Artificial intelligence in dermatologic pharmacokinetics: quantitative modeling, clinical translation, and optimization of precision therapeutics.

INTRODUCTION: Dermatology is rapidly transitioning from broad-spectrum therapies toward biologics, nanotechnology-based drug delivery, and precision therapeutics, placing pharmacokinetics (PK) at the center of treatment optimization. Conventional PK approaches are limited by the complexity of skin biology, inter-individual variability, and heterogeneous real-world clinical settings. Artificial intelligence (AI) offers new opportunities to integrate multimodal data, improve dose-exposure prediction, and enable personalized, model-informed therapeutic strategies. AREAS COVERED: This review summarizes AI applications in topical and systemic PK, focusing on AI-driven PK prediction compared with conventional compartmental and population PK models, AI-enhanced physiologically based pharmacokinetic (PBPK) and systems pharmacology models, and clinically relevant dermatologic applications. We discuss AI for optimizing drug delivery systems, precision dosing, therapeutic drug monitoring, prediction of biologic treatment response, and pharmacovigilance. The review also addresses methodological considerations, including model development, validation, reproducibility, data quality, regulatory requirements, cost-effectiveness, and ethical issues. A literature search of PubMed/MEDLINE, Embase, and Scopus identified relevant English-language studies published between January 2000 and February 2026. EXPERT OPINION: AI is expected to complement rather than replace traditional PK approaches. Hybrid AI-mechanistic models, rigorous external validation, transparent reporting, and equity-focused implementation will be essential to improve personalization, safety, treatment durability, and clinical outcomes in dermatology.