Using correspondence analysis and log-linear models to investigate the factors affecting cardiovascular disease

Cardiovascular disease is the main cause of mortality in the World. This issue has seriously alarmed governments of developed and developing countries both. Diseases related to the heart play a role as the highest risk for human health. There are many factors contributing to the development of these diseases including poor diet, sedentary lifestyle, high blood pressure and hypertension. In this paper, we present a study of the influence of different factors by the correspondence analysis and log-linear models to deal with prediction of cardiovascular disease development. A survey has been conducted amongst affected people of different age groups, gender, and various education levels. Based on this data, we could determine which group would be at the higher risk leading to the cardiovascular disease. It should be noted that all participants were suffering from cardiovascular disease either slightly or seriously. Our findings show that women are at higher risk than men being affected by cardiovascular disease. Moreover, different factors such as smoking, high cholesterol level, physical inactivity and poor diet contribute significantly to the possibility for this disease. Via our analyses, we also can obtain a better comprehension of the data structure and better interpretation of the results by combining two approaches (correspondence analysis and log-linear models). Also, it is concluded that correspondence analysis allows us to find the strong correlations between involving variables. That could lead to the conception of prognostic and biomechanical models using the inter-correlations between variables and building a good structure of big data in the future