Towards Foundation Models for Critical Care Time Series

TL;DR

This paper introduces a large-scale, harmonized dataset of critical care time series data, facilitating transfer learning and addressing distribution shift challenges in hospital data modeling.

Contribution

It establishes the first large-scale, multi-hospital dataset with core treatment variables for critical care time series modeling and benchmarking.

Findings

Created a harmonized dataset for critical care time series.

Demonstrated the dataset's utility for transfer learning across hospitals.

Provided a benchmark for future machine learning research in critical care.

Abstract

Notable progress has been made in generalist medical large language models across various healthcare areas. However, large-scale modeling of in-hospital time series data - such as vital signs, lab results, and treatments in critical care - remains underexplored. Existing datasets are relatively small, but combining them can enhance patient diversity and improve model robustness. To effectively utilize these combined datasets for large-scale modeling, it is essential to address the distribution shifts caused by varying treatment policies, necessitating the harmonization of treatment variables across the different datasets. This work aims to establish a foundation for training large-scale multi-variate time series models on critical care data and to provide a benchmark for machine learning models in transfer learning across hospitals to study and address distribution shift challenges. We introduce a harmonized dataset for sequence modeling and transfer learning research, representing the first large-scale collection to include core treatment variables. Future plans involve expanding this dataset to support further advancements in transfer learning and the development of scalable, generalizable models for critical healthcare applications.