{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:05:57Z","timestamp":1784225157270,"version":"3.55.0"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute kidney injury remains a major cause of morbidity and mortality in critically ill patients. Existing classification systems rely on serum creatinine and urine output thresholds and do not fully capture the complex, multifactorial nature of acute kidney injury severity in the ICU.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate a machine learning model using high-dimensional clinical data to identify covariates associated with the severity of acute kidney injury and enhance early risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We performed a secondary analysis of 2,281 patients from the ICU in the MIMIC-IV database. Acute kidney injury severity was staged (0\u20133) based on serum creatinine criteria. After rigorous data cleaning, imputation, and feature selection, an XGBoost model was trained. Model performance was assessed, and gain-based metrics were used to identify the most important predictors of acute kidney injury severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated favorable discriminative performance, with an overall accuracy of 77.6% and a mean absolute error of 0.241. It achieved high precision and recall for stage 0 (precision\u2009=\u20090.917) and stage 3 (recall\u2009=\u20090.837), but showed decreased performance for stage 2. The top 10 covariates associated with increasing acute kidney injury severity were chronic kidney disease, sepsis, total bilirubin, norepinephrine, vasopressin, furosemide, phenylephrine, phosphate, potassium, and platelet count.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our machine learning-based model effectively identified key covariates of acute kidney injury severity in ICU patients using routinely collected clinical data. The findings provide a foundation for early identification, risk stratification, and targeted intervention strategies for acute kidney injury in critical care settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0352314","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T17:33:11Z","timestamp":1784223191000},"page":"e0352314","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Acute kidney injury severity in ICU patients: Developing and evaluating a data-driven analysis of clinical covariates using machine learning"],"prefix":"10.1371","volume":"21","author":[{"given":"Mohammad","family":"Fathi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nader","family":"Markazi Moghaddam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahdis","family":"Fathi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammadreza","family":"Hajiesmaeili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navid","family":"Nooraei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasser","family":"Malekpour Alamdari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanaz","family":"Zargar Balaye Jame","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5416-1534","authenticated-orcid":true,"given":"Hamed","family":"Markazi Moghadam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"issue":"6","key":"pone.0352314.ref001","doi-asserted-by":"crossref","first-page":"387","DOI":"10.28982\/josam.7827","article-title":"The relationship of KDIGO classification and incidence & mortality of acute kidney injury in sepsis patients in intensive care unit: a retrospective cohort study","volume":"7","author":"BBT Mecit","year":"2023","journal-title":"J Surg Med"},{"issue":"5","key":"pone.0352314.ref002","first-page":"365","article-title":"Comparison between RIFLE, AKIN, and KDIGO: acute kidney injury definition criteria for prediction of in-hospital mortality in critically ill patients","volume":"14","author":"RE Er","year":"2020","journal-title":"Iran J Kidney Dis"},{"issue":"4","key":"pone.0352314.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1003969","article-title":"Use of an extended KDIGO definition to diagnose acute kidney injury in patients with COVID-19: a multinational study using the ISARIC-WHO clinical characterisation protocol","volume":"19","author":"M Wainstein","year":"2022","journal-title":"PLoS Med"},{"issue":"5","key":"pone.0352314.ref004","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1093\/ckj\/sfab256","article-title":"Incorrect application of the KDIGO acute kidney injury staging criteria","volume":"15","author":"IAR Yasrebi-de Kom","year":"2021","journal-title":"Clin Kidney J"},{"issue":"4","key":"pone.0352314.ref005","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1590\/2175-8239-jbn-2020-0191","article-title":"Epidemiological profile of acute kidney injury in critically ill patients admitted to intensive care units: a Prospective Brazilian Cohort","volume":"43","author":"AJ Inda-Filho","year":"2021","journal-title":"J Bras Nefrol"},{"issue":"1","key":"pone.0352314.ref006","first-page":"2028","article-title":"Performance of the renal resistive index and usual clinical indicators in predicting persistent AKI","volume":"44","author":"Y Fu","year":"2022","journal-title":"Ren Fail"},{"issue":"1","key":"pone.0352314.ref007","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1080\/0886022X.2022.2027247","article-title":"The predictive value of the Oxford Acute Severity of Illness Score for clinical outcomes in patients with acute kidney injury","volume":"44","author":"N Wang","year":"2022","journal-title":"Ren Fail"},{"key":"pone.0352314.ref008","article-title":"Machine learning-based prediction of acute kidney injury in patient admitted to ICU with sepsis: a systematic review of clinical evidence","author":"JD Stubnya","year":"2024","journal-title":"J Crit Intensive Care"},{"issue":"4","key":"pone.0352314.ref009","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s10157-026-02824-x","article-title":"Illness severity modifies the association between sepsis and survival in critically ill patients with acute kidney injury","volume":"30","author":"M Derakhshan","year":"2026","journal-title":"Clin Exp Nephrol"},{"issue":"4","key":"pone.0352314.ref010","doi-asserted-by":"crossref","first-page":"323","DOI":"10.21037\/atm-20-5723","article-title":"Development and validation of a risk stratification model for predicting the mortality of acute kidney injury in critical care patients","volume":"9","author":"H Huang","year":"2021","journal-title":"Ann Transl Med"},{"issue":"11","key":"pone.0352314.ref011","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.3390\/biomedicines13112575","article-title":"Impact of early initiation of renal replacement therapy on renal recovery and mortality in critically ill patients with acute kidney injury: a prospective cohort study","volume":"13","author":"RA Moreira","year":"2025","journal-title":"Biomedicines"},{"issue":"1","key":"pone.0352314.ref012","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1053\/j.ajkd.2022.06.004","article-title":"Prediction of mortality and major adverse kidney events in critically ill patients with acute kidney injury","volume":"81","author":"JA Neyra","year":"2023","journal-title":"Am J Kidney Dis"},{"issue":"4","key":"pone.0352314.ref013","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1097\/SHK.0000000000001768","article-title":"A prediction model for assessing prognosis in critically ill patients with sepsis-associated acute kidney injury","volume":"56","author":"H Hu","year":"2021","journal-title":"Shock"},{"issue":"5","key":"pone.0352314.ref014","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1016\/j.ekir.2021.02.031","article-title":"Convolutional neural network model for intensive care unit acute kidney injury prediction","volume":"6","author":"S Le","year":"2021","journal-title":"Kidney Int Rep"},{"issue":"3","key":"pone.0352314.ref015","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.3390\/jcm15031191","article-title":"Forecasting ICU acute kidney injury with actionable lead time using interpretable machine learning: development and multi-center validation","volume":"15","author":"AZ Hourani","year":"2026","journal-title":"J Clin Med"},{"issue":"5","key":"pone.0352314.ref016","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1053\/j.ajkd.2013.02.349","article-title":"KDOQI US commentary on the 2012 KDIGO clinical practice guideline for acute kidney injury","volume":"61","author":"PM Palevsky","year":"2013","journal-title":"Am J Kidney Dis"},{"issue":"1","key":"pone.0352314.ref017","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":"AEW Johnson","year":"2023","journal-title":"Sci Data"},{"issue":"4","key":"pone.0352314.ref018","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1093\/mr\/road076","article-title":"Development and validation of a clinical model for predicting the severity of carpal tunnel syndrome","volume":"34","author":"B Aalaie","year":"2024","journal-title":"Mod Rheumatol"},{"issue":"1","key":"pone.0352314.ref019","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1186\/s13054-025-05573-7","article-title":"The effects of vasopressor choice on renal outcomes in septic shock: a systematic review of randomised trials as a guide for future research","volume":"29","author":"R McDonald","year":"2025","journal-title":"Crit Care"},{"key":"pone.0352314.ref020","first-page":"8753764","article-title":"Incidence, risk factors, and outcome of acute kidney injury in the intensive care unit: a single-center study from Jordan","volume":"2020","author":"AO Oweis","year":"2020","journal-title":"Crit Care Res Pract"},{"key":"pone.0352314.ref021","doi-asserted-by":"crossref","first-page":"21","DOI":"10.54112\/pjicm.v4i01.22","article-title":"A single-center study evaluating the prevalence, risk factors, and consequences of acute kidney injury in the intensive care unit","volume":"4","author":"R Pervaiz","year":"2024","journal-title":"Pak J Intensive Care Med"},{"key":"pone.0352314.ref022","doi-asserted-by":"crossref","first-page":"1055137","DOI":"10.3389\/fmed.2023.1055137","article-title":"Development and validation of a dynamic online nomogram for predicting acute kidney injury in cirrhotic patients upon ICU admission","volume":"10","author":"L-H Feng","year":"2023","journal-title":"Front Med (Lausanne)"},{"issue":"12","key":"pone.0352314.ref023","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.5005\/jp-journals-10071-24372","article-title":"Evaluation of predictors, kinetics of renal recovery and outcomes of COVID-19 patients with acute kidney injury admitted to intensive care unit: an observational study","volume":"26","author":"KK Gudivada","year":"2022","journal-title":"Indian J Crit Care Med"},{"issue":"3","key":"pone.0352314.ref024","doi-asserted-by":"crossref","first-page":"351","DOI":"10.17219\/acem\/186814","article-title":"Association of anion gap and albumin corrected anion gap with acute kidney injury in patients with acute ischemic stroke","volume":"34","author":"H Yao","year":"2025","journal-title":"Adv Clin Exp Med"},{"issue":"5","key":"pone.0352314.ref025","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.3390\/biomedicines10051081","article-title":"Predictors of acute kidney disease severity in hospitalized patients with acute kidney injury","volume":"10","author":"P-C Hsu","year":"2022","journal-title":"Biomedicines"},{"key":"pone.0352314.ref026","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/s12911-019-0733-z","article-title":"Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements","volume":"19","author":"LP Zimmerman","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"pone.0352314.ref027","doi-asserted-by":"crossref","first-page":"20543581221145073","DOI":"10.1177\/20543581221145073","article-title":"Risk factors of AKI in acute respiratory distress syndrome: a time-dependent competing risk analysis on severe COVID-19 patients","volume":"10","author":"A Marchiset","year":"2023","journal-title":"Can J Kidney Health Dis"},{"issue":"6","key":"pone.0352314.ref028","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1007\/s40620-020-00793-2","article-title":"AKI: an increasingly recognized risk factor for CKD development and progression","volume":"33","author":"JT Kurzhagen","year":"2020","journal-title":"J Nephrol"},{"issue":"8","key":"pone.0352314.ref029","doi-asserted-by":"crossref","first-page":"2574","DOI":"10.3390\/jcm9082574","article-title":"Molecular mechanisms of AKI in the elderly: from animal models to therapeutic intervention","volume":"9","author":"B Infante","year":"2020","journal-title":"J Clin Med"},{"issue":"11","key":"pone.0352314.ref030","doi-asserted-by":"crossref","first-page":"1813","DOI":"10.1093\/ckj\/sfad107","article-title":"Update on persistent acute kidney injury in critical illnesses","volume":"16","author":"S Samoni","year":"2023","journal-title":"Clin Kidney J"},{"issue":"3","key":"pone.0352314.ref031","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1053\/j.ajkd.2022.08.028","article-title":"Intensive care unit-acquired weakness in patients with acute kidney injury: a contemporary review","volume":"81","author":"JP Teixeira","year":"2023","journal-title":"Am J Kidney Dis"},{"key":"pone.0352314.ref032","doi-asserted-by":"crossref","DOI":"10.1093\/ndt\/gfaa142.P0610","article-title":"P0610 acute kidney injury in critically ill patients in the ICU","volume":"35","author":"M Markovic","year":"2020","journal-title":"Nephrol Dial Transplant"},{"issue":"8","key":"pone.0352314.ref033","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.34067\/KID.0001632022","article-title":"Refractoriness of hyperkalemia and hyperphosphatemia in dialysis-dependent AKI associated with COVID-19","volume":"3","author":"SR Kanduri","year":"2022","journal-title":"Kidney360"},{"key":"pone.0352314.ref034","article-title":"Dynamic biomarker assessment: a diagnostic paradigm to match the AKI syndrome","volume":"7","author":"RK Basu","year":"2020","journal-title":"Front Pediatr"},{"key":"pone.0352314.ref035","doi-asserted-by":"crossref","DOI":"10.1093\/ndt\/gfaa142.P0654","article-title":"P0654 interest of screening for CKD after AKI in ICU and the place of Cystatin C in this population","volume":"35","author":"G Claisse","year":"2020","journal-title":"Nephrol Dial Transplant"},{"issue":"2","key":"pone.0352314.ref036","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.semnephrol.2020.01.011","article-title":"Pathophysiology of AKI to CKD progression","volume":"40","author":"Y Sato","year":"2020","journal-title":"Semin Nephrol"},{"issue":"1","key":"pone.0352314.ref037","doi-asserted-by":"crossref","first-page":"2488139","DOI":"10.1080\/0886022X.2025.2488139","article-title":"The critical role of ion channels in kidney disease: perspective from AKI and CKD","volume":"47","author":"CSZ Li","year":"2025","journal-title":"Ren Fail"},{"issue":"5","key":"pone.0352314.ref038","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1093\/ndt\/gfx026","article-title":"A risk prediction score for acute kidney injury in the intensive care unit","volume":"32","author":"R Malhotra","year":"2017","journal-title":"Nephrol Dial Transplant"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T17:33:19Z","timestamp":1784223199000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352314"}},"subtitle":[],"editor":[{"given":"Giuseppe","family":"Remuzzi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":38,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352314","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]}}}