JMIR Publications

ABSTRACT

Background:

Background:

Considering the high prevalence of metabolic syndrome (MetS) and its importance in the development of cardiovascular disease.

Objective:

we aimed to predict important factors for the incidence of MetS using data mining models.

Methods:

Methods:

This prospective study was conducted on 3048 adults (aged ≥20 years), who participated in the fifth follow-up examination of the Tehran lipid and glucose study and followed for three years. MetS was defined according to the modified definition of the National Cholesterol Education Program/Adult Treatment panel III. The variable importance was obtained by the training set using the Random Forrest model for determining important factor that affects the MetS.

Results:

Results:

Of participants, 701 (22.9%) had developed MetS. The mean age of participants was 44.3±11.8. The total incidence rate of MetS was 229.98 (95%CI: 278.6-322.9) per 1000, and the mean of follow-up was 40.5±7.3 months. The incidence of MetS was significantly higher in males than in females (27% vs. 20%). Those affected by MetS were older, married, diabetic, low educated. and had a higher body mass index (P<0.001). In females, those affected by MetS were more hospitalized three months ago (p=0.017). Based on variable importance and multiple logistic regression, the most important determinants of MetS were history of diabetes (OR:6.32, 95% CI: [3.92, 10.20], P<0.001), BMI (OR:1.19 95% CI: [1.15, 1.22], P<0.001), age (OR:1.02, 95% CI: [1.01, 1.03], P< 0.001), female gender (OR:0.50, 95% CI: [0.38, 0.63], p< 0.001), and monounsaturated fatty acid (OR:0.97, 95% CI: [0.94, 0.99], P= 0.041).

Conclusions:

Conclusion: Based on our findings, there was high incidence rate of MetS during three years of follow-up. The most important determinants of MetS were history of diabetes, high BMI, older age, male gender, and low dietary monounsaturated fatty acid intake.