DOI QR코드

DOI QR Code

Nomogram for screening the risk of developing metabolic syndrome using naïve Bayesian classifier

  • Minseok Shin (Department of Statistics, Yeungnam University) ;
  • Jeayoung Lee (Department of Statistics, Yeungnam University)
  • Received : 2022.01.24
  • Accepted : 2022.07.26
  • Published : 2023.01.31

Abstract

Metabolic syndrome is a serious disease that can eventually lead to various complications, such as stroke and cardiovascular disease. In this study, we aimed to identify the risk factors related to metabolic syndrome for its prevention and recognition and propose a nomogram that visualizes and predicts the probability of the incidence of metabolic syndrome. We conducted an analysis using data from the Korea National Health and Nutrition Survey (KNHANES VII) and identified 10 risk factors affecting metabolic syndrome by using the Rao-Scott chi-squared test, considering the characteristics of the complex sample. A naïve Bayesian classifier was used to build a nomogram for metabolic syndrome. We then predicted the incidence of metabolic syndrome using the nomogram. Finally, we verified the nomogram using a receiver operating characteristic curve and a calibration plot.

Keywords

References

  1. Aguilar M, Bhuket T, Torres S, Liu B, and Wong RJ (2015). Prevalence of the metabolic syndrome in the United States, 2003-2012, JAMA, 313, 1973-1974. https://doi.org/10.1001/jama.2015.4260
  2. Akobeng AK (2007). Understanding diagnostic tests 3: Receiver operating characteristic curves, Acta Paediatrica, 96, 644-647. https://doi.org/10.1111/j.1651-2227.2006.00178.x
  3. Chung SM, Park JC, Moon JS, and Lee JY (2018). Novel nomogram for screening the risk of developing diabetes in a Korean population, Diabetes Research and Clinical Practice, 142, 286-293. https://doi.org/10.1016/j.diabres.2018.05.036
  4. Cook NR (2008). Statistical evaluation of prognostic versus diagnostic models: Beyond the ROC curve, Clinical Chemistry, 54, 17-23. https://doi.org/10.1373/clinchem.2007.096529
  5. D'Agostino Sr RB, Grundy S, Sullivan LM, Wilson P, and CHD Risk Prediction Group (2001). Validation of the Framingham coronary heart disease prediction scores: Results of a multiple ethnic groups investigation, JAMA, 286, 180-187. https://doi.org/10.1001/jama.286.2.180
  6. Iasonos A, Schrag D, Raj GV, and Panageas KS (2008). How to build and interpret a nomogram for cancer prognosis, Journal of Clinical Oncology, 26, 1364-1370. https://doi.org/10.1200/JCO.2007.12.9791
  7. Jung CH, Park JS, Lee WY, and Kim SW (2002). Effects of smoking, alcohol, exercise, level of education, and family history on the metabolic syndrome in Korean adults, Korean Journal of Medicine, 63, 649-659.
  8. Kim MH, Seo JH, and Lee JY (2019) A study on the method of constructing a nomogram for predicting dyslipidemia, Journal of the Korean Data & Information Science Society, 30, 1063-1075. https://doi.org/10.7465/jkdi.2019.30.5.1063
  9. Kim MH and Lee JY (2020). How to construct a nomogram for hypertension using complex sampling data from Korean adults, Communications in Statistics-Theory and Methods, 51, 2357-2367. https://doi.org/10.1080/03610926.2020.1774057
  10. Korea Centers for Disease Control and Prevention (2018). The Seventh Korea National Health and Nutrition Examination Survey (KNHANES VII), Available from: https://knhanes.kdca.go.kr/knhanes/sub03/sub03_02_05.do
  11. Korean Statistical Information Service (KOSIS) (2018). Census, Statistic Korea, Republic of Korea. Accessed February 2021, Available from: https://kosis.kr/statisticsList/statisticsListIndex.do?menuld=M_01_01&vwcd=MT_ZTITLE&parmTabId=M_01_01&outLink=Y&entrType=#content-group.
  12. Kshirsagar AV, Chiu YL, Bomback AS, August PA, Viera AJ, Colindres RE, and Bang H (2010). A hypertension risk score for middle-aged and older adults, The Journal of Clinical Hypertension, 12, 800-808. https://doi.org/10.1111/j.1751-7176.2010.00343.x
  13. Lee KM, Kim WJ, and Yun SJ (2009). A clinical nomogram construction method using genetic algorithm and naive Bayesian technique, Journal of Korean Institute of Intelligent Systems, 19, 796-801. https://doi.org/10.5391/JKIIS.2009.19.6.796
  14. Lee WY, Park JS, Noh SY, Rhee EJ, Kim SW, and Zimmet PZ (2004). Prevalence of the metabolic syndrome among 40,698 Korean metropolitan subjects, Diabetes Research and Clinical Practice, 65, 143-149. https://doi.org/10.1016/j.diabres.2003.12.007
  15. Mozina M, Demsar J, Kattan M, and Zupan B (2004). Nomograms for visualization of Naive Bayesian classifier, In Proceedings of the Knowledge Discovery in Databases: PKDD 2004, Italy, 337-348.
  16. National Cholesterol Education Program (2001). Executive summary of the third report of the national cholesterol education program (NCEP) expert panel on detection, evaluation and treatment of high blood cholesterol in adults (adult treatment panel III), JAMA, 285, 2486-2497. https://doi.org/10.1001/jama.285.19.2486
  17. Park JC, Kim MH, and Lee JY (2018). Nomogram comparison conducted by logistic regression and naive Bayesian classifier using Type 2 diabetes mellitus, The Korean Journal of Applied Statistics, 31, 573-585.
  18. Rao JNK and Scott AJ (1981). The analysis of categorical data from complex sample surveys: Chisquared tests for goodness of fit the independence in two-way tables, Journal of the American Statistical Association, 76, 221-230. https://doi.org/10.1080/01621459.1981.10477633
  19. Reaven GM (1988). Diabetes, Role of Insulin Resistance in Human Disease, 37, 1595-1607. https://doi.org/10.2337/diab.37.12.1595
  20. Seo JH, Kim HJ, and Lee JY (2020). Nomogram construction to predict dyslipidemia based on a logistic regression analysis, Journal of Applied Statistics, 47, 914-926. https://doi.org/10.1080/02664763.2019.1660760
  21. Shin MS and Lee JY (2021). Building a nomogram for metabolic syndrome using logistic regression with a complex sample - 39,991,680 case study, Healthcare, 10, 372.
  22. Shin MS (2022). Proposal of nomogram using logistic and Bayesian technique for metabolic syndrome with complex sample (Master's thesis), Yeungnam University.
  23. Tran BT, Jeong BY, and Oh JK (2017). The prevalence trend of metabolic syndrome and its components and risk factors in Korean adults: Results from the Korean National Health and Nutrition Examination Survey 2008-2013, BMC Public Health, 17, 71.
  24. Yang D (2013). Build prognostic nomograms for risk assessment using SAS, In Proceedings of SAS Global Forum 2013, Cleveland, OH, 264, Available from: http://support.sas.com/resources/papers/proceedings13/264-2013pdf
  25. Yoo JS, Jung JI, Park CG, Kang SW, and Ahn JA (2009). Impact of life style characteristics on prevalence risk of metabolic syndrome, Journal of Korean Academy of Nursing, 39, 594-601. https://doi.org/10.4040/jkan.2009.39.4.594