Co-Loaded PEGylated Nanoliposomes of Bendamustine and Rutin: Formulation, Release Kinetics, and a Hybrid Predictive...

Area of Science:

• Nanotechnology and Pharmaceutical Sciences
• Drug Delivery Systems
• Biomedical Engineering

Background:

• Current liposomal drug delivery research is often descriptive and lacks predictive power.
• Developing versatile nanoliposome formulations is crucial for advancing targeted drug delivery.
• Predictive models are needed to optimize nanoliposome performance and reduce development time.

Purpose of the Study:

• To develop co-loaded nanoliposomes with enhanced drug encapsulation and release characteristics.
• To establish an integrated analytical framework for the predictive analysis of drug release from nanoliposomes.
• To evaluate the capability of machine learning and kinetic modeling in predicting drug release profiles.

Main Methods:

• PEGylated nanoliposomes co-loaded with bendamustine and rutin were prepared via thin-film hydration.
• Physicochemical properties, encapsulation efficiency, and in vitro drug release were systematically evaluated.
• An integrated analytical approach combining data augmentation, denoising, Weibull kinetic modeling, and machine learning was employed.

Main Results:

• Co-loaded nanoliposomes demonstrated higher encapsulation efficiency (up to 77.75%) and distinct release profiles.
• Weibull modeling accurately described nonlinear release kinetics (R² ≈ 0.90-0.94).
• Machine learning enabled accurate prediction of later-stage release from early time points (R² > 0.98), though cross-formulation generalization was limited.

Conclusions:

• The developed hybrid framework enables early prediction of drug release from nanoliposomes.
• Curve-level drug release behavior can be approximated without precise parameter estimation, indicating parameter compensability.
• This study provides a proof-of-concept for analyzing nanoliposomal drug delivery systems using predictive modeling.