Machine learning is enabling a shift toward predictive, genotype-directed care in precision medicine and pharmacogenomics, according to a recent study in the Annals of Medicine and Surgery discussed in the article. Pharmacogenomics, which involves understanding an individual’s genetic makeup and medication response, has created new opportunities for tailored care through AI-powered modeling of drug-gene interactions and machine learning models that synthesize genomic and population-level data to determine customized dosing and adverse reaction propensity. These opportunities are being leveraged across psychiatry, cardiology, oncology, and infectious diseases. In psychiatry, ML models can predict treatment resistance for antidepressants in advance; in cardiology, genotype-directed warfarin and clopidogrel dosing have reduced mortality and adverse event rates; in oncology, machine learning models analyze biomarkers to enable "ultra-targeted therapies that strike tumor-specific mutations with remarkable precision." Another study published in Frontiers in Artificial Intelligence notes that the transition from a one-size-fits-all approach to curated treatments marks one of the biggest shifts in medical history, made possible by frontier models unlocking new ways to analyze and compute data.