Application of acute kidney injury (AKI) biomarkers with consideration of nonrenal conditions and systemic severity has not been sufficiently determined. Herein, urinary neutrophil gelatinase-associated lipocalin (NGAL), L-type fatty acid-binding protein (L-FABP) and nonrenal disorders, including inflammation, hypoperfusion and liver dysfunction, were evaluated in 249 critically ill patients treated at our intensive care unit. Distinct characteristics of NGAL and L-FABP were revealed using principal component analysis: NGAL showed linear correlations with inflammatory markers (white blood cell count and C-reactive protein), whereas L-FABP showed linear correlations with hypoperfusion and hepatic injury markers (lactate, liver transaminases and bilirubin). We thus developed a new algorithm by combining urinary NGAL and L-FABP with stratification by the Acute Physiology and Chronic Health Evaluation score, presence of sepsis and blood lactate levels to improve their AKI predictive performance, which showed a significantly better area under the receiver operating characteristic curve [AUC-ROC 0.940; 95% confidential interval (CI) 0.793–0.985] than that under NGAL alone (AUC-ROC 0.858, 95% CI 0.741–0.927, P = 0.03) or L-FABP alone (AUC-ROC 0.837, 95% CI 0.697–0.920, P = 0.007) and indicated that nonrenal conditions and systemic severity should be considered for improved AKI prediction by NGAL and L-FABP as biomarkers.