Taguchi/Machine Learning Hybrid Framework for Optimization of Particulate Drug Delivery Systems

Abstract

Optimizing particulate drug carrier systems requires balancing multiple formulation parameters to achieve target physicochemical properties while minimizing experimental burden. Here, we implement a hybrid optimization framework integrating a Taguchi orthogonal array (OA) design with statistical modeling and machine learning (ML)-based interpretability, using doxorubicin-loaded chitosan microspheres (DOX-CS MSs). Microspheres were synthesized via a water-in-oil emulsion crosslinking method and characterized by FTIR, XRD, and FESEM to confirm chemical structure, crystallinity, and spherical morphology. The optimization targeted a particle size of 5-7 {micro}m and encapsulation efficiency (EE) >90%. An initial L Taguchi OA design efficiently narrowed the formulation space by varying chitosan concentration (1-3% w/v), glutaraldehyde concentration (1.5-5% v/v), and crosslinking time (3-5 h), yielding nine core formulations. Pearson/Spearman correlation, second-order polynomial regression (Poly{superscript 2}), and Gradient Boosting Machine (GBM) models quantified parameter influences and predicted performance. SHapley Additive exPlanations (SHAP) identified chitosan concentration as the primary determinant of both size and EE, with glutaraldehyde content exerting secondary, synergistic effects. Poly{superscript 2} response-surface modeling achieved high predictive accuracy (R{superscript 2} = 0.983 for size; R{superscript 2} = 0.986 for EE) and yielded explicit regression equations for real-time formulation targeting. This hybrid Taguchi-ML approach enables rapid factor prioritization, reveals nonlinear interactions overlooked by conventional Taguchi analysis, and offers transparent ML interpretability. Beyond chitosan-based carriers, it provides a generalizable, scalable route to rational formulation design in complex particulate systems for targeted biomedical applications.