Neural network as a decision support system in the development of pharmaceutical formulation-focus on solid dispersions

The aim of the study was to create simple, neural model of ketoprofen (Ket) dissolution from solid dispersions (SD) and physical mixtures (PM), which could be an aid in prospective development of pharmaceutical formulation. An application of artificial neural networks (ANNs) methodology was investigated using experimental data. Backpropagation (BP) ANNs with two hidden layers, hyperbolic tangent as the activation function and Hampel's target function were studied. Neuro-fuzzy systems were also applied. As the input variables formulation type and preparation technology as well as qualitative and quantitative composition of SD and physical mixtures (PM) were selected. Direct incorporation of physicochemical properties of excipients (connectivity index, CI) enhanced ANNs model usability. Further improvement of neural model was achieved by input variables reduction performed on the basis of the sensitivity analysis. ANNs functions as decision support system in prospective ketoprofen SD formulation as well as data-mining tool were confirmed.