Predicting Acute Graft-Versus-Host Disease Using Machine Learning and Longitudinal Vital Sign Data From Electronic Health Records.

Journal: JCO clinical cancer informatics
PMID: 32083957

Abstract

PURPOSE: Acute graft-versus-host disease (aGVHD) remains a significant complication of allogeneic hematopoietic cell transplantation (HCT) and limits its broader application. The ability to predict grade II to IV aGVHD could potentially mitigate morbidity and mortality. To date, researchers have focused on using snapshots of a patient (eg, biomarkers at a single time point) to predict aGVHD onset. We hypothesized that longitudinal data collected and stored in electronic health records (EHRs) could distinguish patients at high risk of developing aGVHD from those at low risk.

Authors

  • Shengpu Tang
    Division of Computer Science and Engineering, Department of Electronic Engineering and Computer Science, University of Michigan, Ann Arbor, MI.
  • Grant T Chappell
    Division of Hematology/Oncology, Department of Pediatrics, University of Michigan, Ann Arbor, MI.
  • Amanda Mazzoli
    Division of Hematology/Oncology, Department of Pediatrics, University of Michigan, Ann Arbor, MI.
  • Muneesh Tewari
    Division of Hematology/Oncology, Department of Internal Medicine, University of Michigan, Ann Arbor, MI.
  • Sung Won Choi
    Division of Hematology/Oncology, Department of Pediatrics, University of Michigan, Ann Arbor, MI.
  • Jenna Wiens
    Computer Science and Engineering, University of Michigan, Ann Arbor.

Keywords

External Resources

Popular Topics
Recent Journals