Prediction of Nitrendipine Anti-Hypertensive Effect from Plasma Concentration Profiles by Neural Networks

Nitrendipine is an effective and safe calcium channel blocker for the treatment of mild to moderate hypertension. The aim of this work is to show that a model of a relation between nitrendipine plasma levels and pharmacodynamic effects can be composed and used for pressure drop prediction after oral administration. To reach the goal, the following steps are needed: evaluation of database quality for artificial neural networks (ANN) training, definition of optimal input set for ANN, prediction of diastolic pressure drop by ANN. To evaluate database quality for ANN training, statistical methods are used, as well as for definition of optimal input set for ANN. ANN training curve of different input sets also served as optimal input set selector. A relation between nitrendipine plasma levels and pharmacodynamic effect is modelled by ANN. Possible consequences of successful ANN modelling are drug administration regimen optimisation, to achieve best possible effect, as well as optimal drug formulation design