Rationalized design to explore the full potential of PLGA microspheres as drug delivery systems

Abstract

Polymeric microparticles are widely used as drug delivery platforms either alone or embedded in more complex structures for regenerative medicine. Emulsion-solvent evaporation is the most extensively used technique for microparticles preparation. Despite the apparent simplicity of this method, there is no general procedure for producing microparticles of predictable characteristics (particle size, size distribution, encapsulation efficiency, and drug loading). Hybrid systems such as neurofuzzy logic allow identifying relationships between inputs and outputs, expressing the generated mathematical models through rules in linguistic format. In this work, the relationships between the variables involved in the emulsion-solvent evaporation process and the quality parameters of PLGA microparticles as drug delivery systems were established. Neurofuzzy logic software was able to generate models of high predictability (> 85%) for the microspheres properties namely particle size, size distribution, encapsulation efficiency and drug loading. Moreover, the generated sets of IF-THEN rules allowed to dictate general guidelines to better select the PLGA microparticles formulation parameters. This approach would be of great interest as a starting point to set-up protocols for the development of PLGA microparticles obtained by emulsion-solvent evaporation for many applications.

Keywords:

• Machine learning
• neurofuzzy logic
• artificial intelligence
• microparticles
• emulsion-solvent evaporation
• PLGA

Author contributions

Conceptualization and design of the work, R.M.B, P.D.R. and M.L.; methodology, R.M.B.; software, M.L.; investigation, R.M.B.; resources, P.D.R. and M.L.; writing—drafting and revising, R.M.B.; writing—review and editing, P.D.R. and M.L.; visualization, R.M.B. and P.D.R.; supervision, P.D.R. and M.L.; project administration, P.D.R. and M.L.; funding acquisition, M.L. All authors have read and agreed to the published version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

The data that support the findings of this study are available on request from the corresponding author, P. D. R. The data are not publicly available due to intellectual properties protection.

Additional information

Funding

This research was funded by grants from the Spanish Government (PID2020-120010RB-I00) and Xunta de Galicia (Competitive Reference Groups, ED431C 2020/17).