The effect of various foods on the development of cardiovascular disease (CVD) has already been investigated. We performed a food pattern analysis and evaluated the association between the consumption of various patterns and the prevalence of CVD risk factors among elderly people from Mediterranean islands (the MEDIS study). During 2005-2006, 300 men and women from Cyprus, 142 from Mitilini, 100 from Samothraki, and 104 from Kefalonia islands (65-100 years old) were enrolled. CVD risk factors (i.e., hypertension, diabetes, hypercholesterolemia, and obesity) were assessed through standard procedures. All participants were asked about their usual frequency of consumption of various foods through a semiquantitative food frequency questionnaire, and food pattern analysis using the principal components analysis (PCA) method was then performed. PCA extracted five components that explained the 56.53% of the total variation in intake: i.e., a food pattern (component 1) that was loaded mainly on low-fat products, a high glycemic index and high-fat pattern (component 2), a pattern that included consumption of cereals and sweets (component 3), a pattern that was characterized by the intake of dairy products and fruits (component 4), and a pattern that was characterized by the consumption of alcoholic beverages (component 5). Ordinal logistic regression analysis revealed that component 1, component 3, and component 5 were associated with lower likelihood of having increased burden of CVD (P < .01), irrespective of various potential confounders. Food pattern analysis revealed the current nutritional status of our elderly participants, and provided a pathway for reducing the burden of CVD risk factors among these people.