A cascade computer model for mocrobicide diffusivity from mucoadhesive formulations.

BACKGROUND: The cascade computer model (CCM) was designed as a machine-learning feature platform for prediction of drug diffusivity from the mucoadhesive formulations. Three basic models (the statistical regression model, the K nearest neighbor model and the modified version of the back propagation neural network) in CCM operate sequentially in close collaboration with each other, employing the estimated value obtained from the afore-positioned base model as an input value to the next-positioned base model in the cascade. The effects of various parameters on the pharmacological efficacy of a female controlled drug delivery system (FcDDS) intended for prevention of women from HIV-1 infection were evaluated using an in vitro apparatus "Simulant Vaginal System" (SVS). We used computer simulations to explicitly examine the changes in drug diffusivity from FcDDS and determine the prognostic potency of each variable for in vivo prediction of formulation efficacy. The results obtained using the CCM approach were compared with those from individual multiple regression model. RESULTS: CCM significantly lowered the percentage mean error (PME) and enhanced r(2) values as compared with those from the multiple regression models. It was noted that CCM generated the PME value of 21.82 at 48169 epoch iterations, which is significantly improved from the PME value of 29.91% at 118344 epochs by the back propagation network model. The results of this study indicated that the sequential ensemble of the classifiers allowed for an accurate prediction of the domain with significantly lowered variance and considerably reduces the time required for training phase. CONCLUSION: CCM is accurate, easy to operate, time and cost-effective, and thus, can serve as a valuable tool for prediction of drug diffusivity from mucoadhesive formulations. CCM may yield new insights into understanding how drugs are diffused from the carrier systems and exert their efficacies under various clinical conditions.

Assessment of diffusion coefficient from mucoadhesive barrier devices using artificial neural networks.

This study is aimed to elucidate the physicodynamic phenomena governing diffusion coefficient (D) of the loaded drugs in a female controlled drug delivery system (FcDDS) and to find the most influencing variable on the diffusivity using artificial neural networks (ANN). The release profiles of sodium dodecyl sulphate (SDS), a topical microbicide used as a model drug, from FcDDS were obtained using in vitro apparatus, the Simulant Vaginal System (SVS), under various conditions. The effects of formulation and intrinsic/extrinsic variables on the diffusivity of SDS were assessed using artificial neural networks (ANN). The release profiles of SDS from FcDDS revealed a non-linear relationship between the diffusivity and formulation/physiological variables. Intrinsic variables (vaginal fluid pH, vaginal fluid secretion rate) have a more prominent role in defining the diffusion coefficient of SDS from FcDDS than formulation variables (formulation loading weight and loaded doses in the formulation) or extrinsic variables (inserting position). Among 5 variables, pH of vagina fluids is the most influencing factor in defining the diffusion coefficient (maximum value of 0.95+/-0.04) of SDS from FcDDS. The external exposure conditions clearly outweighed the effects of the formulation variables on the diffusion coefficient of SDS. A model-based approach can be used to assess the diffusion coefficient of loaded drugs in FcDDS under the given conditions, leading to a parameter-specific prevention strategy against sexually transmitted diseases (STD) with a high degree of confidence.