EUVIMEDEUVIMED entdecken
Crossref

Explainable AI for Enhancing Safety and Efficiency in Drug Delivery Technologies

SK. Yakoob, T. Veeranna, Raghavender K V, C. Dastagiraiah, Cheepu Balakrishna, M. Prem Chander, G.K. Srikanth

International Journal of Drug Delivery Technology · 04.06.2026 · 16 (45s)

DOI: 10.25258/ijddt.16.45s.80 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 04.06.2026. Verfasst von SK. Yakoob und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The adoption of Artificial Intelligence (AI) technologies in drug delivery technologies has led to enhanced precision in drug therapy, allowing for dose optimization, targeted drug delivery, and continuous monitoring. But the opacity of complex AI models presents significant barriers in ensuring safety, regulatory approval and clinical acceptance. This research presents an Explainable Artificial Intelligence (XAI) approach to improve safety and efficiency in innovative drug delivery systems. This framework uses interpretable machine learning models and post-hoc explainable methods (such as SHAP (Shapley Additive Explanations) and LIME (Local Interpretable ModelAgnostic Explanations) to explain model predictions on drug release profiles, biodistribution and individual patient responses. A predictive framework using ensemble learning and deep neural networks was designed and tested on both synthetic and experimental data of nanomedicine drug delivery systems. This model not only delivers accurate predictions but also provides clear insights into the decision-making process, highlighting critical features that affect drug behaviour, including nanoparticle size, surface characteristics, and biological conditions. The explainability module allows clinicians and researchers to verify model predictions, minimise the risk of drug-related side effects and optimise drug formulations. Through experimentation, the system with XAI enhances prediction accuracy by 18% and decreases the confidence in key decision-making parameters. Moreover, the approach complies with regulatory standards by delivering interpretable and traceable results, enabling its seamless integration into clinical and pharmaceutical practice. In summary, this study showcases the role of Explainable AI as a game-changing approach for designing safer, efficient and reliable drug delivery systems, bridging the gap between computational predictive models and clinical practice.

Zitieren

APA

Yakoob, S., Veeranna, T., V, R. K., Dastagiraiah, C., Balakrishna, C., Chander, M. P., & Srikanth, G. (2026). Explainable AI for Enhancing Safety and Efficiency in Drug Delivery Technologies. International Journal of Drug Delivery Technology, 16(45s). https://doi.org/10.25258/ijddt.16.45s.80

Vancouver

Yakoob S, Veeranna T, V RK, Dastagiraiah C, Balakrishna C, Chander MP, et al. Explainable AI for Enhancing Safety and Efficiency in Drug Delivery Technologies. International Journal of Drug Delivery Technology. 2026;16(45s). doi:10.25258/ijddt.16.45s.80

BibTeX
@article{Yakoob2026,
  author = {Yakoob, SK. and Veeranna, T. and V, Raghavender K and Dastagiraiah, C. and Balakrishna, Cheepu and Chander, M. Prem and Srikanth, G.K.},
  title = {Explainable AI for Enhancing Safety and Efficiency in Drug Delivery Technologies},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {45s},
  doi = {10.25258/ijddt.16.45s.80}
}
Kostenlos starten →