Note
Application of artificial neural networks (ANNs) and genetic programming (GP) for prediction of drug release from solid lipid matrices

https://doi.org/10.1016/j.ijpharm.2012.05.021Get rights and content

Abstract

The aim of the present study was to develop a semi-empirical mathematical model, which is able to predict the release profiles of solid lipid extrudates of different dimensions. The development of the model was based on the application of ANNs and GP. ANNs' abilities to deal with multidimensional data were exploited. GP programming was used to determine the constants of the model function, a modified Weibull equation. Differently dimensioned extrudates consisting of diprophylline, tristearin and polyethylene glycol were produced by the use of a twin-screw extruder and their dissolution behaviour was studied. Experimentally obtained dissolution curves were compared to the calculated release profiles, derived from the semi-empirical mathematical model.

Graphical abstract

A model based on artificial neural networks and genetic programming was derived, which is able to predict the release profiles of solid lipid extrudates of different dimensions.

  1. Download : Download high-res image (178KB)
  2. Download : Download full-size image

References (7)

There are more references available in the full text version of this article.

Cited by (11)

  • Potential of Raman spectroscopy in facilitating pharmaceutical formulations development – An AI perspective

    2021, International Journal of Pharmaceutics
    Citation Excerpt :

    Several AI applications have been adopted in the study and property prediction for extrudates. Güres et al. developed a mathematical model to predict the diprophylline release profiles of a solid lipid extrudate based on ANNs and genetic programming, and successfully used it in release profile calculations (Güres et al., 2012). Recently, Manda et al. investigated the influence of formulation and process variables on the drug release behavior from a multiple-unit pellet system (produced by the extrusion-spheronization method) using ANNs, and revealed that the in vitro release profile was significantly impacted by two of the investigated factors, microcrystalline cellulose concentration and sodium starch glycolate concentration, and negligibly influenced by the other two parameters, spheronization time and extrusion speed (Manda et al., 2019).

  • Release modeling of nanoencapsulated food ingredients by artificial intelligence algorithms

    2020, Release and Bioavailability of Nanoencapsulated Food Ingredients
  • Comparison of multi-linear regression, particle swarm optimization artificial neural networks and genetic programming in the development of mini-tablets

    2018, International Journal of Pharmaceutics
    Citation Excerpt :

    Additionally, another AI methodology used successfully in multivariate regression problems is the implementation of an evolutionary algorithm known as GP. In GP, computer programs (or mathematical operations) are encoded as a set of genes that are then modified (evolved) based on Darwin’s Natural Selection theory (Güres et al., 2012; Koza, 1994). The use of such AI regression approaches in combination with DoE may show enhanced fitting performance (i.e. superiority) compared to MLR or logistic regression techniques (and hence, a more precise/safe design space or control strategy can be constructed during QbD-based product development) due to the fact that they: 1) require less formal statistical training to develop, 2) can implicitly model more complex nonlinear relationships between independent and dependent variables, 3) can detect “hidden” (to MLR) interactions between input and output variables (i.e. factors and responses), and 4) can show increased adaptability by embedding multiple training approaches (such as swarm-based intelligence with ANNs) (Tu, 1996).

  • The significance of artificial intelligence in drug delivery system design

    2019, Advanced Drug Delivery Reviews
    Citation Excerpt :

    System inputs included the diameter and length of the extrudates and dissolution times and the amount of released diprophylline was considered as output. Using the modified Weibull equation, it has been revealed that enhancement of the extrudate diameter results in reduced release rate [213]. ANNs have also been used to design the optimal formulations of sustained release dosage forms and predict their dissolution profiles [214].

  • Application of Artificial Neural Networks for modeling drug release from a bicomponent hydrogel system

    2016, 2016 20th International Conference on System Theory, Control and Computing, ICSTCC 2016 - Joint Conference of SINTES 20, SACCS 16, SIMSIS 20 - Proceedings
View all citing articles on Scopus
View full text