Medical Event Data Standard (MEDS): Facilitating Machine Learning for Health

ICLR 2024 Workshop TS4H Submission44 Authors

Published: 08 Mar 2024, Last Modified: 18 Apr 2024TS4H PosterEveryoneRevisionsBibTeXCC BY 4.0
Keywords: healthcare, machine learning, foundation models, benchmarking
TL;DR: The Medical Event Data Standard (MEDS) is a lightweight schema aimed at enhancing machine learning on EHR data by promoting interoperability and encouraging community adoption.
Abstract: We introduce the Medical Event Data Standard (MEDS), a lightweight schema for enabling machine learning over electronic health record (EHR) data. Unlike common data models and data interoperability formats, MEDS is a minimal standard designed for maximum interoperability across datasets, existing tools, and model architectures. By providing a simple standardization layer between datasets and model-specific code, MEDS will enable more reproducible, robust, computationally performant, and collaborative machine learning research using EHR data. We highlight several existing MEDS integrations with models, datasets, and tools, and invite the community for further development and adoption.
Submission Number: 44