Table 4 Creatinine regression metric results presented as means of the 10 folds plus–minus the standard deviation.

From: Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements

 

Features

MSE

R2

MAE

ANN

At-home

\(0.614 \pm 0.170\)

\(0.284 \pm 0.190\)

\(0.585 \pm 0.0845\)

Monitoring

\(0.295 \pm 0.202\)

\(0.674 \pm 0.182\)

\(0.387 \pm 0.0781\)

Laboratory

\(0.300 \pm 0.0847\)

\(0.652 \pm 0.0773\)

\(0.416 \pm 0.0375\)

RF

At-home

\(0.583 \pm 0.134\)

\(0.381 \pm 0.203\)

\(0.551 \pm 0.0351\)

Monitoring

\(0.319 \pm 0.133\)

\(0.682 \pm 0.0882\)

\(0.391 \pm 0.0456\)

Laboratory

\(0.292 \pm 0.143\)

\(0.707 \pm 0.106\)

\(0.366 \pm 0.0524\)