{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T20:19:31Z","timestamp":1772050771290,"version":"3.50.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T00:00:00Z","timestamp":1743724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pediatr."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Renal dysfunction is common in critically ill children and increases morbidity and mortality risk. Diagnosis and management of renal dysfunction relies on creatinine, a delayed marker of renal injury. We aimed to develop and validate a machine learning model using routinely collected clinical data to predict 24-hour creatinine change in critically ill children before change is observed clinically.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Retrospective cohort study of 39,932 pediatric intensive care unit encounters in a national multicenter database from 2007 to 2022. A neural network was trained to predict &amp;lt;50% or \u226550% creatinine change in the next 24\u2005h. Admission demographics, routinely measured vital signs, laboratory tests, and medication use variables were used as predictors for the model. Data set was randomly split at the encounter level into model development (80%) and test (20%) sets. Performance and clinical relevance was assessed in the test set by accuracy of prediction classification and confusion matrix metrics.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The cohort had a male predominance (53.8%), median age of 8.0 years (IQR 1.9\u221214.6), 21.0% incidence of acute kidney injury, and 2.3% mortality. The overall accuracy of the model for predicting change of &amp;lt;50% or \u226550% was 68.1% (95% CI 67.6%\u221268.7%). The accuracy of classification improved substantially with higher creatinine values from 29.9% (CI 28.9%\u221231.0%) in pairs with an admission creatinine &amp;lt;0.3\u2005mg\/dl to 90.0\u201396.3% in pairs with an admission creatinine of \u22650.6\u2005mg\/dl. The model had a negative predictive value of 97.2% and a positive predictive value of 7.1%. The number needed to evaluate to detect one true change \u226550% was 14.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>24-hour creatinine change consistent with acute kidney injury can be predicted using routine clinical data in a machine learning model, indicating risk of significant renal dysfunction before it is measured clinically. Positive predictive performance is limited by clinical reliance on creatinine.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fped.2025.1549836","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:52:13Z","timestamp":1743792733000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Development of a neural network model for early detection of creatinine change in critically Ill children"],"prefix":"10.3389","volume":"13","author":[{"given":"Celeste G.","family":"Dixon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo A.","family":"Trujillo Rivera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anita K.","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murray M.","family":"Pollack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa1611391","article-title":"Epidemiology of acute kidney injury in critically ill children and young adults","volume":"376","author":"Kaddourah","year":"2017","journal-title":"N Engl J Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1097\/PCC.0000000000002679","article-title":"Association between acute kidney injury duration and outcomes in critically ill children*","volume":"22","author":"Alobaidi","year":"2021","journal-title":"Pediatr Crit Care Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"R146","DOI":"10.1186\/cc10269","article-title":"Acute kidney injury is an independent risk factor for pediatric intensive care unit mortality, longer length of stay and prolonged mechanical ventilation in critically ill children: a two-center retrospective cohort study","volume":"15","author":"Alkandari","year":"2011","journal-title":"Crit Care"},{"key":"B4","doi-asserted-by":"publisher","first-page":"gfab219","DOI":"10.1093\/ndt\/gfab219","article-title":"Trajectory of AKI in hospitalized pediatric patients\u2014impact of duration and repeat events","volume":"37","author":"Moffett","year":"2021","journal-title":"Nephrol Dial Transplant"},{"key":"B5","doi-asserted-by":"publisher","first-page":"205435811988018","DOI":"10.1177\/2054358119880188","article-title":"Acute kidney injury in critically ill children and subsequent chronic kidney disease","volume":"6","author":"Hessey","year":"2019","journal-title":"Can J Kidney Health Dis"},{"key":"B6","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1053\/j.ajkd.2011.10.048","article-title":"Long-term risk of CKD in children surviving episodes of acute kidney injury in the intensive care unit: a prospective cohort study","volume":"59","author":"Mammen","year":"2011","journal-title":"Am J Kidney Dis"},{"key":"B7","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.jpeds.2014.04.058","article-title":"Acute kidney injury associated with high nephrotoxic medication exposure leads to chronic kidney disease after 6 months","volume":"165","author":"Menon","year":"2014","journal-title":"J Pediatr"},{"key":"B8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/kisup.2012.7","article-title":"KDIGO clinical practice guideline for acute kidney injury","volume":"2","year":"2012","journal-title":"Kidney Int Suppl"},{"key":"B9","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1681\/ASN.2008070669","article-title":"Creatinine kinetics and the definition of acute kidney injury","volume":"20","author":"Waikar","year":"2009","journal-title":"J Am Soc Nephrol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/cc9004","article-title":"Fluid accumulation, recognition and staging of acute kidney injury in critically-ill patients","volume":"14","author":"Macedo","year":"2010","journal-title":"Crit Care"},{"key":"B11","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1097\/CCM.0000000000005836","article-title":"Fluid overload precedes and masks cryptic kidney injury in pediatric acute respiratory distress syndrome","volume":"51","author":"Dixon","year":"2023","journal-title":"Crit Care Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1159\/000502381","article-title":"Comprehensive assessment of kidney health in acute kidney injury: can it be achieved?","volume":"143","author":"Macedo","year":"2019","journal-title":"Nephron"},{"key":"B13","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1203\/PDR.0b013e318189a6e8","article-title":"Impact of standardization of creatinine methodology on the assessment of glomerular filtration rate in children","volume":"65","author":"Srivastava","year":"2009","journal-title":"Pediatr Res"},{"key":"B14","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s00467-008-0957-0","article-title":"Validation of creatinine assays utilizing HPLC and IDMS traceable standards in sera of children","volume":"24","author":"Schwartz","year":"2009","journal-title":"Pediatr Nephrol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s12882-015-0012-x","article-title":"Routine serum creatinine measurements: how well do we perform?","volume":"16","author":"Hoste","year":"2015","journal-title":"BMC Nephrol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/s00467-021-05335-x","article-title":"Large inter-assay difference of serum creatinine in pediatric population: a threat to accurate staging of chronic kidney disease","volume":"37","author":"Lao","year":"2022","journal-title":"Pediatr Nephrol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"S66","DOI":"10.1542\/peds.2021-052888J","article-title":"Renal dysfunction criteria in critically ill children: the PODIUM consensus conference","volume":"149","author":"Fitzgerald","year":"2022","journal-title":"Pediatrics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"20503121241228446","DOI":"10.1177\/20503121241228446","article-title":"Review of the limitations of current biomarkers in acute kidney injury clinical practices","volume":"12","author":"Bufkin","year":"2024","journal-title":"SAGE Open Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e2349871","DOI":"10.1001\/jamanetworkopen.2023.49871","article-title":"Time to continuous renal replacement therapy initiation and 90-day major adverse kidney events in children and young adults","volume":"7","author":"Gist","year":"2024","journal-title":"JAMA Netw Open"},{"key":"B20","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1038\/ki.2013.349","article-title":"Derivation and validation of the renal angina index to improve the prediction of acute kidney injury in critically ill children","volume":"85","author":"Basu","year":"2014","journal-title":"Kidney Int"},{"key":"B21","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/S2352-4642(17)30181-5","article-title":"Assessment of a renal angina index for prediction of severe acute kidney injury in critically ill children: a multicentre, multinational, prospective observational study","volume":"2","author":"Basu","year":"2018","journal-title":"Lancet Child Adolesc Health"},{"key":"B22","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1097\/PCC.0000000000000750","article-title":"Development of a prediction model of early acute kidney injury in critically ill children using electronic health record data","volume":"17","author":"Sanchez-Pinto","year":"2016","journal-title":"Pediatr Crit Care Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1053\/j.ackd.2022.07.009","article-title":"Artificial intelligence in acute kidney injury prediction","volume":"29","author":"Bajaj","year":"2022","journal-title":"Adv Chronic Kidney Dis"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2309","DOI":"10.1007\/s00467-023-06191-7","article-title":"Artificial intelligence in early detection and prediction of pediatric\/neonatal acute kidney injury: current status and future directions","volume":"39","author":"Raina","year":"2023","journal-title":"Pediatr Nephrol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"536","DOI":"10.3389\/fped.2019.00536","article-title":"Big data and pediatric acute kidney injury: the promise of electronic health record systems","volume":"7","author":"Sutherland","year":"2020","journal-title":"Front Pediatr"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"13","author":"Collins","year":"2015","journal-title":"BMC Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1869","DOI":"10.1093\/ajhp\/zxz203","article-title":"Evidence-based development of a nephrotoxic medication list to screen for acute kidney injury risk in hospitalized children","volume":"76","author":"Goswami","year":"2019","journal-title":"Am J Health Syst Pharm"},{"key":"B28","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1097\/PCC.0000000000001123","article-title":"Fluid overload and kidney injury score: a multidimensional real-time assessment of renal disease burden in the critically ill patient*","volume":"18","author":"Akcan-Arikan","year":"2017","journal-title":"Pediatr Crit Care Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1186\/s13054-021-03724-0","article-title":"Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care","volume":"25","author":"Dong","year":"2021","journal-title":"Crit Care"},{"key":"B30","volume-title":"International Classification of Diseases: Ninth Revision, Basic Tabulation List with Alphabetic Index","year":"1978"},{"key":"B31","volume-title":"ICD\u221210: International Statistical Classification of Diseases and Related Health Problems: Tenth Revision","year":"2004"},{"key":"B32","article-title":"lime: Local Interpretable Model-Agnostic Explanations","author":"Hvitfeldt","year":"2022"},{"key":"B33","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1097\/PCC.0000000000003425","article-title":"The pediatric data science and analytics subgroup of the pediatric acute lung injury and sepsis investigators network: use of supervised machine learning applications in pediatric critical care medicine research","volume":"25","author":"Heneghan","year":"2024","journal-title":"Pediatr Crit Care Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1097\/CCM.0b013e318228234b","article-title":"Acute kidney injury in patients with acute lung injury: impact of fluid accumulation on classification of acute kidney injury and associated outcomes*","volume":"39","author":"Liu","year":"2011","journal-title":"Crit Care Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"348","DOI":"10.2215\/CJN.02870707","article-title":"Influence of muscle mass and physical activity on serum and urinary creatinine and serum cystatin C","volume":"3","author":"Baxmann","year":"2008","journal-title":"Clin J Am Soc Nephrol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1080\/10408363.2021.1879000","article-title":"Current concepts and advances in biomarkers of acute kidney injury","volume":"58","author":"Wen","year":"2021","journal-title":"Crit Rev Clin Lab Sci"},{"key":"B37","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1159\/000296250","article-title":"Variability of creatinine measurements in clinical laboratories: results from the CRIC study","volume":"31","author":"Joffe","year":"2010","journal-title":"Am J Nephrol"},{"key":"B38","doi-asserted-by":"publisher","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":"Zimmerman","year":"2019","journal-title":"BMC Med Inform Decis Mak"},{"key":"B39","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1177\/000313481908500731","article-title":"Comparing machine learning algorithms for predicting acute kidney injury","volume":"85","author":"Parreco","year":"2019","journal-title":"Am Surg"},{"key":"B40","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1016\/j.mayocp.2019.02.009","article-title":"Automated continuous acute kidney injury prediction and surveillance: a random forest model","volume":"94","author":"Chiofolo","year":"2019","journal-title":"Mayo Clin Proc"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e0288233","DOI":"10.1371\/journal.pone.0288233","article-title":"External evaluation of the dynamic criticality index: a machine learning model to predict future need for ICU care in hospitalized pediatric patients","volume":"19","author":"Patel","year":"2024","journal-title":"PLoS One"},{"key":"B42","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1002\/9781444345186.app2","article-title":"Appendix B: pediatric normal laboratory values","volume-title":"Gregory\u2019s Pediatric Anesthesia","author":"Andropoulos","year":"2012"},{"key":"B43","article-title":"Pediatric reference ranges: reference intervals and orienting ranges for clinical chemistry and laboratory medicine in fetuses, newborn, and adolescents","volume-title":"Clinical Laboratory Diagnostics","author":"Klarmann","year":"2023"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1007\/s40262-022-01143-0","article-title":"Clinical pharmacokinetics of gentamicin in various patient populations and consequences for optimal dosing for gram-negative infections: an updated review","volume":"61","author":"Hodiamont","year":"2022","journal-title":"Clin Pharmacokinet"},{"key":"B45","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/0140-6736(93)90277-N","article-title":"High serum procalcitonin concentrations in patients with sepsis and infection","volume":"341","author":"Assicot","year":"1993","journal-title":"Lancet"},{"key":"B46","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1002\/phar.2376","article-title":"Executive summary: therapeutic monitoring of vancomycin for serious methicillin-resistant staphylococcus aureus infections: a revised consensus guideline and review of the American society of health-system pharmacists, the Infectious Diseases Society of America, the pediatric infectious disease society, and the society of infectious disease pharmacists","volume":"40","author":"Rybak","year":"2020","journal-title":"Pharmacotherapy"},{"key":"B47","first-page":"304","article-title":"Hemodynamic monitoring","volume-title":"Rogers\u2019 Handbook of Pediatric Intensive Care","author":"Bronicki","year":"2017"},{"key":"B48","first-page":"118","article-title":"Respiratory physiology","volume-title":"Rogers\u2019 Handbook of Pediatric Intensive Care","author":"Powell","year":"2017"},{"key":"B49","doi-asserted-by":"publisher","first-page":"805620","DOI":"10.3389\/fphys.2021.805620","article-title":"Mechanical ventilation in pediatric and neonatal patients","volume":"12","author":"Kollisch-Singule","year":"2022","journal-title":"Front Physiol"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2025.1549836\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:52:42Z","timestamp":1743792762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2025.1549836\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,4]]},"references-count":49,"alternative-id":["10.3389\/fped.2025.1549836"],"URL":"https:\/\/doi.org\/10.3389\/fped.2025.1549836","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,4]]},"article-number":"1549836"}}