Timo Lustenberger¹, Helena Jenzer² and Farshideh Einsele¹, ¹Bern University of Applied Sciences, Switzerland, ²Hospital of Psychiatry, University of Zurich, Switzerland

This article demonstrates that using data mining methods such as Weighted Association Rule Mining (WARM) on an integrated Swiss database derived from a Swiss national dietary survey (menuCH) and 25 years of Swiss demographical and health data is a powerful way to determine whether a specific population subgroup is at particular risk for developing a lifestyle disease based on its food consumption patterns. The objective of the study was to discover critical food consumption patterns linked with lifestyle diseases known to be strongly tied with food consumption. Food consumption databases from a Swiss national survey menuCH were gathered along with data of large surveys of demographics and health data collected over 25 years from Swiss population conducted by Swiss Federal Office of Public Health (FOPH). These databases were integrated and reported in a previous study as a single integrated database. A data mining method such as WARM was applied to this integrated database. A set of promising rules and their corresponding interpretation was generated. As an example, the found rules of the sample show that the consumption of alcohol in small quantities does not have a negative impact on health, whereas the consumption of vegetables is important for the supply of vitamins of the B group, which help the energy metabolism to pro-vide energy. These vitamins are particularly lacking in alcoholics and should then be taken with supplements. Another finding is that dietary supplements do little specially by diabetes. Applying WARM algorithm was beneficial for this study since no interesting rules were pruned out early and the significance of the rules could be highly increased as compared to a previous study using pure Apriori Algorithm.

Data Mining, WARM Association Analysis, Diet & Chronical Diseases, Health Informatics.