A decision-support tool for the formulation of orally active, poorly soluble compounds

Physicochemical data for a set of potentially poorly soluble compounds was analysed in relation to suitable formulations for these compounds. Physical chemistry was found to be a key determinant of formulation class expressed in terms of conventional, solid dispersion, lipidic/surfactant, and crystalline nanoparticle systems. This relationship was used to build a decision-support tool aimed to guide formulation selection for poorly soluble compounds during product development. Tool components included a user interface, a database of compound cases together with known formulations, and predictive modules based on statistics, decision trees, and case-based reasoning. The tool was tested and exhibited significant and consistent predictive ability across testing conditions. This type of tool has the potential to improve the efficiency and predictability of the formulation development process.