DOIONLINE

DOIONLINE NO - IJASEAT-IRAJ-DOIONLNE-14769

Publish In
International Journal of Advances in Science, Engineering and Technology(IJASEAT)-IJASEAT
Journal Home
Volume Issue
Issue
Volume-6, Issue-4, Spl. Iss-2  ( Dec, 2018 )
Paper Title
Prediction Models of Patient Engagement in Cardiac Rehabilitation Programs
Author Name
Sepideh Jahandideh, Elizabeth Kendall, Samantha Low-Choy, Kenneth Donald, Rohan Jayasinghe
Affilition
Human Services and Social Work, School of Medicine and Menzies Health Institute Queensland, Gold Coast Campus, Griffith University, Queensland, Australia Griffith Social and Behavioral Research College, Griffith University, Queensland, Australia School of Medicine, Gold Coast Campus, Griffith University, Queensland, Australia Medical Director, Cardiology Department, Gold Coast University Hospital, Queensland, Australia
Pages
41-45
Abstract
Patient engagement in the cardiac rehabilitation (CR) process is being increasingly viewed as an essential factor in achieving desired clinical outcomes. Engagement is a construct that can inform our understanding of intention, attendance, and participation in rehabilitation. Despite the extended psychotherapy and mental health context research into patient engagement, research directly exploring this topic within the context of CR has only recently emerged. There is an absence of a coherent approach to understanding and monitoring patient engagement in CR. The most comprehensive model of therapeutic engagement was developedwith reference to acquired brain injury. However, research is yet to thoroughly test this multi-layered model. We propose that the application of such a model could help predict patient engagement in CR, thus providing a useful framework for program planning. We also expect that the lack of application to date is associated with the complexity of multi-layered models, mainly when non-linearity is created by the complex parameters that affect human behavior after an illness. We propose the use of non-linear statistical or machine learning methods to test this complex model, in conjunction with more standard approaches such as variance-weighted linear regressions. Keywords - Patient engagement, Model of therapeutic engagement, Machine learning
  View Paper