Improving Stroke Risk Prediction in the General Population: A Comparative Assessment of Common Clinical Rules, a New Multimorbid Index, and Machine-Learning-Based Algorithms.

Journal: Thrombosis and haemostasis
PMID:

Abstract

BACKGROUND: There are few large studies examining and predicting the diversified cardiovascular/noncardiovascular comorbidity relationships with stroke. We investigated stroke risks in a very large prospective cohort of patients with multimorbidity, using two common clinical rules, a clinical multimorbid index and a machine-learning (ML) approach, accounting for the complex relationships among variables, including the dynamic nature of changing risk factors.

Authors

  • Gregory Y H Lip
    Liverpool Centre for Cardiovascular Science, University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, L69 3BX Liverpool, UK.
  • Ash Genaidy
    Anthem Inc., Indianapolis, Indiana, United States.
  • George Tran
    IngenioRX, Indianapolis, Indiana, United States.
  • Patricia Marroquin
    Anthem Inc., Indianapolis, Indiana, United States.
  • Cara Estes
    Anthem Inc., Indianapolis, Indiana, United States.
  • Sue Sloop
    Anthem Inc., Indianapolis, Indiana, United States.