Linking material properties to 1D-PBM parameters towards a generic model for twin-screw wet granulation

Partial least squares regression to calculate population balance model parameters from material properties in continuous twin-screw wet granulation

“…Therefore, using the values predicted by the PLS models to calculate the PBM parameters. In our previous publication [33], it was also validated that the computed PBM parameters can be used for the simulation of granule size distributions for new formulations. As described above, some improvement opportunities in the model development were found from the validation results.…”

“…The model has a generic nature under development with the same excipient base and produced with the same screw configuration [33]. The model applicability can be extended by adding other factors, e.g., different excipient bases and screw configurations, as inputs of PLS models.…”

“…The primary focus of this work is to identify key material properties on PBM parameters by developing PLS models. A comprehensive account of the validation phase for the hybrid model, consisting of the PBM component and the proposed PLS models, can be found in Barrera Jiménez et al 2023 [33]. All works of PLS development were performed using the Python package scikit-learn.…”

“…Three center-point experiments were performed in each DoE. This work is a continuation of the work of Barrera Jiménez et al[32,33]. For more details on the process and characterization techniques, the reader is referred to the aforementioned work.The formulations contained the same excipient base and differed solely in the Active Pharmaceutical Ingredient (API).…”