Journal article · 2026 · Open access

Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives

Ketana Ganpat Jadhav, Dr. Sudarshan Nagrale, Ashvini Jadhav, Sanjivani Sanjay Jagtap, Tushar Hake

International Journal of Pharmaceutical Sciences and Drug Analysis, 6(2), 259–278 · Published 1 July 2026 · DOI 10.22271/27889246.2026.v6.i2b.207

Open PDFView at the publisherCite this paper

In brief

“Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives” is a 2026 journal article by Ketana Ganpat Jadhav and 4 co-authors, published in International Journal of Pharmaceutical Sciences and Drug Analysis. OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at International Journal of Pharmaceutical Sciences and Drug Analysis.

Citations
0
References
79
Authors
5

Abstract

Background: Conventional drug-delivery systems and many clinically used nanomedicines remain limited by biological barriers, formulation complexity and inter-patient heterogeneity. Nanocarriers such as liposomes, lipid nanoparticles (LNPs), polymeric nanoparticles and emerging biomimetic systems have improved delivery for selected indications, yet development remains largely empirical and translation remains inefficient. Purpose: This narrative review examines how artificial intelligence (AI) and machine learning (ML) are being applied across the nanomedicine development chain — from nanocarrier design and formulation optimization to disease-specific targeting, prediction of biological interactions, pharmacokinetic/pharmacodynamic modelling, patient stratification and manufacturing — and critically evaluates whether AI currently improves development or remains predominantly computational and preclinical. Major evidence: Experimental studies demonstrate that supervised models — including random forests, gradient-boosting machines (XGBoost, LightGBM), artificial neural networks and Gaussian processes — can predict particle size, polydispersity index, zeta potential, encapsulation efficiency and drug release for liposomes, LNPs and poly(lactic-co-glycolic acid) (PLGA) nanoparticles with reasonable accuracy within narrow design spaces. Deep-learning platforms trained on combinatorial lipid libraries (e.g., AGILE, LUMI-lab) can prioritize ionizable lipids for mRNA delivery to specific cell types in vitro and in mice. Models trained on curated protein corona and biodistribution datasets can classify corona composition and rank tissue delivery within the curated corpora on which they were trained; none of these models reports independent external validation, cross-laboratory generalization is poor where it has been examined, and the relationships they learn remain associative rather than mechanistic. Current limitations: Most datasets are small (tens to low hundreds of formulations), single-centre and incompletely annotated. Independent external validation was not reported for any of the formulation or nano-bio interaction studies tabulated in this review; prospective testing and head-to-head comparison with conventional design of experiments are rare. Overfitting, inconsistent characterization, batch effects and limited clinical data constrain generalizability. Regulatory guidance for AI credibility and for nanomaterials remains principle-based, without product-specific standards for AI-driven nanocarriers. Translational significance: Where AI-guided design has been prospectively tested within the originating laboratory, it has reduced the number of candidates carried forward into synthesis and testing: AGILE selected 15 ionizable lipids from a 12,000-member virtual library for experimental screening 81. No study identified here has measured development time or experiment count for AI-guided design relative to conventional design of experiments screening of the same design space, so any shortening of design cycles relative to conventional screening remains unquantified. However, no AI-designed nanocarrier has yet demonstrated superiority in a prospective human trial where AI directly determined the clinical formulation, dose or patient selection. The most advanced clinical translation involves AI-assisted target or neoantigen selection…

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Jadhav, K. G., Nagrale, D. S., Jadhav, A., Jagtap, S. S., & Hake, T. (2026). Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives. International Journal of Pharmaceutical Sciences and Drug Analysis, 6(2), 259–278. https://doi.org/10.22271/27889246.2026.v6.i2b.207

MLA 9

Jadhav, Ketana Ganpat, et al. “Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives.” International Journal of Pharmaceutical Sciences and Drug Analysis, vol. 6, no. 2, 2026, pp. 259–278. https://doi.org/10.22271/27889246.2026.v6.i2b.207.

Chicago

Jadhav, Ketana Ganpat, Dr. Sudarshan Nagrale, Ashvini Jadhav, Sanjivani Sanjay Jagtap, and Tushar Hake. 2026. “Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives.” International Journal of Pharmaceutical Sciences and Drug Analysis 6 (2): 259–278. https://doi.org/10.22271/27889246.2026.v6.i2b.207.

Harvard

Jadhav, K. G. et al. (2026) ‘Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives’, International Journal of Pharmaceutical Sciences and Drug Analysis, 6(2), pp. 259–278. doi:10.22271/27889246.2026.v6.i2b.207.

IEEE

K. G. Jadhav, D. S. Nagrale, A. Jadhav, S. S. Jagtap, and T. Hake, “Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives,” International Journal of Pharmaceutical Sciences and Drug Analysis, vol. 6, no. 2, pp. 259–278, 2026, doi: 10.22271/27889246.2026.v6.i2b.207.

BibTeX

@article{jadhav2026artificial,
  title     = {{Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives}},
  author    = {Jadhav, Ketana Ganpat and Nagrale, Dr. Sudarshan and Jadhav, Ashvini and Jagtap, Sanjivani Sanjay and Hake, Tushar},
  journal   = {International Journal of Pharmaceutical Sciences and Drug Analysis},
  year      = {2026},
  volume    = {6},
  number    = {2},
  pages     = {259--278},
  doi       = {10.22271/27889246.2026.v6.i2b.207},
  url       = {https://doi.org/10.22271/27889246.2026.v6.i2b.207}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Biomaterials › Nanoparticle-Based Drug Delivery

  • artificial intelligence
  • nanomedicine
  • machine learning
  • nanocarrier design
  • lipid nanoparticles
  • liposomes
  • PLGA nanoparticles
  • mRNA delivery

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Jadhav, K. G., Nagrale, D. S., Jadhav, A., Jagtap, S. S., & Hake, T. (2026). Artificial intelligence-driven nanomedicine: Applications, evidence, and translational perspectives. International Journal of Pharmaceutical Sciences and Drug Analysis, 6(2), 259–278. https://doi.org/10.22271/27889246.2026.v6.i2b.207

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Journal of Pharmaceutical Sciences and Drug Analysis: sign in and open the PDF from this page.

Who wrote this paper?

Ketana Ganpat Jadhav, Dr. Sudarshan Nagrale, Ashvini Jadhav, Sanjivani Sanjay Jagtap, Tushar Hake.

What is the DOI of this paper?

10.22271/27889246.2026.v6.i2b.207, permanently at https://doi.org/10.22271/27889246.2026.v6.i2b.207. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.