Extreme value analysis for dietary intake based on weight class.

Biomarkers are metrics of biological variables that can identify a health state. They consist of measurement of a single variable or of a combination of variables as related to the health state that those variables represent. Biomarkers can provide an early warning of a health problem with regard to an individual patient or a group of patients and, thus, trigger actions and drive interventions. Nutritional biomarkers may be interpreted more broadly as a biological consequence of dietary intake or dietary patterns [1]. In a recent work, we established a strong connection via blood biomarkers and weight status as expressed by the body mass index (B.M.I) [2]. In this work, we are using mathematical and statistical paradigms, with a focus on the extreme value theory, in order to connect different dietary patterns between weight classes and the extreme values of those patterns. We also attempt to systematize the process of extreme value examination for medical-related data, to extract valued information and automate decision making. In our study, we use datasets derived from the Centers for Disease Control and Prevention.