(206c) A Practical Framework Towards Prediction of Breaking Force and Disintegration of Tablet Formulations Using Machine Learning Tools and Nondestructive Ultrasound

Enabling the paradigm of quality by design requires the ability to quantitatively correlate material properties and process variables to measureable product performance attributes. Conventional, quality-by-test methods for determining tablet breaking force and disintegration time usually involve destructive tests, which consume significant amount of time, labor and provide limited information. Recent advances in material characterization, statistical analysis and machine learning have provided multiple tools that have the potential to develop nondestructive, fast and accurate approaches in drug product development. In this work, a methodology to predict the tablet breaking force and disintegration time of tablet formulations using nondestructive ultrasonics and machine learning tools was developed. The inputs to the model include intrinsic properties of drug formulation as well as extrinsic process variables influencing the tablet during manufacturing. The model has been applied to predict tablet breaking force and disintegration time of tablets using small quantities of API and prototype formulation designs. The accuracy of the predicted outputs are ± 7 N for tablet breaking force and ± 11 second for disintegration time of the actual value, even with the presence of wide range of measured breaking force and disintegration time. The novel approach presented in this study is a step forward toward rational design of a robust drug product based on insight into the performance of common materials during formulation and process development. It may also help reduce development time, API usage and facilitate the development of a robust drug product.