The role of artificial intelligence in scaling nanomedicine toward broad clinical impact

Abstract The field of medicine has long sought to overcome major barriers in optimizing treatment outcomes. These include improving the ability to target disease sites, reduce drug toxicity, and improve treatment efficacy among other objectives. The emergence of nanotechnology-based drug delivery has made major strides, both during the drug development as well as the clinical validation process, toward markedly improving patient treatment outcomes. This has ultimately led to Food and Drug Administration (FDA)-approved therapies that have harnessed the implementation of nanomedicine in the clinic. As the field of nanomedicine continues to advance toward in-human studies and gain additional FDA approvals, other emerging approaches, such as artificial intelligence (AI), will play an increasing role in optimizing nanotechnology-based drug delivery. This is due to the fact that treatment strategies for indications ranging from oncology to infectious diseases rely on combination therapy for cornerstone regimens. Conventional approaches in designing combination therapy involve drug selection followed by dose finding. While nanoparticle-based drug delivery is being widely explored for drug codelivery from a single particle, or multiagent delivery using different classes of particles, and nanomedicine-based combination therapy continues to be studied for potential clinical advancement, it is necessary to develop new approaches to sufficiently interrogate both the drug and dose spaces in order to truly optimize treatment outcomes. This chapter will explore recent advances in nanomedicine-based drug delivery, and detail powerful clinically validated AI approaches that may successfully bridge nanotechnology with globally optimized combination therapies.