Sammanfattning

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).

Originalspråkengelska
Titel på värdpublikationCaring is Sharing - Exploiting the Value in Data for Health and Innovation - Proceedings of MIE 2023
RedaktörerMaria Hagglund, Madeleine Blusi, Stefano Bonacina, Lina Nilsson, Inge Cort Madsen, Sylvia Pelayo, Anne Moen, Arriel Benis, Lars Lindskold, Parisis Gallos
FörlagIOS Press
Sidor609-610
Antal sidor2
ISBN (elektroniskt)9781643683881
DOI
StatusPublished - 2023
Evenemang33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023 - Gothenburg, Sverige
Varaktighet: 2023 maj 222023 maj 25

Publikationsserier

NamnStudies in Health Technology and Informatics
Volym302
ISSN (tryckt)0926-9630
ISSN (elektroniskt)1879-8365

Konferens

Konferens33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023
Land/TerritoriumSverige
OrtGothenburg
Period2023/05/222023/05/25

Ämnesklassifikation (UKÄ)

  • Datavetenskap (datalogi)

Fingeravtryck

Utforska forskningsämnen för ”A Masked Language Model for Multi-Source EHR Trajectories Contextual Representation Learning”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här