Foundational artificial intelligence models and modern medical practice

Abstract

Our opinion piece pays homage to the evolution of medical practices, tracing back to the era of Hippocrates, through significant historical milestones, and drawing parallels with the principles underpinning foundational artificial intelligence (AI) models. It emphasizes the shared ethos of both domains: a commitment to comprehensive care that values diverse data integration and individualized patient treatment. The excitement surrounding foundation models in medical imaging is understandable. However, a critical and cautious approach is crucial before widespread adoption. By addressing the present 4 major limitations (ie, data bias and generalizability, interpretability of AI models, data scarcity and diversity, and computational resources and infrastructure) and fostering a culture of rigorous research, we can unlock the true potential of these models and revolutionize medical care. This critique (opinion) paper highlights the need for a more measured approach in the field of foundation AI models for medicine in general and for medical imaging in particular. It emphasizes the importance of tackling core challenges before rushing toward clinical applications. By focusing on robust methodologies and addressing limitations, researchers can ensure the development of truly impactful and trustworthy models for the betterment of healthcare.

Keywords: artificial intelligence; clinical adoption; data bias; data scarcity and diversity; foundational models; interpretable AI; large language models; large visual models; modern medicine; precision medicine.