Optimization of a stability-indicating HPLC method for the simultaneous determination of rifampicin, isoniazid, and pyrazinamide in a fixed-dose combination using artificial neural networks

The aim of this study is to develop and optimize a simple and reliable high-performance liquid chromatography (HPLC) method for the simultaneous determination of rifampicin (RIF), isoniazid (INH), and pyrazinamide (PZA) in a fixed-dose combination. The method is developed and optimized using an artificial neural network (ANN) for data modeling. Retention times under different experimental conditions (solvent, buffer type, and pH) and using four different column types (referred to as the input and testing data) are used to train, validate, and test the ANN model. The developed model is then used to maximize HPLC performance by optimizing separation. The sensitivity of the separation (retention time) to the changes in column type, concentration, and type of solvent and buffer in the mobile phase are investigated. Acetonitrile (ACN) as a solvent and tetrabutylammonium hydroxide (tBAH), used to adjust pH, have the greatest influence on the chromatographic separation of PZA and INH and are used for the final optimization. The best separation and reasonably short retention times are produced on the µ-bondapak C18, 4.6 ¥ 250-mm column, 10 µm/125 Å using ACN–tBAH (42.5:57.5, v/v) (0.0002M) as the mobile phase, and optimized at a final pH of 3.10