Salvato in:
Dettagli Bibliografici
Autori principali: Burger, Manuel, Sergeev, Fedor, Londschien, Malte, Chopard, Daphné, Yèche, Hugo, Gerdes, Eike, Leshetkina, Polina, Morgenroth, Alexander, Babür, Zeynep, Bogojeska, Jasmina, Faltys, Martin, Kuznetsova, Rita, Rätsch, Gunnar
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.16346
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909403867774976
author Burger, Manuel
Sergeev, Fedor
Londschien, Malte
Chopard, Daphné
Yèche, Hugo
Gerdes, Eike
Leshetkina, Polina
Morgenroth, Alexander
Babür, Zeynep
Bogojeska, Jasmina
Faltys, Martin
Kuznetsova, Rita
Rätsch, Gunnar
author_facet Burger, Manuel
Sergeev, Fedor
Londschien, Malte
Chopard, Daphné
Yèche, Hugo
Gerdes, Eike
Leshetkina, Polina
Morgenroth, Alexander
Babür, Zeynep
Bogojeska, Jasmina
Faltys, Martin
Kuznetsova, Rita
Rätsch, Gunnar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Foundation Models for Critical Care Time Series
Burger, Manuel
Sergeev, Fedor
Londschien, Malte
Chopard, Daphné
Yèche, Hugo
Gerdes, Eike
Leshetkina, Polina
Morgenroth, Alexander
Babür, Zeynep
Bogojeska, Jasmina
Faltys, Martin
Kuznetsova, Rita
Rätsch, Gunnar
Machine Learning
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.
title Towards Foundation Models for Critical Care Time Series
topic Machine Learning
url https://arxiv.org/abs/2411.16346