A Big Data Approach to Predict NEOnatal Acute Kidney Injury in Newborns expoSed to nephroTOxic Drugs (NeoAKI STOP)

Acute Kidney Injury Clinical Trial

— NeoAKISTOP  

Official title:

Predicting Acute Kidney Injury in Infants Exposed to Nephrotoxic Drugs: A Big Data Approach to Predict NEOnatal Acute Kidney Injury in Newborns expoSed to nephroTOxic Drugs. (NeoAKI STOP)

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT05851222
• Other study ID #: NeoAKI STOP
• Status: Not yet recruiting
• Start date: August 1, 2023
• Est. completion date: December 31, 2024

Study information

• Verified date: May 2023
• Source: Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico
• Contact: Giacomo Cavallaro, MD, PhD
• Phone: +390255032234
• Email: giacomo.cavallaro[@]policlinico.mi.it
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

This observational retrospective study aims to learn about the incidence of acute kidney (AKI) injury in newborns in infants exposed to nephrotoxic drugs with a big data approach. The main question it aims to answer are: - Develop a model that can predict the occurrence of AKI in infants admitted to the NICU; - Identify the drug or combination of drugs associated with an increased risk of AKI. The group of infants exposed to drugs will be defined based on exposure for at least 1-day tone one or more therapies commonly used in the NICU. Once the AKI event has occurred, the observation of the trend of daily creatinine and diuresis values will be continued for the period covered by the study.

Description:

1. Rationale and background Acute Kidney Injury (AKI) is defined as the sudden impairment of kidney function that results in altered hydro electrolyte balance and renal waste product elimination. Extensive evidence shows that the onset of AKI in critically ill pediatric patients is associated with an increased risk of death and a longer length of hospitalization. Furthermore, in patients who survive an episode of AKI, there is an increased risk of developing long-term morbidity, particularly Chronic Kidney Disease (CKD). The neonatal kidney has numerous features on the pathophysiological level that predispose this population more to AKI than at other life ages. In addition to the peculiarities related to the development and physiology of the kidney, especially if preterm, infants admitted to the NICU are exposed to multiple risk factors that may contribute to the onset of AKI. A recent multicenter study conducted in neonatal intensive care units in Canada, Australia, India, and the United States reported an overall incidence of AKI of 29.9% and showed that the development of AKI is an independent risk factor for death and prolonged hospitalization. The incidence of AKI by gestational age also showed a typical U-shaped distribution, with the greater occurrence at the two extremes represented by infants with gestational ages >36 weeks (36.7%) and <29 weeks (47.9%), while the lowest value was recorded in the 29-36 weeks range. The risk of developing acute kidney injury is known to increase with the number of medications used (especially if > 3) and the duration of exposure, especially for the aminoglycoside antibiotic category. In addition, critically ill patients who developed AKI were generally more exposed to nephrotoxic drugs than those who did not develop AKI. In the NICU setting, it is estimated that 87% of VLBW infants are exposed to at least one nephrotoxic drug during their hospital stay, and about a quarter of these infants develop at least one episode of acute renal distress. The diagnosis of AKI is based on increased serum creatinine (SCr) or decreased urinary output. To date, the definition of acute kidney injury is based on the former Kidney Disease Improving Global Outcomes (KIDGO) criteria modified for newborns. However, in light of the premises made, it can be understood how creatinine monitoring allows only passive observation of the phenomenon, noting the rise in creatinine values when renal insult has already occurred by then. This allows only retrospective changes in some aspects of the infant's management, such as optimizing fluid intake, suspending the administration of nephrotoxic drugs, and correcting any electrolyte imbalances, but without being able to prevent the onset of AKI. Ideally, the investigators should be able to understand and predict how different risk factors contribute to the beginning of renal damage in a given patient, thus allowing individualized management. Given the complexity of patients admitted to the NICU and the number of variables in the field, the problem lends itself well to analysis through AI and general statistical inference methods. Such methods have previously been used successfully for studies on adult patients but, to our knowledge, never on newborn patients. The investigators hope to apply these models in a prospective cohort study to validate their use and develop a real-time monitoring system of the kidney well-being of our nephrotoxic drug-exposed infants that can guide the clinician in patient management. Indeed, systematic surveillance of at-risk patients can significantly reduce the onset of kidney damage and limit both short-term and long-term consequences, thereby improving neonatal outcomes. 2. Research question and objectives 2.1 Primary objectives - Develop a model that can predict the occurrence of AKI in infants admitted to the NICU; - Identify the drug or combination associated with an increased risk of AKI. 2.2 Secondary objectives - Identify subgroups of patients at increased risk of AKI; - Identify time windows at increased risk of AKI during NICU admission. 3. Methods 3.1 Study design Single-center retrospective observational cohort study at the UOC of Neonatology and Neonatal Intensive Care Unit of Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Milan, Italy. 3.1.1 Primary endpoints • Development of AKI defined according to modified KIDGO criteria for the newborn based on increased serum creatinine values or reduced mean hourly diuresis during NICU admission. 3.1.2 Secondary endpoints - Number of AKI cases in risk subcategories: very low birth weight (birth weight < 1500 g), extremely low birth weight (birth weight < 1000 g), cardiopathic, with surgical pathology, sepsis, asphyxia; - Number of AKI cases in the first week of hospitalization compared with other periods. 4. Setting A population of infants admitted to the NICU of the Foundation will be retrospectively considered. 4.1 Study population The study population will consist of patients born between January 2010 and December 2022. 5. Inclusion criteria • Patients who meet all of the following criteria will be included in the study: - born between 01/01/2010 and 31/12/2022; - admitted within 24 hours of birth in the NICU (both inborn and outborn); - availability of at least two serum creatinine values or a daily hourly diuresis assessment in the first 30 days of life. 6. Exclusion Criteria Patients who meet even one of the following criteria will be excluded: - pre- or postnatal diagnosis of severe urologic and/or nephrologic pathology on a malformative and/or genetic basis; - finding of serum creatinine > 2 mg/dl in the first 24 hours of life; - genetic conditions that may impact patient survival or renal function; - length of stay in the NICU less than 48 hours (death or transfer to another department); - infants undergoing ECMO. 7. Variables Clinical and instrumental data regarding each patient's medical history will be acquired for the NICU admission by the first month of life. Definition of AKI All available serum creatinine values for each patient during the NICU admission will be recorded, considering that determinations made within the first 48 hours of the infant's life are affected by maternal creatinine values. The presence of AKI will be determined according to the modified KIDGO criteria for the newborn, as reported in previous work in the neonatal setting. Exposure to drugs. The group of infants exposed to drugs will be defined based on exposure for at least 1-day tone one or more therapies commonly used in the NICU. Special attention will be given to exposure to antibiotics, antivirals, antifungals, diuretics, anti-inflammatories, inotropes, and vasopressors. In addition to the active ingredient, other significant data such as prescribed dose, administration route, treatment duration, and temporal relationship between treatment and diagnosis of AKI will also be considered. Once the AKI event has occurred, the observation of the trend of daily creatinine and diuresis values will be continued for the period covered by the study. 8. Source documents Data will be collected from each newborn's Neocare electronic medical record (GPI SpA). 9. Sample size Approximately 600 newborns are admitted to the neonatal intensive care unit each year. The incidence of renal damage in the critically ill newborn population is reported in the literature to be approximately 30%. In light of these considerations, over the decade of our observation, the estimated number of infants admitted to the NICU is about 6000 patients. Assuming a 30% drop-out related to exclusion criteria (about 1800 subjects), the investigators expect to be able to include approximately 4200 subjects in the study, among whom the investigators should find about 1200 cases of acute renal damage. 10. Data management Data will be collected anonymously by assigning a code to each patient. They will then be organized and stored on data storage systems with secure access. 11. Data Analysis Data will be analyzed using statistical inference approaches peculiar to Data Science and Artificial Intelligence (AI), such as Decision Trees, Logistic Regression, and Machine Learning (ML). The data themselves will suggest the choice of methods used. 12. Primary endpoint: analysis Identifying patterns or items in the administration of so-called off-label drugs in the neonatal patient (premature or not) and the development of renal syndromes related to the administration of the drug itself. Once one or more correlation factors have been identified, they could be entered within the Electronic Medical Record system (and in particular within the Clinical Decision Support System) in order to be able to alert the treating clinical staff of any clinical risk associated with the administration. 13. Secondary endpoint: analysis Development of a computational Early Warning model for AKI that ensures the interpretability of the prediction.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 4200
• Est. completion date: December 31, 2024
• Est. primary completion date: September 30, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• born between 01/01/2010 and 31/12/2022;
• admitted within 24 hours of birth in the NICU (both inborn and outborn);
• availability of at least two serum creatinine values or a daily hourly diuresis assessment in the first 30 days of life.

Exclusion Criteria:

• pre- or postnatal diagnosis of severe urologic and/or nephrologic pathology on a malformative and/or genetic basis;
• finding of serum creatinine > 2 mg/dl in the first 24 hours of life;
• genetic conditions that may impact patient survival or renal function;
• length of stay in the NICU less than 48 hours (death or transfer to another department);
• infants undergoing ECMO.

Related Conditions & MeSH terms

• Acute Kidney Injury
• Drug Interaction
• Drug Toxicity
• Drug Use
• Drug-Induced Nephropathy
• Drug-Related Side Effects and Adverse Reactions
• Machine Learning
• Newborn Morbidity
• Premature Birth
• Wounds and Injuries

Locations

Country	Name	City	State
Italy	Neonatal Intensive Care Unit, Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico	Milan	MI

Sponsors (1)

Lead Sponsor	Collaborator
Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico

Country where clinical trial is conducted

Italy, 

References & Publications (44)

Abitbol CL, Seeherunvong W, Galarza MG, Katsoufis C, Francoeur D, Defreitas M, Edwards-Richards A, Master Sankar Raj V, Chandar J, Duara S, Yasin S, Zilleruelo G. Neonatal kidney size and function in preterm infants: what is a true estimate of glomerular — View Citation

Askenazi D, Patil NR, Ambalavanan N, Balena-Borneman J, Lozano DJ, Ramani M, Collins M, Griffin RL. Acute kidney injury is associated with bronchopulmonary dysplasia/mortality in premature infants. Pediatr Nephrol. 2015 Sep;30(9):1511-8. doi: 10.1007/s004 — View Citation

Askenazi DJ, Feig DI, Graham NM, Hui-Stickle S, Goldstein SL. 3-5 year longitudinal follow-up of pediatric patients after acute renal failure. Kidney Int. 2006 Jan;69(1):184-9. doi: 10.1038/sj.ki.5000032. — View Citation

Askenazi DJ, Koralkar R, Hundley HE, Montesanti A, Parwar P, Sonjara S, Ambalavanan N. Urine biomarkers predict acute kidney injury in newborns. J Pediatr. 2012 Aug;161(2):270-5.e1. doi: 10.1016/j.jpeds.2012.02.007. Epub 2012 Mar 16. — View Citation

Askenazi DJ, Koralkar R, Hundley HE, Montesanti A, Patil N, Ambalavanan N. Fluid overload and mortality are associated with acute kidney injury in sick near-term/term neonate. Pediatr Nephrol. 2013 Apr;28(4):661-6. doi: 10.1007/s00467-012-2369-4. Epub 201 — View Citation

Askenazi DJ, Koralkar R, Levitan EB, Goldstein SL, Devarajan P, Khandrika S, Mehta RL, Ambalavanan N. Baseline values of candidate urine acute kidney injury biomarkers vary by gestational age in premature infants. Pediatr Res. 2011 Sep;70(3):302-6. doi: 1 — View Citation

Askenazi DJ, Montesanti A, Hundley H, Koralkar R, Pawar P, Shuaib F, Liwo A, Devarajan P, Ambalavanan N. Urine biomarkers predict acute kidney injury and mortality in very low birth weight infants. J Pediatr. 2011 Dec;159(6):907-12.e1. doi: 10.1016/j.jped — View Citation

Auron A, Mhanna MJ. Serum creatinine in very low birth weight infants during their first days of life. J Perinatol. 2006 Dec;26(12):755-60. doi: 10.1038/sj.jp.7211604. Epub 2006 Oct 12. — View Citation

Brion LP, Fleischman AR, McCarton C, Schwartz GJ. A simple estimate of glomerular filtration rate in low birth weight infants during the first year of life: noninvasive assessment of body composition and growth. J Pediatr. 1986 Oct;109(4):698-707. doi: 10 — View Citation

Carmody JB, Charlton JR. Short-term gestation, long-term risk: prematurity and chronic kidney disease. Pediatrics. 2013 Jun;131(6):1168-79. doi: 10.1542/peds.2013-0009. Epub 2013 May 13. — View Citation

Carmody JB, Swanson JR, Rhone ET, Charlton JR. Recognition and reporting of AKI in very low birth weight infants. Clin J Am Soc Nephrol. 2014 Dec 5;9(12):2036-43. doi: 10.2215/CJN.05190514. Epub 2014 Oct 3. — View Citation

Drukker A, Guignard JP. Renal aspects of the term and preterm infant: a selective update. Curr Opin Pediatr. 2002 Apr;14(2):175-82. doi: 10.1097/00008480-200204000-00006. — View Citation

Faa G, Gerosa C, Fanni D, Nemolato S, Locci A, Cabras T, Marinelli V, Puddu M, Zaffanello M, Monga G, Fanos V. Marked interindividual variability in renal maturation of preterm infants: lessons from autopsy. J Matern Fetal Neonatal Med. 2010 Oct;23 Suppl — View Citation

Gadepalli SK, Selewski DT, Drongowski RA, Mychaliska GB. Acute kidney injury in congenital diaphragmatic hernia requiring extracorporeal life support: an insidious problem. J Pediatr Surg. 2011 Apr;46(4):630-635. doi: 10.1016/j.jpedsurg.2010.11.031. — View Citation

Gameiro J, Branco T, Lopes JA. Artificial Intelligence in Acute Kidney Injury Risk Prediction. J Clin Med. 2020 Mar 3;9(3):678. doi: 10.3390/jcm9030678. — View Citation

Genc G, Ozkaya O, Avci B, Aygun C, Kucukoduk S. Kidney injury molecule-1 as a promising biomarker for acute kidney injury in premature babies. Am J Perinatol. 2013 Mar;30(3):245-52. doi: 10.1055/s-0032-1323587. Epub 2012 Aug 8. — View Citation

Guignard JP, Drukker A. Why do newborn infants have a high plasma creatinine? Pediatrics. 1999 Apr;103(4):e49. doi: 10.1542/peds.103.4.e49. — View Citation

Jetton JG, Askenazi DJ. Acute kidney injury in the neonate. Clin Perinatol. 2014 Sep;41(3):487-502. doi: 10.1016/j.clp.2014.05.001. Epub 2014 Jul 22. — View Citation

Jetton JG, Boohaker LJ, Sethi SK, Wazir S, Rohatgi S, Soranno DE, Chishti AS, Woroniecki R, Mammen C, Swanson JR, Sridhar S, Wong CS, Kupferman JC, Griffin RL, Askenazi DJ; Neonatal Kidney Collaborative (NKC). Incidence and outcomes of neonatal acute kidn — View Citation

Jetton JG, Guillet R, Askenazi DJ, Dill L, Jacobs J, Kent AL, Selewski DT, Abitbol CL, Kaskel FJ, Mhanna MJ, Ambalavanan N, Charlton JR; Neonatal Kidney Collaborative. Assessment of Worldwide Acute Kidney Injury Epidemiology in Neonates: Design of a Retro — View Citation

Jose PA, Fildes RD, Gomez RA, Chevalier RL, Robillard JE. Neonatal renal function and physiology. Curr Opin Pediatr. 1994 Apr;6(2):172-7. doi: 10.1097/00008480-199404000-00009. — View Citation

Koralkar R, Ambalavanan N, Levitan EB, McGwin G, Goldstein S, Askenazi D. Acute kidney injury reduces survival in very low birth weight infants. Pediatr Res. 2011 Apr;69(4):354-8. doi: 10.1203/PDR.0b013e31820b95ca. — View Citation

Mammen C, Al Abbas A, Skippen P, Nadel H, Levine D, Collet JP, Matsell DG. Long-term risk of CKD in children surviving episodes of acute kidney injury in the intensive care unit: a prospective cohort study. Am J Kidney Dis. 2012 Apr;59(4):523-30. doi: 10. — View Citation

Mathur NB, Agarwal HS, Maria A. Acute renal failure in neonatal sepsis. Indian J Pediatr. 2006 Jun;73(6):499-502. doi: 10.1007/BF02759894. — View Citation

Miall LS, Henderson MJ, Turner AJ, Brownlee KG, Brocklebank JT, Newell SJ, Allgar VL. Plasma creatinine rises dramatically in the first 48 hours of life in preterm infants. Pediatrics. 1999 Dec;104(6):e76. doi: 10.1542/peds.104.6.e76. — View Citation

Paton JB, Fisher DE, DeLannoy CW, Behrman RE. Umbilical blood flow, cardiac output, and organ blood flow in the immature baboon fetus. Am J Obstet Gynecol. 1973 Oct 15;117(4):560-6. doi: 10.1016/0002-9378(73)90122-1. No abstract available. — View Citation

Rhone ET, Carmody JB, Swanson JR, Charlton JR. Nephrotoxic medication exposure in very low birth weight infants. J Matern Fetal Neonatal Med. 2014 Sep;27(14):1485-90. doi: 10.3109/14767058.2013.860522. Epub 2013 Nov 29. — View Citation

Rodriguez MM, Gomez AH, Abitbol CL, Chandar JJ, Duara S, Zilleruelo GE. Histomorphometric analysis of postnatal glomerulogenesis in extremely preterm infants. Pediatr Dev Pathol. 2004 Jan-Feb;7(1):17-25. doi: 10.1007/s10024-003-3029-2. — View Citation

Rudolph, A. M., Heymann, M. A., Teramo, K. A., Barrett, C. T., & Räihä, N. C. Studies on the circulation of the previable human fetus. Pediatric Research, 1971, 5.9: 452-465.

Saint-Faust M, Boubred F, Simeoni U. Renal development and neonatal adaptation. Am J Perinatol. 2014 Oct;31(9):773-80. doi: 10.1055/s-0033-1361831. Epub 2014 Mar 12. — View Citation

Salerno SN, Liao Y, Jackson W, Greenberg RG, McKinzie CJ, McCallister A, Benjamin DK, Laughon MM, Sanderson K, Clark RH, Gonzalez D. Association between Nephrotoxic Drug Combinations and Acute Kidney Injury in the Neonatal Intensive Care Unit. J Pediatr. — View Citation

Sarafidis K, Tsepkentzi E, Agakidou E, Diamanti E, Taparkou A, Soubasi V, Papachristou F, Drossou V. Serum and urine acute kidney injury biomarkers in asphyxiated neonates. Pediatr Nephrol. 2012 Sep;27(9):1575-82. doi: 10.1007/s00467-012-2162-4. Epub 2012 — View Citation

Sarafidis K, Tsepkentzi E, Diamanti E, Agakidou E, Taparkou A, Soubasi V, Papachristou F, Drossou V. Urine neutrophil gelatinase-associated lipocalin to predict acute kidney injury in preterm neonates. A pilot study. Pediatr Nephrol. 2014 Feb;29(2):305-10 — View Citation

Sarkar S, Askenazi DJ, Jordan BK, Bhagat I, Bapuraj JR, Dechert RE, Selewski DT. Relationship between acute kidney injury and brain MRI findings in asphyxiated newborns after therapeutic hypothermia. Pediatr Res. 2014 Mar;75(3):431-5. doi: 10.1038/pr.2013 — View Citation

Selewski DT, Charlton JR, Jetton JG, Guillet R, Mhanna MJ, Askenazi DJ, Kent AL. Neonatal Acute Kidney Injury. Pediatrics. 2015 Aug;136(2):e463-73. doi: 10.1542/peds.2014-3819. Epub 2015 Jul 13. — View Citation

Selewski DT, Jordan BK, Askenazi DJ, Dechert RE, Sarkar S. Acute kidney injury in asphyxiated newborns treated with therapeutic hypothermia. J Pediatr. 2013 Apr;162(4):725-729.e1. doi: 10.1016/j.jpeds.2012.10.002. Epub 2012 Nov 10. — View Citation

Slater MB, Gruneir A, Rochon PA, Howard AW, Koren G, Parshuram CS. Identifying High-Risk Medications Associated with Acute Kidney Injury in Critically Ill Patients: A Pharmacoepidemiologic Evaluation. Paediatr Drugs. 2017 Feb;19(1):59-67. doi: 10.1007/s40 — View Citation

Stoops C, Sims B, Griffin R, Askenazi DJ. Neonatal Acute Kidney Injury and the Risk of Intraventricular Hemorrhage in the Very Low Birth Weight Infant. Neonatology. 2016;110(4):307-312. doi: 10.1159/000445931. Epub 2016 Aug 5. — View Citation

Stoops C, Stone S, Evans E, Dill L, Henderson T, Griffin R, Goldstein SL, Coghill C, Askenazi DJ. Baby NINJA (Nephrotoxic Injury Negated by Just-in-Time Action): Reduction of Nephrotoxic Medication-Associated Acute Kidney Injury in the Neonatal Intensive — View Citation

Sutherland MR, Gubhaju L, Moore L, Kent AL, Dahlstrom JE, Horne RS, Hoy WE, Bertram JF, Black MJ. Accelerated maturation and abnormal morphology in the preterm neonatal kidney. J Am Soc Nephrol. 2011 Jul;22(7):1365-74. doi: 10.1681/ASN.2010121266. Epub 20 — View Citation

Tabel Y, Elmas A, Ipek S, Karadag A, Elmas O, Ozyalin F. Urinary neutrophil gelatinase-associated lipocalin as an early biomarker for prediction of acute kidney injury in preterm infants. Am J Perinatol. 2014 Feb;31(2):167-74. doi: 10.1055/s-0033-1343770. — View Citation

Vieux R, Hascoet JM, Merdariu D, Fresson J, Guillemin F. Glomerular filtration rate reference values in very preterm infants. Pediatrics. 2010 May;125(5):e1186-92. doi: 10.1542/peds.2009-1426. Epub 2010 Apr 5. — View Citation

Viswanathan S, Manyam B, Azhibekov T, Mhanna MJ. Risk factors associated with acute kidney injury in extremely low birth weight (ELBW) infants. Pediatr Nephrol. 2012 Feb;27(2):303-11. doi: 10.1007/s00467-011-1977-8. Epub 2011 Aug 3. — View Citation

Yao LP, Jose PA. Developmental renal hemodynamics. Pediatr Nephrol. 1995 Oct;9(5):632-7. doi: 10.1007/BF00860962. — View Citation

* Note: There are 44 references in all — Click here to view all references

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Develop a model that can predict the occurrence of AKI in infants admitted to the NICU;	All available serum creatinine values for each patient during the NICU admission will be recorded, considering that determinations made within the first 48 hours of the infant's life are affected by maternal creatinine values.; The presence of AKI will be determined according to the modified KIDGO criteria for the newborn, as reported in previous work in the neonatal setting (Jetton JG, 2017; Jetton JG and Askenazi DJ, 2012; Stoops C, 2016; Askenazi DJ, Patil NR, et al., 2015; Sarkar S, 2014).	From the date of randomization until the date of the first documented progression of AKI and up to 4 weeks
Primary	Identify the drug or combination of drugs associated with an increased risk of AKI	The group of infants exposed to drugs will be defined based on exposure for at least 1-day tone one or more therapies commonly used in the NICU. Special attention will be given to exposure to antibiotics, antivirals, antifungals, diuretics, anti-inflammatories, inotropes, and vasopressors. In addition to the active ingredient, other significant data such as prescribed dose, administration route, treatment duration, and temporal relationship between treatment and diagnosis of AKI will also be considered.	From the date of randomization until the date of the first documented progression of AKI and up to 4 weeks
Secondary	Identify subgroups of patients at increased risk of AKI	Number of AKI cases in risk subcategories: very low birth weight (birth weight < 1500 g), extremely low birth weight (birth weight < 1000 g), cardiopathic, with surgical pathology, sepsis, asphyxia	From the date of randomization until the date of the first documented progression of AKI and up to 4 weeks
Secondary	Identify time windows at increased risk of AKI during NICU admission.	Number of AKI cases in the first week of hospitalization compared with other periods	From the date of randomization until the date of the first documented progression of AKI and up to 4 weeks