Machine Learning Algorithms for Objective Remission and Clinical Outcomes with Thiopurines.

Journal: Journal of Crohn's & colitis
PMID: 28333183

Abstract

BACKGROUND AND AIMS: Big data analytics leverage patterns in data to harvest valuable information, but are rarely implemented in clinical care. Optimising thiopurine therapy for inflammatory bowel disease [IBD] has proved difficult. Current methods using 6-thioguanine nucleotide [6-TGN] metabolites have failed in randomized controlled trials [RCTs], and have not been used to predict objective remission [OR]. Our aims were to: 1) develop machine learning algorithms [MLA] using laboratory values and age to identify patients in objective remission on thiopurines; and 2) determine whether achieving algorithm-predicted objective remission resulted in fewer clinical events per year.

Authors

  • Akbar K Waljee
    VA Center for Clinical Management Research, VA Ann Arbor Health Care System, Ann Arbor, Michigan.
  • Kay Sauder
    Division of Gastroenterology, University of Michigan, Ann Arbor, MI, USA.
  • Anand Patel
    Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
  • Sandeep Segar
    Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA.
  • Boang Liu
    Department of Statistics, University of Michigan, Ann Arbor, Michigan.
  • Yiwei Zhang
    College of Chemical Engineering, Nanjing Forestry University Nanjing 210037 China njfu2304@163.com +86-25-85427396.
  • Ji Zhu
    Department of Statistics, University of Michigan, Ann Arbor, Michigan.
  • Ryan W Stidham
    Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan.
  • Ulysses Balis
    Department of Pathology, University of Michigan, Ann Arbor, MI, USA.
  • Peter D R Higgins
    Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Michigan Health System, Ann Arbor, Michigan.

Keywords

External Resources

Popular Topics
Recent Journals