Machine Learning-Driven Optimization of Therapeutic Substance Composition for High-Hardness, Fast-Dissolving Microneedles for Androgenetic Alopecia Treatment

This study addresses the challenge of delivering platelet-rich plasma (PRP) for androgenetic alopecia (AGA) treatment by developing a machine-learning-driven strategy to optimize the composition of microneedles (MNs). The approach involves selecting therapeutic substances, conducting 18 orthogonal experiments, and using machine learning to identify an optimal material composition that achieves high hardness and rapid dissolution. The resulting MNs demonstrated sustained release of growth factors, over 90% bacterial inhibition, reactive oxygen species scavenging, and enhanced proliferation of dihydrotestosterone-damaged human dermal papilla cells. In vivo studies showed significant hair regrowth in AGA mice via the Wnt/β-catenin pathway, surpassing minoxidil's effects, while avoiding biosafety risks from synthetic materials. This framework could expedite the clinical translation of biomaterials like MNs.