A Data-Driven Assessment of the Metabolic Syndrome Criteria for Adult Health Management in Taiwan.

Ming-Shu Chen,Shih-Hsin Chen

doi:10.3390/ijerph16010092

Abstract

According to the modified Adult Treatment Panel III, five indices are used to define metabolic syndrome (MetS): waist circumference (WC), high blood pressure, fasting glucose, triglycerides (TG), and high-density lipoprotein cholesterol. Our work evaluates the importance of these indices. In addition, we attempted to identify whether trends and patterns existed among young, middle-aged, and older people. Following the analysis, a decision tree algorithm was used to analyze the importance of the five criteria for MetS because the algorithm in question selects the attribute with the highest information gain as the split node. The most important indices are located on the top of the tree, indicating that these indices can effectively distinguish data in a binary tree and the importance of this criterion. That is, the decision tree algorithm specifies the priority of the influence factors. The decision tree algorithm examined four of the five indices because one was excluded. Moreover, the tree structures differed among the three age groups. For example, the first key index for middle-aged and older people was TG whereas for younger people it was WC. Furthermore, the order of the second to fourth indices differed among the groups. Because the key index was identified for each age group, researchers and practitioners could provide different health care strategies for individuals based on age. High-risk middle-aged and healthy older people maintained low values of TG, which might be the most crucial index. When a person can avoid the first and second indices provided by the decision tree, they are at lower risk of MetS. Therefore, this paper provides a data-driven guideline for MetS prevention.

Highlights

With economic growth and changes in diet and lifestyle habits, people are increasingly being diagnosed with metabolic syndrome (MetS)
After running the decision tree algorithm, we show the results of the whole dataset in Figure 3; l_tg, g_wc, g_ssr, and l_hdlc were included in the decision tree, whereas dm_fg was excluded
Hildrum et al discovered that the prevalence of MetS increased strongly with age according to the Adult Treatment Panel III (ATP III) and International Diabetes Federation [20]

Summary

Introduction

With economic growth and changes in diet and lifestyle habits, people are increasingly being diagnosed with metabolic syndrome (MetS). MetS is associated with gender, age, and obesity [1]. In the United States, 34% of adults met the criteria for MetS [2]. Men and women older than 60 years are more likely to have MetS. In São Paulo, Brazil, the prevalence of MetS in adults was 30.3% [3]. In Taiwan, the prevalence of MetS in women was markedly higher in postmenopausal women, for whom the prevalence exceeded that among men [4]. MetS is a global health risk, and places a substantial burden on health care [8]. Because MetS is highly correlated with other diseases [4,9,10,11,12], MetS management is key for adult health management

Methods

Results

Discussion

Conclusion