Author/Authors :
Shahlaei، Mohsen نويسنده , , Andisheh، Hadi نويسنده Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran , , Derakhshandeh، Katayoun نويسنده School of Pharmacy, Kermanshah University of Medical Sciences, Kermanshah, Iran. , , Sadrjavadi، Komail نويسنده Novel Drug Delivery Research Center, Faculty of Pharmacy, Kermanshah University of Medical Sciences, Kermanshah, Iran , , Azami، Mahsa نويسنده ,
Abstract :
A sensitive and selective method using combination of principal component analysis (PCA), artificial neural network (ANN) and UV-Visible spectroscopy has been developed for the simultaneous determination of acetaminophen (AMP) and codeine (COD) in plasma samples. The ANN trained by the back-propagation learning was employed to model the complex non-linear relationship between the PCs extracted from UV-visible spectra of medications and the absorbance values. Optimal ANN model were as follows: Number of input PCs: 6, number of neurons in hidden layer: 5. The linear calibration range was 10-70 µg ml-1 and 40-700 µg ml-1, and the detection limit were 0.3 µg ml-1 and 1.3 µg ml-1, for AMP and COD, respectively. The results have been compared with those obtained by the HPLC method.
