Probabilistic design space exploration and optimization via bayesian approach for a fluid bed drying process

The concept of Design Space (DS), delineated as a region of investigated variables aimed at maintaining product quality, was introduced in the International Conference on Harmonisation (ICH) Q8 as a framework to direct pharmaceutical development. However, the complexity of processes and the presence of uncertainties in pharmaceutical manufacturing exacerbate the difficulties of exploring a reliable and robust DS. This study investigates the probabilistic design space to explain the process operability and performance reliability using a Bayesian approach for a fluid bed drying process. We initially develop a Bayesian model by integrating a surrogate-based predictive model with embedded uncertainty quantification of material variability. Subsequently, employing a grid search-based technique to discretize the operational variable domain facilitates the exploration of the probabilistic DS to meet the specified product quality requirements. Meanwhile, optimization is employed to obtain the maximum DS region and enhance its operability. Results demonstrate that the Bayesian approach is an effective method to identify a probability DS to guarantee product quality at the desired reliability level considering material and process uncertainty.