Application of dominance-based rough set approach in vaginal dosage forms optimization

Abstract

The objective of this study was to identify cause-effect relationships between various data related to vaginal dosage forms, such as composition, process parameters (condition attributes), and quality (decision attribute), by employing a mathematical data mining approach that utilizes Rough Set Theory. The analyzed data were organized in a tabular format known as an information system. Objects were labeled as rows, and attributes as columns, with attribute-values serving as entries. Each formulation was described by its condition attributes (composition, manufacturing process, quality parameters), while the decision attribute indicated the quality of the formulation (expressed as pH after vaginal tablet or pessary application) and enabled classification as correct/incorrect or good/bad. The decision rules generated by the study provide insights into relationships between the condition attributes and the decision attribute. They highlight the importance of LA content and LA:polymer ratios in maintaining physiological pH. Additionally, the findings confirm the favorable impact of chitosan on pH regulation while indicating that the type of formulation (pessaries or tablets) does not significantly affect the classification of objects. Decision rules with high confirmation coefficients of condition attributes can help developing optimal formulations. These decision rules contain essential information that describes the cause-and-effect relationships and are free of redundant information. They form the basis for understanding and optimizing processes, and establishing a design space.

Keywords

• machine learning
• rough set theory
• dosage forms
• data mining
• vaginal route of administration
• vaginal tablet