Improving the Body Mass Index (BMI) Formula with Heuristic Search

Abstract

The body mass index (BMI) is nowadays the most used tool to evaluate obesity, involving only two anthropometric measures easy to obtain, the weight and the height (BMI=weight/height2). The BMI is valuable because it evaluates obesity, classifying people into 'underweight', 'normal weight', and 'overweight' classes. The value of the BMI means that through a classification of the weight condition, it implicitly estimates the possible alteration in metabolic parameters, such as blood glucose, blood pressure, and cholesterol, among others. Because it is widely used, a little variation in the accuracy of the classification of the BMI may involve thousands of individuals misclassified. The aim of this work was to evaluate variations of the BMI formula searching for one which increases the specificity and sensitivity, respect to metabolic alterations. We applied heuristic search of algebraic and constant variation to the original BMI formula, for example, a rule to generate new variations of the BMI formula is increasing the exponent of the denominator by 0.1. The heuristic function used was the intersection of specificity and sensitivity of the particular formula evaluated, i.e., the maximum values of the two statistics. To evaluate the specificity and sensitivity a database of a sample of 4,308 young Mexicans (17-24 years old), including the parameters of the metabolic alterations evaluated, and weight and height was used. The heuristic search can be applied to adjust formulae that evaluate other clinical alterations, such as the atherogenic index. Also, we propose to use the variations of the BMI formula found in this study, with the high sensitivity and specificity when evaluate obesity of young Mexican as a risk to present metabolic alterations.