EUVIMEDEUVIMED entdecken
Crossref

Predictive Intelligence for Drug Release Behavior Across Advanced Controlled Delivery Platforms

Harish Asifiqbal Jardawala, Nirav chandravadanbhai kansara, Khant shilpaben kishorsinh, Vijay Bharatbhai vasaiya, Akshar Hiteshbhai Brahmbhatt, Mande Ashmita Sunil

International Journal of Drug Delivery Technology · 04.05.2026 · 16 (35s)

DOI: 10.25258/ijddt.16.35s.89 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 04.05.2026. Verfasst von Harish Asifiqbal Jardawala und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The precise control and prediction of drug release kinetics remains a fundamental challenge in the design and optimization of controlled drug delivery systems. Conventional empirical and mechanistic modeling approaches, while informative, are often limited by their inability to capture the complex, nonlinear interactions among formulation variables, polymer matrices, and physiological conditions. This study presents a machine learning (ML)-based predictive intelligence framework capable of accurately forecasting drug release behavior across a diverse range of advanced controlled delivery platforms, including hydrogels, nanoparticles, microspheres, and polymeric implants. A comprehensive dataset encompassing physicochemical drug properties, carrier material characteristics, processing parameters, and in vitro release profiles was curated and employed to train and validate multiple ML algorithms, including Random Forest, Gradient Boosting, Support Vector Regression, and Artificial Neural Networks. Feature importance analysis revealed that polymer molecular weight, drug-polymer interaction parameters, particle size distribution, and pH conditions were among the most influential determinants of release kinetics. The optimized ML models demonstrated superior predictive accuracy, achieving R² values exceeding 0.95 and significantly outperforming traditional mathematical models such as Korsmeyer-Peppas and Higuchi. Furthermore, the proposed framework enables rapid in silico screening of formulation candidates, substantially reducing experimental burden and accelerating the development pipeline. This work underscores the transformative potential of predictive intelligence in pharmaceutical sciences, offering a robust, data-driven strategy for the rational design of nextgeneration controlled drug delivery systems.

Zitieren

APA

Jardawala, H. A., kansara, N. C., kishorsinh, K. S., vasaiya, V. B., Brahmbhatt, A. H., & Sunil, M. A. (2026). Predictive Intelligence for Drug Release Behavior Across Advanced Controlled Delivery Platforms. International Journal of Drug Delivery Technology, 16(35s). https://doi.org/10.25258/ijddt.16.35s.89

Vancouver

Jardawala HA, kansara NC, kishorsinh KS, vasaiya VB, Brahmbhatt AH, Sunil MA. Predictive Intelligence for Drug Release Behavior Across Advanced Controlled Delivery Platforms. International Journal of Drug Delivery Technology. 2026;16(35s). doi:10.25258/ijddt.16.35s.89

BibTeX
@article{Jardawala2026,
  author = {Jardawala, Harish Asifiqbal and kansara, Nirav chandravadanbhai and kishorsinh, Khant shilpaben and vasaiya, Vijay Bharatbhai and Brahmbhatt, Akshar Hiteshbhai and Sunil, Mande Ashmita},
  title = {Predictive Intelligence for Drug Release Behavior Across Advanced Controlled Delivery Platforms},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {35s},
  doi = {10.25258/ijddt.16.35s.89}
}
Kostenlos starten →