Saved in:
Bibliographic Details
Main Authors: Amirahmadi, Ali, Ohlsson, Mattias, Etminani, Kobra, Melander, Olle, Björk, Jonas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.06675
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916121104351232
author Amirahmadi, Ali
Ohlsson, Mattias
Etminani, Kobra
Melander, Olle
Björk, Jonas
author_facet Amirahmadi, Ali
Ohlsson, Mattias
Etminani, Kobra
Melander, Olle
Björk, Jonas
contents Using electronic health records data and machine learning to guide future decisions needs to address challenges, including 1) long/short-term dependencies and 2) interactions between diseases and interventions. Bidirectional transformers have effectively addressed the first challenge. Here we tackled the latter challenge by masking one source (e.g., ICD10 codes) and training the transformer to predict it using other sources (e.g., ATC codes).
format Preprint
id arxiv_https___arxiv_org_abs_2402_06675
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Masked language model for multi-source EHR trajectories contextual representation learning
Amirahmadi, Ali
Ohlsson, Mattias
Etminani, Kobra
Melander, Olle
Björk, Jonas
Machine Learning
Using electronic health records data and machine learning to guide future decisions needs to address challenges, including 1) long/short-term dependencies and 2) interactions between diseases and interventions. Bidirectional transformers have effectively addressed the first challenge. Here we tackled the latter challenge by masking one source (e.g., ICD10 codes) and training the transformer to predict it using other sources (e.g., ATC codes).
title A Masked language model for multi-source EHR trajectories contextual representation learning
topic Machine Learning
url https://arxiv.org/abs/2402.06675