A Study about Discovery of Critical Food Consumption Patterns Linked with Lifestyle Diseases using Data Mining Methods Farshideh Einsele 1 , Leila Sadeghi 2 , Rolf Ingold 3 and Helena Jenzer 2 1 Section of Business Information, Bern University of Applied Sciences, Switzerland 2 Health Division, a R&D in Nutrition and Dietetics, Bern University of Applied Sciences, Switzerland 3 Department of Computer Science, University of Fribourg, Switzerland Keywords: Data Mining, Association Rules, Nutritional Patterns, Knowledge Interpretation, Lifestyle Diseases, Demographic, Customer Profiles, Disease Diagnosis. Abstract: Background: To date, the analysis of the implications of dietary patterns on lifestyle diseases is based on data coming either from clinical studies or food surveys, both comprised of a limited number of participants. This article demonstrates that linking big data from a grocery store sales database with demographical and health data by using data mining tools such as classification and association rules is a powerful way to determine if a specific population subgroup is at particular risk for developing a lifestyle disease based on its food consumption patterns. Objective: The objective of the study was to link big data from grocery store sales with demographic and health data to discover critical food consumption patterns linked with lifestyle diseases known to be strongly tied with food consumption. Design: Food consumption databases from a publicly available grocery store database dating from 1997–1998 were gathered along with corresponding demographics and health data from the U. S. west coast, pre-processed, cleaned and finally integrated to a unique database. Results: This study applied data mining techniques such as classification and association mining analysis. Firstly, the studied population was classified according to the demographical information “ age groups” and “race” and data for lifestyle diseases were correspondingly attributed. Secondly, association mining analysis was used to incorporate rules about food consumption and lifestyle diseases. A set of promising preliminary rules and their corresponding interpretation was generated and reported in the present paper. Conclusions: Association mining rules were successfully used to describe and predict rules linking food consumption patterns with lifestyle diseases. In the selected grocery store database, information about interesting aspects of the grocery store customers were found such as marital status, educational background, profession and number of children at home. An in-depth research on these attributes is needed to further expand the present demographical database. Since the search on the internet for demographical attributes back to the year of 2000 corresponding to the studied population subgroup was extremely laborious, the selected demographical attributes to prove the feasibility of the study were limited to age groups and race. 1 INTRODUCTION Lifestyle diseases are diseases that increase in frequency as countries become more industrialized and people get more aged. Lifestyle diseases include obesity, hypertension, heart disease, type II diabetes, cancer, mental disorders and many others. They differ from the infectious diseases originated from malnutrition, also called communicable diseases (CD) due to their contagious, dispersive nature. Lifestyle diseases are therefore among the so-called NC (non-communicable) diseases. According to World Health Organization (WHO), the growing epidemic of chronic diseases afflicting both developed and developing countries are related to dietary and lifestyle changes (WHO, 2003). “Food has become commodities produced and traded in a global market. Changes in the world food economy are reflected in shifting dietary patterns, for example, increased consumption of energy-dense diets high in fat, particularly saturated fat, and low in unrefined carbohydrates” (WHO, 2003). Food consumption patterns play an important role in the health of the people and consequently in the prevention of lifestyle diseases. These patterns represent the interplay of all the individual food choices that describe a complete food pattern. Food consumption patterns are influenced by many factors 239 Einsele F., Sadeghi L., Ingold R. and Jenzer H.. A Study about Discovery of Critical Food Consumption Patterns Linked with Lifestyle Diseases using Data Mining Methods. DOI: 10.5220/0005170402390245 In Proceedings of the International Conference on Health Informatics (HEALTHINF-2015), pages 239-245 ISBN: 978-989-758-068-0 Copyright c  2015 SCITEPRESS (Science and Technology Publications, Lda.)