Multimodal Large Language Models in Human-Centered Health: Practical Insights

Multimodal data offer a comprehensive view of human health by integrating diverse sources, such as text, medical images, physiological signals, and behavioral data. Recent advancements in large language models (LLMs) have led to the development of multimodal large language models (MLLMs), which leverage the text understanding capabilities of LLMs and integrate them with other modalities. While MLLMs show great promise for human-centered health applications, the practical challenges of implementing them in the healthcare sector remain largely unexplored. This article discusses these practical considerations and the future potential of MLLMs in transforming human-centered healthcare.