METHOD: Eight pseudoternary phase triangles, containing ethyl oleate as the oil component and a mixture of two nonionic surfactants and n-alcohol or 1,2-alkanediol as a cosurfactant, were constructed and used for training, testing, and validation purposes. A total of 21 molecular descriptors were calculated for each cosurfactant. A genetic algorithm was used to select important molecular descriptors, and a supervised artificial neural network with two hidden layers was used to correlate selected descriptors and the weight ratio of components in the system with the observed phase behavior.

RESULTS: The results proved the dominant role of the chemical composition, hydrophile-lipophile balance, length of hydrocarbon chain, molecular volume, and hydrocarbon volume of cosurfactant. The best GNN model, with 14 inputs and two hidden layers with 14 and 9 neurons, predicted the phase behavior for a new set of cosurfactants with 82.2% accuracy for ME, 87.5% for LC, 83.3% for the O/W EM, and 91.5% for the W/O EM region.

Methods: The behaviour of GEM in MCT/surfactants/NaCl systems was studied in the ternary system at different ratios of Tween 80 and Span 80. The system with surfactant ratio 3:7 of Tween 80 and Span 80 was chosen for further study on the preparation of nanoemulsion formulation due to the highest isotropic region. Based on the selected ternary phase diagram, a composition of F1 was chosen and used for optimization by using the D-optimal mixture design. The interaction variables between medium chain triglyceride (MCT), surfactant mixture Tween 80: Span 80 (ratio 3:7), 0.9 % sodium chloride solution and gemcitabine were evaluated towards particle size as a response.