Predicting the serum digoxin concentrations of infants in the neonatal intensive care unit through an artificial neural network

Table 2 MSE, RMSE, MAD, MAPE of each ANN model between the observed serum digoxin concentrations and the corresponding predicting concentrations on validation dataset

Model	No. of parameters	Parameters	MAPE(%)	MSE	RMSE	MAD	R²(%)
1	11	All Variables	16.72	0.05	0.23	0.19	63.00
2	10	-Sex	15.88	0.05	0.22	0.17	65.17
3	9	-Sex-DCM	17.70	0.06	0.24	0.19	74.46
4	8	-Sex-DCM -PH	15.03	0.04	0.20	0.16	73.82
5	7	-Sex-DCM -PH -Captopril	21.41	0.09	0.30	0.24	57.30
6	6	-Sex-DCM -PH -Captopril -Furosemide	23.18	0.09	0.29	0.25	63.43
7	5	-Sex-DCM -PH -Captopril -Furosemide -VSD	25.16	0.11	0.33	0.26	46.37
8	4	-Sex-DCM -PH -Captopril -Furosemide -VSD -ibuprofen	24.68	0.10	0.31	0.26	44.43

“- “in the column of parameters refers to “exclude” that specific variable from the model 1, which contain all variables. MAPE Mean Absolute Percentage Error; MSE Mean Square Error; RMSE Root Mean Square Error; MAD Mean Absolute Deviation, R²% determination of coefficient
All 11 variables include: dose per total body weight, gender, postmenstrual age (PMA), Congestive heart failure (CHF), dilated cardiomyopathy (DCM), pulmonary hypertension (PH), Ventricular septal defect (VSD), with captopril, with furosemide, with ibuprofen
*Common variables used in population pharmacokinetics were dose per total body weight, PMA, CHF

ISSN: 1471-2431