Skip to main content

Table 6 Numerical Results for the Deep learning Model

From: A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients

Model Working point auROC (avg) Sensitivity Specificity LR+  LR-
Deep Learning Sensitivity = 80% 0.89 ± 0.01 80.0% 84.0 ± 3.0% 5.00 0.20
  Knee-point   82.0% 82.0 ± 3.0% 4.50 0.22
  1. auROC area under receiving operator curve LR + likelihood positive ratio, LR- likelihood negative ratio