Optimization of the Manufacturing Process for Oral Formulations Using Multivariate Statistical Methods

Multivariate statistical analysis has and will continue to play an important role in the development of pharmaceutical products. Although many examples have been reported, few have applied multivariate statistical analysis to the overall manufacturing process. In this study, the model drug core tablets were manufactured under different conditions, and the challenge to understand the cause-and-effect relationship between process parameters and response variables was addressed by applying three different multivariate statistical methods. It was confirmed that conventional multivariate statistical methods were able to extract the process parameters (granulation time, drying temperature, blending time, and compression force) that affected both the average and the variance of the response variables (hardness, content uniformity, and dissolution) with a science-based rationale. In order to overcome the multiobjective optimization problem among the response variables, an advanced multivariate statistical method was also applied. It was confirmed that the mathematical models of response variables were determined with sufficiently high accuracy and the optimal levels of both process parameters and response variables were determined with high reliability, which provided a more profound understanding of the process. These methods enable us to develop pharmaceutical products more efficiently and accurately.