Pacific D
Bayesian Analysis of Psychological Diseases related to Chronic Illness for the Canadian Community Health Surveys (307835)
Salah El Adlouni, Université de Moncton*Jalila Jbilou, Université de Moncton
Keywords: Bayesian Logistic Regression, Psychological Diseases, Chronic Illness, Behavioural cardiology, Canada
Health delivery systems are currently constrained with respect to providing integrated effective interventions to assist cardiac people in the inherent challenge of adherence to healthier behaviours (AHB). Indeed, in people diagnosed with cardiovascular disease (CVD), poor AHB can compromise prognosis and survival. There has been tremendous work on psychosocial and economic factors (PSEF) as major determinants of AHB through the cognitive and behavioural theories lens. This study aims to develop a Logistic Regression in Bayesian framework to introduce prior information, and examine PSEF as determinants of AHB in cardiac adults and propose a tailored risk stratification tool. Probability samples of men and women aged 18 to 74, from all Canadian provinces, randomly selected using their phone number and invited to participate to the Canadian Community Health Surveys (CCHS). The survey relies upon a large sample of respondents and is designed to provide reliable estimates at the health region level every 2 years (2001 to 2015). We consider Bayesian Logistic Regression (BLR) to extract linear components that capture correlations between both classes of variables, PSEF and AHB.