Artificial Intelligence in Drug Delivery System Design: From Predictive Modeling to Inverse Formulation Design

AI is revolutionising medication delivery research by enabling data-driven prediction, multidimensional formulation optimisation and rational design of delivery devices with increased therapeutic performance. Traditional drug delivery development is heavily dependent on iterative experimental approaches, empirical manipulation of formulations and step-wise optimisation of single formulation variables which are resource intensive and potentially inadequate to capture complex non-linear interactions between drugs, excipients, physicochemical characteristics, biological barriers and process parameters. Machine learning, deep learning, artificial neural networks and AI-based generative computational techniques offer possibilities to model these multidimensional interactions and to speed up the finding of formulations with defined performance features. Predictive modelling can be used to predict drug release kinetics, physico-chemical stability, pharmacokinetic behaviour, drug-excipient compatibility and carrier related properties to support early stage formulation decisions. AI-assisted optimisation enables systematic combination of formulation and process parameters to identify parameter combinations that result in good drug loading capacity, particle properties, encapsulation efficiency, stability and controlled or targeted release. More recently, a new paradigm was developed called inverse design approaches where the desired therapeutic/material features are first described and mathematical models then propose potential formulations that can achieve the predefined characteristics. Coupling generative AI with inverse design could further boost this capacity to build novel delivery structures outside the empirically investigated formulation space. However, there remain several challenges to be addressed, including data heterogeneity, limited datasets, model interpretability, external validation, reproducibility, regulatory approval, and the translation of computational predictions to clinically viable formulations. This review critically discusses the evolving role of AI in drug delivery with focus on forecasting, formulation optimisation and emerging inverse design strategies as well as translational barriers and future opportunities to develop more efficient, personalised and rationally engineered systems for drug delivery.

Authors

Publication Details

Journal
World Journal of Current Medical and Pharmaceutical Research
Published
2026-11-18
DOI
https://doi.org/10.37022/wjcmpr.v8i3.469
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial Intelligence in Drug Delivery System Design: From Predictive Modeling to Inverse Formulation Design

Balaji Nagarajan, Mohammed Thariq
3 links
World Journal of Current Medical and Pharmaceutical Research
Computational Drug Discovery Methods
article

Artificial Intelligence in Drug Delivery System Design: From Predictive Modeling to Inverse Formulation Design

Balaji Nagarajan, Mohammed Thariq
article en

Abstract

AI is revolutionising medication delivery research by enabling data-driven prediction, multidimensional formulation optimisation and rational design of delivery devices with increased therapeutic performance. Traditional drug delivery development is heavily dependent on iterative experimental approaches, empirical manipulation of formulations and step-wise optimisation of single formulation variables which are resource intensive and potentially inadequate to capture complex non-linear interactions between drugs, excipients, physicochemical characteristics, biological barriers and process parameters. Machine learning, deep learning, artificial neural networks and AI-based generative computational techniques offer possibilities to model these multidimensional interactions and to speed up the finding of formulations with defined performance features. Predictive modelling can be used to predict drug release kinetics, physico-chemical stability, pharmacokinetic behaviour, drug-excipient compatibility and carrier related properties to support early stage formulation decisions. AI-assisted optimisation enables systematic combination of formulation and process parameters to identify parameter combinations that result in good drug loading capacity, particle properties, encapsulation efficiency, stability and controlled or targeted release. More recently, a new paradigm was developed called inverse design approaches where the desired therapeutic/material features are first described and mathematical models then propose potential formulations that can achieve the predefined characteristics. Coupling generative AI with inverse design could further boost this capacity to build novel delivery structures outside the empirically investigated formulation space. However, there remain several challenges to be addressed, including data heterogeneity, limited datasets, model interpretability, external validation, reproducibility, regulatory approval, and the translation of computational predictions to clinically viable formulations. This review critically discusses the evolving role of AI in drug delivery with focus on forecasting, formulation optimisation and emerging inverse design strategies as well as translational barriers and future opportunities to develop more efficient, personalised and rationally engineered systems for drug delivery.

World Journal of Current Medical and Pharmaceutical Research
Good health and well-being
Computational Drug Discovery Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon