Background and objectives: The current threshold used for oliguria in the definition of neonatal AKI has been empirically defined as 1 ml/kg per hour. Urine output criteria are generally poorly documented, resulting in uncertainty in the most accurate threshold to identify AKI in very preterm infants with known tubular immaturity.

Design, setting, participants, & measurements: We conducted a bicentric study including 473 very preterm infants (24^0/7-29^6/7weeks of gestation) born between January 2014 and December 2018 with urine output measurements every 3 hours during the first 7 days of life and two serum creatinine measurements during the first 10 days of life. AKI was defined using the neonatal Kidney Disease Improving Global Outcomes (KDIGO) definition. We tested whether higher urine output thresholds (1.5 or 2 ml/kg per hour) in modified AKI definitions may better discriminate neonatal mortality compared with the current definition.

Results: Early-onset AKI was developed by 101 of 473 (21%) very preterm infants. AKI was diagnosed on the basis of urine output criteria alone (no rise in creatinine) for 27 of 101 (27%) participants. Early-onset AKI was associated with higher risk of death before discharge (adjusted odds ratio, 3.9; 95% confidence interval, 1.9 to 7.8), and the AKI neonatal KDIGO score showed good discriminative performance for neonatal mortality, with an area under the receiver operating characteristic (ROC) curve of 0.68 (95% confidence interval, 0.61 to 0.75). Modified AKI definitions that included higher urine output thresholds showed significantly improved discriminative performance, with areas under the ROC curve of 0.73 (95% confidence interval, 0.66 to 0.80) for the 1.5-ml/kg per hour threshold and 0.75 (95% confidence interval, 0.68 to 0.81) for the 2-ml/kg per hour threshold.

Conclusions: Early-onset AKI was diagnosed on the basis of urine output exclusively for a quarter of the cases. Furthermore, modified AKI definitions that included higher urine output improved the discriminative performance for predicting mortality.