Figures & data
Table 1 General description of created database
Table 2 Settings for selection of variables performed by fscaret
Figure 1 Scheme of work.
Abbreviations: 3D, three-dimensional; SEM, scanning electron microscope; API, active pharmaceutical ingredient.
Figure 2 General structure of created models.
Table 3 Structure of the database contained 28 input variables prepared based on fscaret results
Table 4 Results for the best models created based on the database contained 28 input vectors
Figure 3 Observed versus predicted plot for model created with the genetic programming method.
Abbreviation: FPF, fine particle fraction.
Table 5 Architecture and settings of created models for various modeling methods
Figure 4 Response surfaces for predicted FPF and variables.
Notes: (A) Drug lipophilicity (logP) and carrier surface properties (Rsk). (B) Drug content in formulation (%) and flow rate (L/min).
Abbreviations: FPF, fine particle fraction; Rsk, skewness of the assessed profile.
Figure 5 Plots and Rsk values for various surfaces.
Notes: (A) Rsk =1.4, (B) Rsk =1.5, (C) Rsk = −0.18, (D) Rsk =0.08.
Abbreviations: Rsk, the skewness of the assessed profile; Z-depth(pixel), distance.
Table 6 Parameters of validation formulation
Table 7 Results of model validation on new experimental data
Figure 6 Scanning electron micrograph of hydroxyapatite carrier for additional formulation.
