Design Space of Pharmaceutical Processes Using Data-Driven-Based Methods

Abstract

Introduction The identification and graphical representation of process design space are critical in locating not only feasible but also optimum operating variable ranges and design configurations. In this work, the mapping of the design space of pharmaceutical processes is achieved using the ideas of process operability and flexibility under uncertainty. Methods For this purpose, three approaches are proposed which are based on different data-driven modeling techniques: response surface methodology, high-dimensional model representation, and kriging methodology. Using these approaches, models that describe the behavior of the process at different design configurations are generated using solely experimental data. The models are utilized in mixed integer non-linear programming formulations, where the optimum designs are identified for different combinations of input parameters within the operating parameter and material property ranges. Results Based on this idea, by defining a desirable output range, the corresponding range of input variables that result to acceptable performance can be accurately calculated and graphically represented. Conclusions The main advantages of the methodologies used in this work are, firstly, that there is no restriction by the lack of first-principle models that describe the investigated process and, secondly, that the models developed are computationally inexpensive. This work can also be used for the comparative analysis of the use of different surrogate-based methodologies for the identification of pharmaceutical process Design Space.

Modeling of Particulate Processes for the Continuous Manufacture of Solid-Based Pharmaceutical Dosage Forms

“…Predictive process models can be used as a supplement to experiments throughout process development, enhancing understanding of process variability and contributing to design space exploration [12,13]. Modeling and computational tools such as flowsheet simulations and global sensitivity analysis can also contribute to identification of critical process parameters to support quality risk assessment (QRA) [14][15][16].…”

“…[124][125][126][127][128]. Alternatively a computationally expensive model can be replaced by lower dimensional surrogate model obtained through fitting of experimental or simulated data using techniques such as kriging, response surface methodology (RSM), artificial neural networks (ANN) or high dimensional model representation (HDMR) [12,[129][130][131][132][133][134]. The motivation for using ROMs is that they are less computationally expensive than the original models and are therefore suitable for process simulation and optimization purposes.…”

“…Its popularity can be attributed in part to its ability to model complex nonlinear and dynamic processes [138]. In addition, Kriging generates error estimates associated with each predicted point that can be used to assess prediction accuracy and direct future sampling [12,139,140]. This combined with the fact that Kriging models do not rely on a pre-defined closed form allows for the development of accurate model representations from relatively sparse datasets as compared with those obtained through traditional experimental designs [131,139].…”

Improvement of Tablet Coating Uniformity Using a Quality by Design Approach

“…The identification and graphical representation of process design space is critical for locating not only the feasible but also the optimum operating variable ranges and design configurations. In Boukouvala et al (34), the mapping of the design space of pharmaceutical processes was achieved using the ideas of process operability and flexibility under uncertainty. Optimal process design under uncertainty was defined as a rigorous formulation in the 1980s (35), where the effects of parameters that contain considerable uncertainty on the optimality and feasibility of a chemical plant were studied.…”

Mathematical Development and Comparison of a Hybrid PBM-DEM Description of a Continuous Powder Mixing Process

“…Among the several other modeling approaches which exist in literature, for example, Monte-Carlo methods [12], continuum and constitutive models [13], statistical models [14,15], compartment models [16,17], RTD models [18,19] and hybrid models [20,21], discrete element modeling (DEM) is one of the fundamental modeling approaches that is able to capture the particle level physics. In DEM, each particle is treated as a discrete entity where the trajectory of the particles is tracked and the collision between particles is modeled.…”