Skip to main content
Fig. 3 | Critical Care

Fig. 3

From: Machine learning versus physicians’ prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor

Fig. 3

Performance of AKIpredictor for predictions of AKI-23 by SCr and UO. a At ICU admission (n = 252), AUROC [95% CI] was 0.76 [0.66–0.85], net benefit in ranges 0–74%. b On the first morning of ICU stay (n = 238), AUROC [95% CI] was 0.87 [0.79–0.95], net benefit in ranges 0–48%. c After 24 h (n = 195), AUROC [95% CI] was 0.85 [0.75–0.96], net benefit in ranges 0–43%

Back to article page

Critical Care

ISSN: 1364-8535