Artificial Intelligence-Based Optimization of Pulmonary Drug Delivery Performance in Smart Inhaler Drug–Device Combination Systems

Advancements in pulmonary drug delivery have enabled effective treatment approaches for more severe disease conditions, such as chronic obstructive pulmonary diseases, asthma, cystic fibrosis, and other pulmonary disorders, via targeted, sustained, and immediate drug delivery routes with minimal systemic side effects. However, conventional delivery systems have many limitations, such as poor drug targeting, adherence, and deposition, which ultimately cause variations in drug profiles and therapeutic efficacy. Recent advances in artificial intelligence (AI) and machine learning (ML) have enabled the development of smart inhaler drug–device combination systems for personalized therapy using predictive formulation parameters, design variables, device performance, and inhalation pattern monitoring. Advanced AI techniques, such as artificial neural networks, deep learning, random forests, support vector machines, deep learning algorithms, and computational modeling, predict the mass median aerodynamic diameter (MMAD), fine-particle fraction (FPF), emitted dose, and regional lung deposition. Smart inhalation devices coupled with digital sensors and computing systems enable the real-time monitoring of inhalation profiles and adherence. Moreover, AI- and ML-enabled Quality by Design (QbD) and digital twin framework technologies enhance the optimization of manufacturing process parameters, consistency, robustness, and scale-up performance. Although several developments have been reported, there is still room for improvement in terms of data heterogeneity, algorithm transparency, interpretability, cybersecurity, regulations, and long-term clinical standardization. This review emphasizes the use of AI to improve the performance of pulmonary drug delivery through smart inhaler drug–device combination therapies, focusing on technological advancements, formulation optimizations, smart inhalers, regulatory issues, current limitations, and future perspectives of AI-based pulmonary drug delivery.