An-Najah Staff

Artificial neural networks (ANNs) were employed in the optimization of a nimodipine zero-order release matrix tablet formulation, and their efficiency was compared to that of multiple linear regression (MLR) on an external validation set. The amounts of PEG-4000, PVP K30, HPMC K100 and HPMC E50LV were used as independent variables following a statistical experimental design, and three dissolution parameters (time at which the 90% of the drug was dissolved, t_90%, percentage of nimodipine released in 2 and 8 h, Y_2h, and Y_8h, respectively) were chosen as response variables. It was found that a feed-forward back-propagation ANN with eight hidden units showed better fit for all responses (R² of 0.96, 0.90 and 0.98 for t_90%, Y_2h and Y_8h, respectively) compared to the MLR models (0.92, 0.87 and 0.92 for t_90%, Y_2h and Y_8h, respectively). The ANN was further simplified by pruning, which preserved only PEG-4000 and HPMC K100 as inputs. Optimal formulations based on ANN and MLR predictions were identified by minimizing the standardized Euclidian distance between measured and theoretical (zero order) release parameters. The estimation of the similarity factor, f₂, confirmed ANNs increased prediction efficiency (81.98 and 79.46 for the original and pruned ANN, respectively, and 76.25 for the MLR).

In the present study an isocratic reversed-phase high-performance liquid chromatography was investigated for the separation of nimodipine and impurities (A, B and C) using statistical experimental design. Initially, a full factorial design was used in order to screen five independent factors: type of the organic modifier – methanol or acetonitrile – and concentration, column temperature, mobile phase flow rate and pH. Except pH, the rest examined factors were identified as significant, using ANOVA analysis. The optimum conditions of separation (optimum values of significant factors) determined with the aid of central composite design were: (1) mobile phase: acetonitrile/H₂O (67.5/32.5, v/v), (2) column temperature 40 °C and (3) mobile phase flow rate 0.9 ml/min. The proposed method showed good prediction ability (observed–predicted correlation). The analysis was found to be linear, specific, precise, sensitive and accurate. The method was also studied for robustness and intermediate precision using experimental design methodology. Three commercially available nimodipine tablets were analyzed showing good % recovery and %RSD. No traceable amounts of impurities were found in all products.