year":"2016","unstructured":"Johnson AEW et al (2016) Mimic-III, a freely accessible critical care database. Sci Data. https:\/\/doi.org\/10.1038\/sdata.2016.35","journal-title":"Sci Data"},{"key":"928_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178","author":"TJ Pollard","year":"2018","unstructured":"Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi O (2018) The eICU collaborative research database, a freely available multi-center database for critical care research. Sci Data. https:\/\/doi.org\/10.1038\/sdata.2018.178","journal-title":"Sci Data"},{"issue":"6","key":"928_CR16","doi-asserted-by":"publisher","first-page":"E563","DOI":"10.1097\/CCM.0000000000004916","volume":"49","author":"PJ Thoral","year":"2021","unstructured":"Thoral PJ et al (2021) Sharing ICU patient data responsibly under the Society of Critical Care Medicine\/European Society of Intensive Care Medicine Joint Data Science Collaboration: the Amsterdam University Medical Centers Database (AmsterdamUMCdb) example\u2217. Crit Care Med 49(6):E563\u2013E577. https:\/\/doi.org\/10.1097\/CCM.0000000000004916","journal-title":"Crit Care Med"},{"key":"928_CR17","unstructured":"\u201cGiViTI Gruppo Italiano per la Valutazione degli Interventi In Terapia Intensiva.\u201d www.giviti.marionegri.it"},{"issue":"8","key":"928_CR18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/aad10f","volume":"39","author":"S Finazzi","year":"2018","unstructured":"Finazzi S et al (2018) Data collection and research with MargheritaTre. Physiol Meas 39(8):084004. https:\/\/doi.org\/10.1088\/1361-6579\/aad10f","journal-title":"Physiol Meas"},{"key":"928_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/kisup.2012.1","author":"JA Kellum","year":"2012","unstructured":"Kellum JA et al (2012) Kidney disease: Improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury. Kidney Int Supl. https:\/\/doi.org\/10.1038\/kisup.2012.1","journal-title":"Kidney Int Supl."},{"issue":"6","key":"928_CR20","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1038\/ki.2009.479","volume":"77","author":"ED Siew","year":"2010","unstructured":"Siew ED et al (2010) Commonly used surrogates for baseline renal function affect the classification and prognosis of acute kidney injury. Kidney Int 77(6):536\u2013542. https:\/\/doi.org\/10.1038\/ki.2009.479","journal-title":"Kidney Int"},{"issue":"7767","key":"928_CR21","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev N et al (2019) A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572(7767):116\u2013119. https:\/\/doi.org\/10.1038\/s41586-019-1390-1","journal-title":"Nature"},{"key":"928_CR22","unstructured":"\u201cXGboost.\u201d Accessed: Mar. 21, 2024. https:\/\/xgboosting.com\/"},{"key":"928_CR23","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2016, pp. 785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"issue":"5","key":"928_CR24","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.13359","volume":"6","author":"Y Feng","year":"2023","unstructured":"Feng Y et al (2023) Characterization of risk prediction models for acute kidney injury: a systematic review and meta-analysis. JAMA Netw Open 6(5):e2313359. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.13359","journal-title":"JAMA Netw Open"},{"issue":"3","key":"928_CR25","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-054092","volume":"12","author":"Q Liang","year":"2022","unstructured":"Liang Q, Xu Y, Zhou Y, Chen X, Chen J, Huang M (2022) Severe acute kidney injury predicting model based on transcontinental databases: a single-centre prospective study. BMJ Open 12(3):e054092. https:\/\/doi.org\/10.1136\/bmjopen-2021-054092","journal-title":"BMJ Open"},{"key":"928_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103783","author":"H Sun","year":"2021","unstructured":"Sun H et al (2021) A scalable approach for developing clinical risk prediction applications in different hospitals. J Biomed Inform. https:\/\/doi.org\/10.1016\/j.jbi.2021.103783","journal-title":"J Biomed Inform"},{"key":"928_CR27","doi-asserted-by":"publisher","DOI":"10.2196\/34295","author":"H Sun","year":"2022","unstructured":"Sun H et al (2022) Machine learning-based prediction models for different clinical risks in different hospitals: evaluation of live performance. J Med Internet Res. https:\/\/doi.org\/10.2196\/34295","journal-title":"J Med Internet Res"},{"key":"928_CR28","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-019-2563-x","author":"M Flechet","year":"2019","unstructured":"Flechet M et al (2019) Machine learning versus physicians\u2019 prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor. Crit Care. https:\/\/doi.org\/10.1186\/s13054-019-2563-x","journal-title":"Crit Care"},{"key":"928_CR29","doi-asserted-by":"publisher","DOI":"10.1159\/000518365","author":"M Ostermann","year":"2022","unstructured":"Ostermann M, Karsten E, Lumlertgul N (2022) Biomarker-based management of AKI: fact or fantasy? Nephron. https:\/\/doi.org\/10.1159\/000518365","journal-title":"Nephron"},{"issue":"9","key":"928_CR30","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1681\/ASN.2014070724","volume":"26","author":"JA Kellum","year":"2015","unstructured":"Kellum JA, Sileanu FE, Murugan R, Lucko N, Shaw AD, Clermont G (2015) Classifying AKI by urine output versus serum creatinine level. J Am Soc Nephrol 26(9):2231\u20132238. https:\/\/doi.org\/10.1681\/ASN.2014070724","journal-title":"J Am Soc Nephrol"},{"issue":"12","key":"928_CR31","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1038\/s41581-023-00744-7","volume":"19","author":"KB Kashani","year":"2023","unstructured":"Kashani KB et al (2023) Digital health and acute kidney injury: consensus report of the 27th Acute Disease Quality Initiative workgroup. Nat Rev Nephrol 19(12):807\u2013818. https:\/\/doi.org\/10.1038\/s41581-023-00744-7","journal-title":"Nat Rev Nephrol"},{"issue":"11","key":"928_CR32","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1007\/s00134-016-4670-3","volume":"43","author":"M Meersch","year":"2017","unstructured":"Meersch M et al (2017) Prevention of cardiac surgery-associated AKI by implementing the KDIGO guidelines in high risk patients identified by biomarkers: the PrevAKI randomized controlled trial. Intensive Care Med 43(11):1551\u20131561. https:\/\/doi.org\/10.1007\/s00134-016-4670-3","journal-title":"Intensive Care Med"},{"issue":"2","key":"928_CR33","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1213\/ANE.0000000000005458","volume":"133","author":"A Zarbock","year":"2021","unstructured":"Zarbock A et al (2021) Prevention of cardiac surgery-associated acute kidney injury by implementing the KDIGO guidelines in high-risk patients identified by biomarkers: the PrevAKI-multicenter randomized controlled trial. Anesth Analg 133(2):292\u2013302. https:\/\/doi.org\/10.1213\/ANE.0000000000005458","journal-title":"Anesth Analg"},{"key":"928_CR34","doi-asserted-by":"publisher","DOI":"10.1186\/s44158-023-00125-3","author":"T Fragasso","year":"2023","unstructured":"Fragasso T, Raggi V, Passaro D, Tardella L, Lasinio GJ, Ricci Z (2023) Predicting acute kidney injury with an artificial intelligence-driven model in a pediatric cardiac intensive care unit. J Anesth Analg Crit Care. https:\/\/doi.org\/10.1186\/s44158-023-00125-3","journal-title":"J Anesth Analg Crit Care"},{"issue":"12","key":"928_CR35","doi-asserted-by":"publisher","first-page":"3911","DOI":"10.1093\/ndt\/gfp766","volume":"25","author":"J Z\u00e1vada","year":"2010","unstructured":"Z\u00e1vada J et al (2010) A comparison of three methods to estimate baseline creatinine for RIFLE classification. Nephrol Dial Transplant 25(12):3911\u20133918. https:\/\/doi.org\/10.1093\/ndt\/gfp766","journal-title":"Nephrol Dial Transplant"}],"container-title":["Intensive Care Medicine Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40635-026-00928-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40635-026-00928-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40635-026-00928-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T07:14:49Z","timestamp":1781075689000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40635-026-00928-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["928"],"URL":"https:\/\/doi.org\/10.1186\/s40635-026-00928-y","relation":{},"ISSN":["2197-425X"],"issn-type":[{"value":"2197-425X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"assertion":[{"value":"9 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The data collection protocol for the Margherita Tre dataset was reviewed by the coordinating ethics committee, Comitato Etico Indipendente di Area Vasta Emilia Centro (CE-VAC), and by each local ethics committee of the hospitals adopting Margherita Tre software. Informed consent was obtained in accordance with national regulations. This prospective study was performed at Maggiore Hospital in Lodi, Maria Vittoria Hospital in Turin, and Joan XXIII Hospital in Tarragona. Each hospital's local ethics committee reviewed and approved the protocol of data collection. Informed consent was obtained in accordance with national regulations. The remaining datasets were fully deidentified before access; therefore, no institutional or ethical approvals were obtained, and informed consent was waived. The Mimic-III project was evaluated and approved by the Massachusetts Institute of Technology (No. 0403000206) and the Institutional Review Board of the Beth Israel Deaconess Medical Center (2001-P-001699\/14). Individual patient consent was waived after deidentification. The eICU was not assessed by an institutional review board because of its retrospective nature, absence of direct patient intervention, and inability to reidentify patients in compliance with the safety standards of Privacert (Cambridge, MA) (Health Insurance Portability and Accountability Act Certification no. 1031219-2). The privacy audit on the Amsterdam UMC database concluded that the reidentification of patients from this database is not reasonably likely, and it can therefore be considered anonymous information in the context of the U.S. Health Insurance Portability and Accountability Act, the European General Data Protection Regulation (GDPR), and Dutch national Laws. The ethics audit also concluded that responsible data sharing imposes a minimal burden, whereas the potential benefit is tremendous.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Francesca Alfieri, Simone Zappal\u00e0, Alessandro Bacci, Valentina Cauda, and Andrea Ancona are co-holders of the European patent EP23180428, titled \u201cSystem and method for detection and prediction of kidney disease events,\u201d which is directly related to the AI model presented in this study. In addition, Andrea Ancona is CEO of U-Care Medical; Francesca Alfieri, Valentina Cauda, and Andrea Ancona are shareholders; Francesca Alfieri, Alessandro Bacci, and Simone Zappal\u00e0 are employees of the company. To mitigate potential conflicts of interest and ensure scientific integrity, the following measures were taken: (1) External and prospective validation of the model was conducted using datasets from independent hospitals not affiliated with the authors or their institutions; (2) Independent co-authors with no financial or intellectual property interests were involved in study design, data interpretation, and manuscript drafting, providing objective oversight; (3) Pre-specified protocols and analysis plans agreed with the independent hospitals were followed to reduce bias and enhance reproducibility.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"71"}}