Use of machine learning to identify patients at risk of sub-optimal adherence: study based on real-world data from 10,929 children using a connected auto-injector device.

Journal: BMC medical informatics and decision making
PMID: 35794586

Abstract

BACKGROUND: Our aim was to develop a machine learning model, using real-world data captured from a connected auto-injector device and from early indicators from the first 3 months of treatment, to predict sub-optimal adherence to recombinant human growth hormone (r-hGH) in patients with growth disorders.

Authors

  • Amalia Spataru
    Swiss Data Science Center, ETH Zürich and EPFL, Zürich, Switzerland.
  • Paula van Dommelen
    The Netherlands Organization for Applied Scientific Research TNO, Leiden, The Netherlands.
  • Lilian Arnaud
    Connected Health and Devices, Global Healthcare Operations, Ares Trading S.A., An Affiliate of Merck KGaA, Eysins, Switzerland.
  • Quentin Le Masne
    Connected Health and Devices, Global Healthcare Operations, Ares Trading S.A., An Affiliate of Merck KGaA, Eysins, Switzerland.
  • Silvia Quarteroni
    Swiss Data Science Center, ETH Zürich and EPFL, Zürich, Switzerland.
  • Ekaterina Koledova
    Global Medical Affairs Endocrinology, Global Medical, Safety & CMO Office, Merck KGaA, Darmstadt, Germany.

Keywords

External Resources

Popular Topics
Recent Journals