Exploring an algorithm to harmonize International Obesity Task Force and World Health Organization child overweight and obesity prevalence rates

Abstract

Background: The International Obesity Task Force (IOTF) and World Health Organization (WHO) body mass index (BMI) cut-offs are widely used to assess child overweight, obesity and thinness prevalence, but the two references applied to the same children lead to different prevalence rates.

Objectives: To develop an algorithm to harmonize prevalence rates based on the IOTF and WHO cut-offs, to make them comparable.

Methods: The cut-offs are defined as age-sex-specific BMI z-scores, for example, WHO +1 SD for overweight. To convert an age-sex-specific prevalence rate based on reference cut-off A to the corresponding prevalence based on reference cut-off B, first back-transform the z-score cut-offs $z_A$ and $z_B$ to age-sex-specific BMI cut-offs, then transform the BMIs to z-scores $z_{B,A}$ and $z_{A,B}$ using the opposite reference. These z-scores together define the distance between the two cut-offs as the z-score difference ${\mathrm{dz}}_{A,B}=\frac{1}{2}\left(z_B-z_A+z_{A,B}-z_{B,A}\right)$ . Prevalence in the target group based on cut-off A is then transformed to a z-score, adjusted up or down according to ${\mathrm{dz}}_{A,B}$ and back-transformed, and this predicts prevalence based on cut-off B. The algorithm's performance was tested on 74 groups of children from 14 European countries.

Results: The algorithm performed well. The standard deviation (SD) of the difference between pairs of prevalence rates was 6.6% (n = 604), while the residual SD, the difference between observed and predicted prevalence, was 2.3%, meaning that the algorithm explained 88% of the baseline variance.

Conclusions: The algorithm goes some way to addressing the problem of harmonizing overweight and obesity prevalence rates for children aged 2-18.

Keywords: IOTF; WHO; harmonization; obesity; overweight; prevalence.

FIGURE 1

The frequency distribution of BMI in boys aged 8 according to the WHO and IOTF references. The vertical lines mark the overweight cut‐offs WHO +1 and IOTF 25, while the shaded areas indicate the corresponding overweight prevalence (grey where they overlap). The four points mark where the cut‐offs cross the distributions, with filled circles for the reference and open circles for the opposite reference. The inset shows the four points as BMI z‐scores according to the two references, along with open triangles for z‐scores corresponding to observed overweight prevalence in the target group of boys aged 8

FIGURE 2

Prevalence rates by Centers for Disease Control, International Obesity Task Force and World Health Organization of obesity, overweight and thinness in groups of boys and girls from Deren (n = 22) and Wijnhoven (n = 52), on the z‐score scale (left) and the corresponding prevalence (%) scale (right). For overweight and obesity, the z‐score and prevalence scales are inversely related. The points for each group are connected by lines. The grey triangles correspond to the nominal prevalence rates defined by the three reference cut‐offs

FIGURE 3

Differences in the prevalence of obesity, overweight and thinness, as measured on the z‐score scale, according to pairs of reference cut‐offs, plotted against the corresponding z‐score difference between the cut‐offs, in 74 groups of boys and girls aged 6.0–17.5, (n = 302). Each point corresponds to a line in Figure 2. The line of equality is shown (dashed), and points are coded by sex and data source, while regression lines per facet are coded by data source. The lines for obesity and overweight with Deren are close to the line of equality, while those for thinness and for Wijnhoven are not

FIGURE 4

Bland–Altman plots comparing observed and predicted prevalence (%) of obesity, overweight and thinness, colour‐coded by data source (n = 604), with predicted prevalence calculated in two ways: (A) from observed prevalence and ${\mathit{dz}}_{A,B}$ (3); and (B) as for (A) except that ${\mathit{dz}}_{A,B}$ is multiplied by $b_1=0.84$. Also shown (in grey) are Bland–Altman plots comparing the original prevalence data for the pairs of references. The scatter about the origin of the original data is greatly reduced by applying the algorithm, and more so for (B) than for (A)