Skip to main content
. 2020 Jan 22;10:1550. doi: 10.3389/fphar.2019.01550

Table 3.

Mean absolute error (MAE) and percentage within 20% of actual dose in the overall test set of the Caribbean Hispanic cohort.

Models MAE (mg/week) Within 20%
RPART 6.27 (4.16-8.38) 72.22
MARS 8.52 (5.92-11.12) 55.56
RFR 4.73 (3.24-6.21) 80.56
ANN 9.73 (6.53-12.93) 58.33
SVR# 6.86 (4.75-8.97) 61.11
iBK1 6.78 (4.41-9.15) 66.67
iBK2 6.30 (3.88-8.71) 69.44
iBK3 6.15 (3.72-8.57) 72.22
REPT# 9.87 (6.62-13.12) 47.22

#best prediction model does not include common variants in VKORC1 (rs9923231), CYP2C9 (rs1799853), CYP4F2 (rs2108622) and NQO1 (rs1800566).

Data are expressed as mean (95% CI) or percentage. MAE, mean absolute error; multivariate adaptive regression splines (MARS), artificial neural networks (ANN), random forest regression (RFR), support vector regression (SVR), K-nearest neighbor for K from 1 to 3 (iBK1, iBK2, iBK3), recursive partitioning (RPART) and reduces error pruning tree classifier (REPT).