On the Application of Clustering and Classification Techniques to Analyze Metabolic Syndrome Severity Distribution Area and Critical Factors

Chien-Chih Wang, Jin-Jiang Jhu, Chien-Chih Wang, Jin-Jiang Jhu

Abstract

In recent years, metabolic syndrome has become one of the leading causes of death in Taiwan. This study proposes a classification and clustering method specific to the administrative regions of New Taipei City to explore the incidence and corresponding risk factors for metabolic syndrome in various geographic areas. We used integrated community health screening data and survey results obtained from people aged ≥40 years in each of the administrative regions of New Taipei City as study samples. Using a combination of Ward's method, multivariate analysis of variance, and k-means, we identified administrative regions of New Taipei City with metabolic syndrome incidences of a similar nature. Classification and regression tree methods were used to discover the key causes of metabolic syndrome in each region based on lifestyles and dietary habits. The administrative regions were divided into four groups: high-risk, slightly high-risk, normal-risk, and low-risk. The results showed that the severity of metabolic syndrome varies by region and the risk factors for metabolic syndrome vary by region. It has also been found that regions with a higher incidence of metabolic syndrome have relatively fewer medical resources.

Keywords: decision trees; integrated community health screening; metabolic syndrome.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Tree diagram for the results of Ward’s grouping method.
Figure 2
Figure 2
Distribution of severity of metabolic syndrome in New Taipei City.
Figure 3
Figure 3
Decision tree analysis results.

References

    1. Wu S.H. Master’s Thesis. National Taipei University; New Taipei City, Taiwan: 2007. Potential Risk Factors Associated with Hypertension, Hyperglycemia, Hyperplasma Prevalences in Taiwan.
    1. Ford E.S., Giles W.H., Dietz W.H. Prevalence of the metabolic syndrome among US adults: Findings from the Third National Health and Nutrition Examination Survey. JAMA J. Am. Med Assoc. 2002;287:356–359. doi: 10.1001/jama.287.3.356.
    1. Tan C.E., Ma S., Wai D., Chew S.K., Tai E.S. Can we apply the National Cholesterol Education Program Adult Treatment Panel definition of the metabolic syndrome to Asians? Diabetes Care. 2004;27:1182–1186. doi: 10.2337/diacare.27.5.1182.
    1. Meigs J.B., Wilson P.W., Nathan D.M., D’Agostino R.B., Sr., Williams K., Haffner S.M. Prevalence and characteristics of the metabolic syndrome in the San Antonio Heart and Framingham Offspring Studies. Diabetes. 2003;52:2160–2167. doi: 10.2337/diabetes.52.8.2160.
    1. Moon J.Y., Park S., Rhee J.H., Jee S.H., Park C.M., Choi D.S., Park H.Y., Ko Y.G., Choi D., Jang Y., et al. The applicability of the Asian modified criteria of the metabolic syndrome in the Korean population. Int. J. Cardiol. 2007;114:83–89. doi: 10.1016/j.ijcard.2005.12.008.
    1. Lai M.M., Li C.I., Kardia S.L., Liu C.S., Lin W.Y., Lee Y.D., Chang P.C., Lin C.C., Li T.C. Sex difference in the association of metabolic syndrome with high sensitivity C-reactive protein in a Taiwanese population. BMC Public Health. 2010;10:429. doi: 10.1186/1471-2458-10-429.
    1. Chiu Y.H., Lin W.Y., Wang P.E., Chen Y.D., Wang T.T., Warwick J., Chen T.H.H. Population-based family case-control proband study on familial aggregation of metabolic syndrome: Finding from Taiwanese people involved in Keelung community-based integrated screening (KCIS no. 5) Diabetes Res. Clin. Pract. 2007;75:348–356. doi: 10.1016/j.diabres.2006.07.014.
    1. Hsieh C.H. Master’s Thesis. Taipei Medical University; Taipei City, Taiwan: 2006. The Effects of Regular Exercise Training on Body Composition, Cardiorespiratory Fitness, and Blood Biochemical Index in Subjects with Metabolic Syndrome.
    1. Ni J., Qian T., Xi C., Rui Y., Wang J. Spatial distribution characteristics of healthcare facilities in Nanjing: Network point pattern analysis and correlation analysis. Int. J. Environ. Res. Public Health. 2016;13:833. doi: 10.3390/ijerph13080833.
    1. Yang N., Chen S., Hu W., Wu Z., Chao Y. Spatial distribution balance analysis of hospitals in Wuhan. Int. J. Environ. Res. Public Health. 2016;13:971. doi: 10.3390/ijerph13100971.
    1. Tao Z., Yao Z., Kong H., Duan F., Li G. Spatial accessibility to healthcare services in Shenzhen, China: Improving the multi-modal two-step floating catchment area method by estimating travel time via online map APIs. BMC Health Serv. Res. 2018;18:345. doi: 10.1186/s12913-018-3132-8.
    1. Breiman L. Bagging predictors. Mach. Learn. 1996;24:123–140. doi: 10.1007/BF00058655.
    1. Dummer T.J. Health geography: Supporting public health policy and planning. Can. Med. Assoc. J. 2008;178:1177–1180. doi: 10.1503/cmaj.071783.
    1. Hancock T. Lalonde and beyond: Looking back at “A New Perspective on the Health of Canadians”. Health Promot. Int. 1986;1:93–100. doi: 10.1093/heapro/1.1.93.
    1. Yu W., Cowper D., Berger M., Kuebeler M., Kubal J., Manheim L. Using GIS to profile health-care costs of VA Quality-Enhancement Research Initiative diseases. J. Med. Syst. 2004;28:271–285. doi: 10.1023/B:JOMS.0000032844.26308.95.
    1. Maantay J. Asthma and air pollution in the Bronx: Methodological and data considerations in using GIS for environmental justice and health research. Health Place. 2007;13:32–56. doi: 10.1016/j.healthplace.2005.09.009.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe