Background: Acute kidney injury (AKI) is common among critically ill children. The current definitions of AKI rely on serum creatinine and urine output, which may not be deranged until late in the course of the illness. There has been a lot of work in search of novel biomarkers to define and predict AKI, and urinary neutrophil gelatinase-associated lipocalin (NGAL) is a promising one. We planned to study the usefulness of urinary NGAL in predicting AKI. Patients and methods: Children in the age group of 1 month to 18 years admitted to the pediatric intensive care unit (PICU) from September 2016 to December 2017 were enrolled. Children with preexisting kidney disease, urinary tract infection (UTI), postsurgical patients, or children with expected duration of stay <48 hours were excluded. Data regarding demographics, clinical features, and laboratory parameters were collected. Urinary NGAL was sent within 6 hours of admission. Children were classified to have AKI based upon the Pediatric Risk, Injury, Failure, Loss, End Stage Renal Disease (pRIFLE) criteria. Using receiver operating characteristic (ROC) curves, sensitivity, specificity, and area under the curve (AUC) for admission creatinine and urinary NGAL to predict AKI were deduced. Results: One hundred and thirty children were included. Out of 130 children, 59 (45.4%) developed AKI. Urinary NGAL at admission to the PICU >88.5 ng/mL had a sensitivity of 81.4% and specificity of 83.6% in detecting AKI while its AUC to detect AKI was 0.842 (95% confidence interval (CI) 0.765-0.918). Urinary NGAL predicted AKI in 17 (28.8%) of 59 patients at least 24 hours earlier than serum creatinine. Mortality rates in patients with and without AKI were 18.6 and 2.8%, respectively. Conclusion: Urinary NGAL has good sensitivity and specificity in detecting AKI and predicts AKI earlier than creatinine in a significant number of patients. [ABSTRACT FROM AUTHOR]