Skip to main content

Table 1 Prediction accuracy for different statistical models

From: Generation and validation of a formula to calculate hemoglobin loss on a cohort of healthy adults subjected to controlled blood loss

Model

Test MSE

Test EV

Reference model

696.0

0.542

Linear regression

614.2

0.601

Ridge regression

612.8

0.595

Neural networks

748.6

0.542

Support vector regression

656.9

0.548

  1. Prediction accuracy for the different statistical models is shown. The lower the mean squared error (MSE) and the higher the explained variance (EV), the better the prediction accuracy. Linear and ridge regression outperform the alternative models