Login / Signup

A semi-supervised approach for rapidly creating clinical biomarker phenotypes in the UK Biobank using different primary care EHR and clinical terminology systems.

Spiros DenaxasAnoop D ShahBilal Akhter MateenValerie KuanJennifer K QuintNatalie FitzpatrickAna TorralboGhazaleh FatemifarHarry Hemingway
Published in: JAMIA open (2020)
Bootstrapping phenotyping algorithms from similar EHR can potentially address pre-existing methodological concerns that undermine the outputs of biomarker discovery pipelines and provide research-quality phenotyping algorithms.
Keyphrases
  • machine learning
  • primary care
  • high throughput
  • electronic health record
  • deep learning
  • small molecule
  • cross sectional
  • quality improvement
  • single cell