Discovering Pediatric Asthma Phenotypes on the Basis of Response to Controller Medication Using Machine Learning.

Journal: Annals of the American Thoracic Society
PMID:

Abstract

RATIONALE: Pediatric asthma has variable underlying inflammation and symptom control. Approaches to addressing this heterogeneity, such as clustering methods to find phenotypes and predict outcomes, have been investigated. However, clustering based on the relationship between treatment and clinical outcome has not been performed, and machine learning approaches for long-term outcome prediction in pediatric asthma have not been studied in depth.

Authors

  • Mindy K Ross
    1 Department of Pediatrics, Division of Pediatric Pulmonology and Sleep Medicine, and.
  • Jinsung Yoon
    2 Department of Electrical Engineering, University of California-Los Angeles, Los Angeles, California.
  • Auke van der Schaar
    3 Stratagem Technologies, London, United Kingdom; and.
  • Mihaela van der Schaar
    University of California, Los Angeles, CA, USA.