Machine Learning in Bioequivalence: Towards Identifying an Appropriate Measure of Absorption Rate

In this study, the modern tool of machine learning is used to address an old problem from a new perspective. Traditionally, scientific basis for determining bioequivalence based on pharmacokinetic comparison, specifically rate and extent absorption between two products. Even though it generally agreed that peak plasma concentration (Cmax) should be measure absorption, several studies have raised concerns. Thus, alternative metrics been proposed Cmax shortcomings. The aim study utilize unsupervised (principal component analysis) supervised (random forest) algorithms uncover relationships among parameters identify most suitable metric rate. One actual three simulated donepezil datasets were utilized. For needs population model was also developed further simulation BE with different kinetics. Among explored, newly Cmax/Tmax ratio investigated. latter found better reflect rate, regardless kinetic properties absorption. This one first utilizing in field bioequivalence.