Application of Artificial Intelligence Techniques for the Estimation of Basal Insulin in Patients with Type I Diabetes

Table 2

Metrics used to measure the accuracy of experiments for dose calculation.

Technique	MAE	MSE	RMSE	R	R^2
BNs	0.1199083333	0.03133645935	0.1770210704	0.7754166667	0.634873650
NNs	0.3369750000	0.20192390070	0.4493594338	−0.0303916666	0.067199665
RF	0.0000657431064	0.00000037425226	0.000611761611	0.9999964346	0.999992869
SVM	0.01282676086	0.001109456742	0.03330850856	0.9921356180	0.984373906

MAE: mean absolute error. MSE: mean squared error. RMSE: root-mean-square error. R: Pearson's correlation coefficient. R²: coefficient of determination. BNs: Bayesian networks. NNs: neural networks. RF: Random Forest. SVMs: support vector machines.