Machine learning applied to wearable fitness tracker data and the risk of hospitalizations and cardiovascular events.

Journal: American journal of preventive cardiology
Published Date:

Abstract

BACKGROUND: Wearable fitness trackers generate extensive physiological and activity data, offering potential to monitor health and predict outcomes. Machine learning (ML) techniques applied to these data may enable early identification of adverse health conditions, such as hospitalizations and development of cardiovascular diseases (CVD). This study aimed to evaluate ML models' ability to forecast the incidence of (1) hospitalizations from any cause and (2) of new diagnosis of CVD, including a composite of heart failure (HF), coronary artery disease or myocardial infarction (CAD-MI), cardiomyopathy (CMP), and atrial fibrillation (AF).

Authors

  • John Kundrick
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Aditi Naniwadekar
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Virginia Singla
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Krishna Kancharla
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Aditya Bhonsale
    Heart and Vascular Institute, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania.
  • Andrew Voigt
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Alaa Shalaby
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • N A Mark Estes
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Sandeep K Jain
    Heart and Vascular Institute, Division of Cardiology, University of Pittsburgh Medical Center, Pittsburgh, PA, United States.
  • Samir Saba
    Division of Cardiology, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA.

Keywords

No keywords available for this article.