EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Nanomaterials in Drug Delivery: Leveraging Artificial Intelligence and Big Data for Predictive Design

Youngji Han iD, Dong Hyun Kim, Seung Pil Pack

International Journal of Molecular Sciences · 17.11.2025 · 26 (22) · 11121

DOI: 10.3390/ijms262211121 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 17.11.2025. Verfasst von Youngji Han und 2 weiteren Autor:innen. Beteiligte Einrichtung: Bio-Medical Research Institute, Kyungpook National University Hospital, Daegu 41940, Republic of Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Big Data, Drug Delivery Systems, Nanostructures. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 129 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korean government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nanomaterials have revolutionized drug delivery by enabling precise control over solubility, stability, circulation time, and targeted release, yet translation from bench to bedside remains challenging due to complex synthesis, unpredictable biological interactions, and regulatory hurdles. Recent advances in artificial intelligence (AI) and big data analytics offer powerful solutions to these bottlenecks by integrating multidimensional datasets—encompassing physicochemical characterization, pharmacokinetics, omics profiles, and preclinical outcomes—to generate predictive models for rational nanocarrier design. Machine learning and deep learning approaches enable the prediction of key parameters such as particle size, drug loading efficiency, and biodistribution, while generative algorithms explore novel chemistries and architectures optimized for specific clinical applications. Nanoinformatics platforms and large-scale data repositories further enhance reproducibility and cross-study comparisons, supporting regulatory science and accelerating clinical translation. This review provides a comprehensive overview of nanomaterial-based drug delivery systems, highlights AI-driven strategies for predictive modeling and optimization, and discusses translational and regulatory perspectives. By bridging nanotechnology, computational modeling, and precision medicine, AI-assisted nanomaterial design has the potential to transform drug delivery into a more efficient, reproducible, and patient-centered discipline.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceBig DataDrug Delivery SystemsNanostructuresHumansAnimalsMachine Learning

Stichwörter der Autor:innen

artificial intelligencedeep learningdrug deliverymachine learningnanoinformaticsnanomaterialsprecision medicinepredictive modeling

Autor:innen und Institutionen

  • Bio-Medical Research Institute, Kyungpook National University Hospital, Daegu 41940, Republic of Korea.
  • Department of Biotechnology and Bioinformatics, Korea University, Sejong 30019, Republic of Korea.
  • Biological Clock-Based Anti-Aging Convergence RLRC, Korea University, Sejong 30019, Republic of Korea.

ORCID-Profile: Youngji Han

Förderung

  • National Research Foundation of Korea
  • Korean government

Zitieren

APA

Han, Y., Kim, D. H., & Pack, S. P. (2025). Nanomaterials in Drug Delivery: Leveraging Artificial Intelligence and Big Data for Predictive Design. International Journal of Molecular Sciences, 26(22), 11121. https://doi.org/10.3390/ijms262211121

Vancouver

Han Y, Kim DH, Pack SP. Nanomaterials in Drug Delivery: Leveraging Artificial Intelligence and Big Data for Predictive Design. International Journal of Molecular Sciences. 2025;26(22):11121. doi:10.3390/ijms262211121

BibTeX
@article{Han2025,
  author = {Han, Youngji and Kim, Dong Hyun and Pack, Seung Pil},
  title = {Nanomaterials in Drug Delivery: Leveraging Artificial Intelligence and Big Data for Predictive Design},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  volume = {26},
  number = {22},
  pages = {11121},
  doi = {10.3390/ijms262211121}
}
Kostenlos starten →