S. Agatonovic-kustrin et al., Solid state assay of ranitidine HCl as a bulk drug and as active ingredient in tablets using DRIFT spectroscopy with artificial neural networks, PHARM RES, 16(9), 1999, pp. 1477-1482
Purpose. A new, simple, sensitive and rapid method was developed to analyse
the polymorphic purity of crystalline ranitidine-HCl as a bulk drug and fr
om a tablet formulation.
Methods. Diffuse reflectance infrared Fourier transform (DRIFT) spectroscop
y was combined with Artificial Neural Networks (ANNs) as a data modelling t
ool. A standard feed-forward network, with backpropagation rule and with si
ngle hidden layer architecture was chosen. Reduction and transformation of
the spectral data enhanced the ANN performance and reduced the complexity o
f the ANNs model. Spectral intensities from 1738 wavenumbers were reduced i
nto 173 averaged spectral values. These 173 values were used as inputs for
the ANN. Following a sensitivity analysis the number of inputs was reduced
to 30, or 35, these being the input windows which had most effect on the ou
tput of the ANN.
Results. For the bulk drug assay, the ANN model had 30 inputs selected from
a sensitivity analysis, one hidden layer, and two output neurons, one for
the percentage of each ranitidine hydrochloride crystal form. The model cou
ld simultaneously distinguish between crystal forms and quantify them enabl
ing the physical purity of the bulk drug to be checked. For the tablet assa
y, the ANN model had 173 averaged spectral values as the inputs, one hidden
layer and five output neurons, two for the percentage of the two ranitidin
e hydrochloride crystal forms and three more outputs for tablet excipients
and additives. The ANN was able to solve the problem of overlapping peaks a
nd it successfully identified and quantified all components in tablet formu
lation with reasonable accuracy.
Conclusions. Some of the advantages over conventional analytical methods in
clude simplicity, speed and good selectivity. The results from DRIFT spectr
al quantification study show the benefits of the neural network approach in
analysing spectral data.