EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A computational framework for data-driven drug delivery design: computational validation via drug release kinetics prediction

John Dike N. Ogbonna, Chinatu M. Anyanwu, Onyinye Precious Chukwudi, Vivien Ikebudu, Nkiru C. Ogbonna, Chinazom P. Agbo, Adaeze Linda Onugwu, Franklin C. Kenechukwu, Anthony A. Attama

Frontiers in Drug Delivery · 19.11.2026 · 6

DOI: 10.3389/fddev.2026.1941896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Drug Delivery, online erschienen am 19.11.2026. Verfasst von John Dike N. Ogbonna und 8 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of drug release plays an important role in the design of controlled-release pharmaceutical formulations. Traditional formulation development relies heavily on experimental trial-and-error approaches, which are often time-consuming and resource-intensive. This study presents a computational framework for predicting cumulative drug release from key formulation variables and evaluates its performance using a simulated dataset generated with the Korsmeyer-Peppas model. The dataset consisted of 180 simulated formulation samples described by six input variables: polymer concentration, drug load, particle size, dissolution medium pH, dissolution time, and viscosity. Two supervised learning models, Random Forest (RF) and an Artificial Neural Network (ANN), were developed and evaluated using an 80:20 train-test split and five-fold cross-validation. The ANN achieved higher predictive performance than the RF model, with a test R2 of 0.9652, RMSE of 6.855%, and MAE of 6.060%, while the RF model achieved a test R2 of 0.5901, RMSE of 23.539%, and MAE of 16.437%. Feature importance analysis identified particle size and polymer concentration as the most influential variables affecting the predicted drug release profiles. The findings show that machine learning can effectively model relationships between formulation variables and simulated drug release behaviour, and provide a reproducible framework for computational evaluation during the early stages of formulation development. The reported results are based on simulated data and should be interpreted as computational validation of the proposed framework. Future studies will focus on evaluating the framework using experimentally measured dissolution datasets.

Zitieren

APA

Ogbonna, J. D. N., Anyanwu, C. M., Chukwudi, O. P., Ikebudu, V., Ogbonna, N. C., Agbo, C. P., Onugwu, A. L., Kenechukwu, F. C., & Attama, A. A. (2026). A computational framework for data-driven drug delivery design: computational validation via drug release kinetics prediction. Frontiers in Drug Delivery, 6. https://doi.org/10.3389/fddev.2026.1941896

Vancouver

Ogbonna JDN, Anyanwu CM, Chukwudi OP, Ikebudu V, Ogbonna NC, Agbo CP, et al. A computational framework for data-driven drug delivery design: computational validation via drug release kinetics prediction. Frontiers in Drug Delivery. 2026;6. doi:10.3389/fddev.2026.1941896

BibTeX
@article{Ogbonna2026,
  author = {Ogbonna, John Dike N. and Anyanwu, Chinatu M. and Chukwudi, Onyinye Precious and Ikebudu, Vivien and Ogbonna, Nkiru C. and Agbo, Chinazom P. and Onugwu, Adaeze Linda and Kenechukwu, Franklin C. and Attama, Anthony A.},
  title = {A computational framework for data-driven drug delivery design: computational validation via drug release kinetics prediction},
  journal = {Frontiers in Drug Delivery},
  year = {2026},
  volume = {6},
  doi = {10.3389/fddev.2026.1941896}
}
Kostenlos starten →