Skip to main content

MEDS: a Health AI Ecosystem

Enabling reproducible modelling and analytics for health AI

Get Started with MEDSContribute to MEDS
Shockingly Simple

Shockingly Simple

MEDS (Medical Event Data Standard) is the simplest possible standard for health AI, making it easy to use with diverse data sources and modelling needs.

Health AI Ecosystem

Health AI Ecosystem

MEDS empowers a high-performance and flexible health AI ecosystem to streamline your research via parallelism and sparse data structures.

Frictionless Reproducibility

Frictionless Reproducibility

MEDS ensures that your models, tools, and pipelines are easily reproducible across data sites, research tasks, and computational environments.

Featured paper

NEJM AI ·

Matthew B. A. McDermott, Ethan Steinberg, Jason A. Fries, Robin P. van de Water, Chao Pang, Patrick Rockenschaub, Pawel Renc, Jungwoo Oh, Kamilė Stankevičiūtė, Justin Xu, Tom J. Pollard, Nassim Oufattole, Michael Wornow, Teya S. Bergamaschi, Hyewon Jeong, Simon A. Lee, Vincent Jeanselme, Kiril V. Klein, Mikkel Odgaard, Maria E. Montgomery, Arkadiusz Sitek, Mads Nielsen, Jeffrey N. Chiang, Noa Dagan, Isaac Kohane, Shalmali Joshi, Edward Choi, Nigam H. Shah

Describes MEDS in detail and reviews its adoption across institutions, datasets and models.

Read in NEJM AI