Phenotypic characterisation of Crohn's disease severity

Annu Int Conf IEEE Eng Med Biol Soc. 2015 Aug:2015:7023-6. doi: 10.1109/EMBC.2015.7320009.

Abstract

Crohn's disease (CD) is a highly heterogeneous disease, with great variation in patient severity. Using supervised machine learning techniques to predict severity from common laboratory and clinical measurements, we found that high levels of C-reactive protein and low levels of lymphocytes and albumin are important predictive factors. Building upon this knowledge, we used extreme value theory to create a probabilistic model that combines information about behaviour in the extremes of these lab measurements to produce a single risk score over time. We then clustered these patient risk scores to identify several common clinical trajectories for CD patients.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • C-Reactive Protein / metabolism
  • Cluster Analysis
  • Crohn Disease / diagnosis*
  • Female
  • Follow-Up Studies
  • Humans
  • Lymphocytes / metabolism
  • Male
  • Models, Theoretical
  • Phenotype
  • Sensitivity and Specificity
  • Serum Albumin / metabolism

Substances

  • Serum Albumin
  • C-Reactive Protein