hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Masked Language Model for Multi-Source EHR Trajectories Contextual Representation Learning
Halmstad University, School of Information Technology.ORCID iD: 0000-0002-1999-8435
Halmstad University, School of Information Technology. Lund University, Lund, Sweden.ORCID iD: 0000-0003-1145-4297
Halmstad University, School of Information Technology.ORCID iD: 0000-0003-2006-6229
Lund University, Lund, Sweden.
Show others and affiliations
2023 (English)In: Caring is Sharing – Exploiting the Value in Data for Health and Innovation: Proceedings of MIE 2023 / [ed] Maria Hägglund; Madeleine Blusi; Stefano Bonacina; Lina Nilsson; Inge Cort Madsen; Sylvia Pelayo; Anne Moen; Arriel Benis; Lars Lindsköld; Parisis Gallos, Amsterdam: IOS Press, 2023, Vol. 302, p. 609-610Conference paper, Published paper (Refereed)
Abstract [en]

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). © 2023 European Federation for Medical Informatics (EFMI) and IOS Press.

Place, publisher, year, edition, pages
Amsterdam: IOS Press, 2023. Vol. 302, p. 609-610
Series
Studies in Health Technology and Informatics, ISSN 0926-9630, E-ISSN 1879-8365 ; 302
Keywords [en]
deep learning, disease prediction, electronic health records, Masked language model, patient trajectories, representation learning
National Category
Computer Sciences
Research subject
Health Innovation, IDC; Health Innovation, IDC
Identifiers
URN: urn:nbn:se:hh:diva-51734DOI: 10.3233/SHTI230217PubMedID: 37203760Scopus ID: 2-s2.0-85159757442ISBN: 978-1-64368-389-8 (print)OAI: oai:DiVA.org:hh-51734DiVA, id: diva2:1801836
Conference
The 33rd Medical Informatics Europe Conference, MIE2023, Gothenburg, Sweden, 22-25 May, 2023
Available from: 2023-10-03 Created: 2023-10-03 Last updated: 2023-10-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Amirahmadi, AliOhlsson, MattiasEtminani, Kobra

Search in DiVA

By author/editor
Amirahmadi, AliOhlsson, MattiasEtminani, KobraBjörk, Jonas
By organisation
School of Information Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
isbn
urn-nbn

Altmetric score

doi
pubmed
isbn
urn-nbn
Total: 60 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf