The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Photo of Mattias Ohlsson

Mattias Ohlsson

Professor

Photo of Mattias Ohlsson

A Masked Language Model for Multi-Source EHR Trajectories Contextual Representation Learning

Author

  • Ali Amirahmadi
  • Mattias Ohlsson
  • Kobra Etminani
  • Olle Melander
  • Jonas Björk

Editor

  • Maria Hagglund
  • Madeleine Blusi
  • Stefano Bonacina
  • Lina Nilsson
  • Inge Cort Madsen
  • Sylvia Pelayo
  • Anne Moen
  • Arriel Benis
  • Lars Lindskold
  • Parisis Gallos

Summary, in English

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).

Department/s

  • Centre for Environmental and Climate Science (CEC)
  • LU Profile Area: Natural and Artificial Cognition
  • eSSENCE: The e-Science Collaboration
  • Division of Occupational and Environmental Medicine, Lund University
  • EpiHealth: Epidemiology for Health
  • EXODIAB: Excellence of Diabetes Research in Sweden
  • MultiPark: Multidisciplinary research focused on Parkinson´s disease
  • Surgery and public health
  • EPI@LUND

Publishing year

2023

Language

English

Pages

609-610

Publication/Series

Studies in Health Technology and Informatics

Volume

302

Document type

Conference paper

Publisher

IOS Press

Topic

  • Computer Science

Keywords

  • deep learning
  • disease prediction
  • electronic health records
  • Masked language model
  • patient trajectories
  • representation learning

Conference name

33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023

Conference date

2023-05-22 - 2023-05-25

Conference place

Gothenburg, Sweden

Status

Published

Research group

  • Surgery and public health
  • EPI@LUND

ISBN/ISSN/Other

  • ISSN: 0926-9630
  • ISSN: 1879-8365
  • ISBN: 9781643683881