Advancing Pharmaceutical Science with Artificial Neural Networks: A Review on Optimizing Drug Delivery Systems Formulation.

Abstract

Drug Delivery Systems (DDS) have been developed to address the challenges associated with traditional drug delivery methods. These DDS aim to improve drug administration, enhance patient compliance, reduce side effects, and optimize target therapy. To achieve these goals, it is crucial to design DDS with optimal performance characteristics. The final properties of a DDS are determined by several factors that go into formulating a pharmaceutical preparation. Thus, optimizing these factors can lead to the ideal DDS formulation. Artificial Neural Networks (ANN) are computational models that mimic the function of biological neurons and neural networks and perform mathematical operations on inputs to generate outputs. ANN is widely used in medical sciences for modeling disease diagnosis and treatment, dose adjustment in combination therapy, medical education, and other fields. In the pharmaceutical sciences, ANN has gained significant attention for designing and optimizing pharmaceutical formulations. This article reviews the use of ANN in the design and optimization of pharmaceutical formulations, specifically DDS. Since DDS is highly diverse, different factors are examined for each type of DDS. These factors are considered independent and dependent parameters for each ANN model, and various examples are provided. By utilizing ANN, it is possible to establish the relationship between the formulation factors and the resulting DDS characteristics, ultimately leading to the development of optimized DDS.