Comparative study on the predictability of statistical models (RSM and ANN) on the behavior of optimized buccoadhesive wafers containing Loratadine and their in vivo assessment

Abstract

Objective: Buccoadhesive wafer dosage form containing Loratadine is formulated utilizing Formulation by Design (FbD) approach incorporating sodium alginate and lactose monohydrate as independent variable employing solvent casting method.

Methods: The wafers were statistically optimized using Response Surface Methodology (RSM) and Artificial Neural Network algorithm (ANN) for predicting physicochemical and physico-mechanical properties of the wafers as responses. Morphologically wafers were tested using SEM. Quick disintegration of the samples was examined employing Optical Contact Angle (OCA).

Results: The comparison of the predictability of RSM and ANN showed a high prognostic capacity of RSM model over ANN model in forecasting mechanical and physicochemical properties of the wafers. The in vivo assessment of the optimized buccoadhesive wafer exhibits marked increase in bioavailability justifying the administration of Loratadine through buccal route, bypassing hepatic first pass metabolism.

• ANN
• buccoadhesive
• in vivo
• Loratadine
• optimization
• RSM
• wafer

Acknowledgements

The authors are grateful to the Department of Metallurgy, Jadavpur University, Kolkata, India for providing SEM facility, Birla Institute of Technology, Mesra, Ranchi, India for providing optical contact angle measurement facility and Girijananda Institute of Pharmaceutical Sciences, Guwahati, Assam, India, for providing TAXT2i Texture Analyzer facility. The authors are also thankful to the Management, Bengal College of Pharmaceutical Sciences and Research, Durgapur, India for providing necessary facilities to carry out the research work.

Declaration of interest

The authors report no conflicts of interest. The authors alone are responsible for the content and writing of this article.