Artificial intelligence (AI) is increasingly driving advances in precision medicine, with the potential to enable treatments that reflect the molecular and clinical profiles of each patient. This chapter examines how AI is reshaping precision therapy through methods such as predictive modeling, unsupervised learning, graph neural networks, and reinforcement learning, applied to drug response prediction, patient stratification, and adaptive treatment design. The discussion extends to generative AI, focusing on its applications in drug discovery and repurposing alongside the development of virtual patient models and digital twins for personalized health management. Integrating multiscale biomedical data from omics, structural biology, clinical records, imaging, and population health offers a pathway to more precise therapeutic targeting and the discovery of novel clinical patterns. Case studies from recent years illustrate this potential while highlighting persistent challenges such as data heterogeneity, interoperability gaps, and the ethical dimensions of large-scale data use. Looking ahead, we reflect on the transition toward integrated, multimodal decision support systems that incorporate emerging technologies such as synthetic biology and digital twins and on the steps needed to move healthcare toward a patient-centric, predictive, therapeutic, and preventive discipline.