AI and multimodal data drive evolution in precision medicine

Precision medicine is undergoing a shift from a model primarily driven by genomics to a broader approach that integrates molecular, clinical, imaging, behavioral, and real-world data. Artificial intelligence (AI) is playing a critical role in this transition by enabling the analysis of complex, multimodal datasets to improve disease classification, diagnosis, and treatment selection.

Researchers are advocating for adaptive treatment strategies that account for how diseases evolve over time. Rather than relying on molecular characteristics measured at a single point, new models aim to integrate longitudinal molecular and clinical data to inform subsequent treatment decisions. While AI offers significant potential for patient stratification and predictive analytics, challenges remain regarding data quality, privacy, governance, and the clinical reliability of AI-generated recommendations.