Document Type : Original/Review Paper


1 Department of Industrial Engineering, Birjand University of Technology, Birjand, Iran.

2 Department of Computer Engineering, Birjand University of Technology, Birjand, Iran.

3 Cardiovascular Diseases Research Centre, Department of Pediatric, Birjand University of Medical Sciences, Birjand, Iran.

4 Cardiovascular Diseases Research Centre, Department of Cardiology, Birjand University of Medical Sciences, Birjand, Iran.


Today, Metabolic Syndrome in the age group of children and adolescents has become a global concern. In this paper, a data mining model is used to determine a continuous Metabolic Syndrome (cMetS) score using Linear Discriminate Analysis (cMetS-LDA). The decision tree model is used to specify the calculated optimal cut-off point cMetS-LDA. In order to evaluate the method, multilayer perceptron neural network (NN) and Support Vector Machine (SVM) models were used and statistical significance of the results was tested with Wilcoxon signed-rank test. According to the results of this test, the proposed CART is significantly better than the NN and SVM models. The ranking results in this study showed that the most important risk factors in making cMetS-LDA were WC, SBP, HDL and TG for males and WC, TG, HDL and SBP for females. Our research results show that high TG and central obesity have the greatest impact on MetS and FBS has no effect on the final prognosis. The results also indicate that in the preliminary stages of MetS, WC, HDL and SBP are the most important influencing factors that play an important role in forecasting.


[1] A. Pan, N. Keum, O. I. Okereke, Q. Sun, M. Kivimaki, R. R. Rubin, and F. B. Hu, “Bidirectional association between depression and metabolic syndrome: a systematic review and meta-analysis of epidemiological studies,” Diabetes care, vol. 35, no. 5, pp. 1171-1180, 2012.
[2] D. Lent-Schochet, M. McLaughlin, N. Ramakrishnan, and I. Jialal, “Exploratory metabolomics of metabolic syndrome: A status report,” World journal of diabetes, vol. 10, no. 1, pp. 23, 2019.
[3] W. Borena, M. Edlinger, T. Bjørge, C. Häggström, B. Lindkvist, G. Nagel, A. Engeland, T. Stocks, S. Strohmaier, and J. Manjer, “A prospective study on metabolic risk factors and gallbladder cancer in the metabolic syndrome and cancer (Me-Can) collaborative study,” PloS one, vol. 9, no. 2, pp. e89368, 2014.
[4] A. Maleki, M. Montazeri, N. Rashidi, M. Montazeri, and E. Yousefi-Abdolmaleki, “Metabolic syndrome and its components associated with chronic kidney disease,” Journal of research in medical sciences: the official journal of Isfahan University of Medical Sciences, vol. 20, no. 5, pp. 465, 2015.
[5] M. Jari, M. Qorbani, M. E. Motlagh, R. Heshmat, G. Ardalan, and R. Kelishadi, “Association of overweight and obesity with mental distress in Iranian adolescents: the CASPIAN-III study,” International journal of preventive medicine, vol. 5, no. 3, pp. 256, 2014.
[6] M. K. Birarra, and D. A. Gelayee, “Metabolic syndrome among type 2 diabetic patients in Ethiopia: a cross-sectional study,” BMC cardiovascular disorders, vol. 18, no. 1, pp. 1-12, 2018.
[7] M. Zardast, K. Namakin, T. Chahkandi , F. Taheri , T. Kazemi , and B. Bijari, “Prevalence of metabolic syndrome in elementary school children in East of Iran,” J Cardiovasc Thorac Res, vol. 7, no. 4, pp. 158-163, 2015.
[8] M.-K. Lee, K. Han, M. K. Kim, E. S. Koh, E. S. Kim, G. E. Nam, and H.-S. Kwon, “Changes in metabolic syndrome and its components and the risk of type 2 diabetes: a nationwide cohort study,” Scientific reports, vol. 10, no. 1, pp. 1-8, 2020.
[9] P. Golabi, M. Otgonsuren, L. de Avila, M. Sayiner, N. Rafiq, and Z. M. Younossi, “Components of metabolic syndrome increase the risk of mortality in nonalcoholic fatty liver disease (NAFLD),” Medicine, vol. 97, no. 13, 2018.
[10] A. N. Rodrigues, G. R. Abreu, R. S. Resende, W. L. Goncalves, and S. A. Gouvea, “Cardiovascular risk factor investigation: a pediatric issue,” International journal of general medicine, vol. 6, pp. 57, 2013.
[11] P. Shi, J. M. Goodson, M. L. Hartman, H. Hasturk, T. Yaskell, and J. Vargas, “Continuous Metabolic Syndrome Scores for Children Using Salivary Biomarkers,” PLoS ONE, vol. 10, no. 9, pp. e0138979, 2015.
[12] D. Pandit , S. Chiplonkar, A. Khadilkar, A. Kinare, and V. Khadilkar “Efficacy of a continuous metabolic syndrome score in Indian children for detecting subclinical atherosclerotic risk,” Int J Obes (Lond), vol. 35, no. 10, pp. 1318-1324, 2011.
[13] H.-S. Ejtahed, M. Qorbani, M. E. Motlagh, P. Angoorani, S. Hasani-Ranjbar, H. Ziaodini, M. Taheri, Z. Ahadi, S. Beshtar, and T. Aminaee, “Association of anthropometric indices with continuous metabolic syndrome in children and adolescents: the CASPIAN-V study,” Eating and Weight Disorders-Studies on Anorexia, Bulimia and Obesity, vol. 23, no. 5, pp. 597-604, 2018.
[14] S. P. Sawant, and A. S. Amin, “Use of continuous metabolic syndrome score in overweight and obese children,” The Indian Journal of Pediatrics, vol. 86, no. 10, pp. 909-914, 2019.
[15] S. Rose, F. F. Dieny, and A. Tsani, “The Correlation between Waist-to-Height Ratio (WHtR) and Second to Fourth Digit Ratio (2D: 4D) with an Increase in Metabolic Syndrome Scores in Obese Adolescent Girls,” Electronic Journal of General Medicine, vol. 17, no. 3, 2020.
[16] G. Shafiee, R. Kelishadi, R. Heshmat, M. Qorbani, M. E. Motlagh, T. Aminaee, G. Ardalan, M. Taslimi, P. Poursafa, and B. Larijani, “First report on the validity of a continuous Metabolic Syndrome score as an indicator for Metabolic Syndrome in a national sample of paediatric population—the CASPIAN-III study,” Endokrynologia Polska, vol. 64, no. 4, pp. 278-284, 2013.
[17] A. L. Beam, and I. S. Kohane, “Big Data and Machine Learning in Health Care,” JAMA, vol. 319, no. 13, pp. 1317-1318, 2018.
[18] J. H. Chen, and S. M. Asch, “Machine Learning and Prediction in Medicine — Beyond the Peak of Inflated Expectations,” New England Journal of Medicine, vol. 376, no. 26, pp. 2507-2509, 2017.
[19] B. A. Goldstein, A. M. Navar, and R. E. Carter, “Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges,” European Heart Journal, vol. 38, no. 23, pp. 1805-1814, 2016.
[20] S. M. Cho, P. C. Austin, H. J. Ross, H. Abdel-Qadir, D. Chicco, G. Tomlinson, C. Taheri, F. Foroutan, P. R. Lawler, and F. Billia, “Machine Learning Compared To Conventional Statistical Models For Predicting Myocardial Infarction Readmission And Mortality: A Systematic Review,” Canadian Journal of Cardiology, 2021.
[21] H. C. Lee, J. S. Park, J. C. Choe, J. H. Ahn, H. W. Lee, J.-H. Oh, J. H. Choi, K. S. Cha, T. J. Hong, and M. H. Jeong, “Prediction of 1-Year Mortality from Acute Myocardial Infarction Using Machine Learning,” The American Journal of Cardiology, vol. 133, pp. 23-31, 2020.
[22] M. V. Bhargavi, V. R. Mudunuru, and S. Veeramachaneni, "Colon cancer stage classification using decision trees," Data Engineering and Communication Technology, pp. 599-609: Springer, 2020.
[23] A. G. Aydin, O. Eray, A. V. Sayrac, A. Oskay, And U. D. Ulusar, “The Reliability of an Artificial Intelligence Tool,‘Decision Trees’, in Emergency Medicine Triage,” 2020.
[24] K. T. Win, “Comparison of C4. 5 and Weighted C4. 5 Decision Trees for Breast Cancer Classification,” Unversity of Computer Studies, Yangon, 2020.
[25] G. Battineni, N. Chintalapudi, and F. Amenta, “Late-Life Alzheimer’s Disease (AD) Detection Using Pruned Decision Trees,” Int J Brain Disord Treat, vol. 6, pp. 033, 2020.
[26] M. Mamprin, S. Zinger, P. de With, J. Zelis, and P. Tonino, "Gradient boosting on decision trees for mortality prediction in transcatheter aortic valve implantation." pp. 325-329.
[27] M. M. Ghiasi, “Implementing decision tree-based algorithms in medical diagnostic decision support systems,” Memorial University of Newfoundland, 2020.
[28] A. Alaoui, and Z. Elberrichi, "Enhanced Ant Colony Algorithm for Best Features Selection for a Decision Tree Classification of Medical Data," Critical Approaches to Information Retrieval Research, pp. 278-293: IGI Global, 2020.
[29] Y. Wei, X. Wang, and M. Li, “Intelligent Medical Auxiliary Diagnosis Algorithm Based on Improved Decision Tree,” Journal of Electrical and Computer Engineering, vol. 2020, 2020.
[30] C.-S. Yu, Y.-J. Lin, C.-H. Lin, S.-T. Wang, S.-Y. Lin, S. H. Lin, J. L. Wu, and S.-S. Chang, “Predicting metabolic syndrome with machine learning models using a decision tree algorithm: Retrospective cohort study,” JMIR medical informatics, vol. 8, no. 3, pp. e17110, 2020.
[31] J. C. Eisenmann, K. R. Laurson, K. D. DuBose, B. K. Smith, and J. E. Donnelly, “Construct validity of a continuous metabolic syndrome score in children,” Diabetology & metabolic syndrome, vol. 2, no. 1, pp. 1-8, 2010.
[32] H.-S. Ejtahed, Z. Mahmoodi, M. Qorbani, P. Angoorani, M. E. Motlagh, S. Hasani-Ranjbar, H. Ziaodini, M. Taheri, R. Heshmat, and R. Kelishadi, “A comparison between body mass index and waist circumference for identifying continuous metabolic syndrome risk score components in Iranian school-aged children using a structural equation modeling approach: the CASPIAN-V study,” Eating and Weight Disorders-Studies on Anorexia, Bulimia and Obesity, pp. 1-8, 2020.
[33] N. V. Chawla, “SMOTEBoost: Improving prediction of the minority class in boosting, in Knowledge Discovery in Databases: PKDD ” Springer, vol. P.107-119, 2003.
[34] A. Ramezankhani, “The impact of oversampling with SMOTE on the performance of 3 classifiers in prediction of type 2 diabetes,” Medical Decision Making, vol. p. 0272989X14560647., 2014.
[35] N. Chawla, “SMOTE: Synthetic Minority Over-Sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. p. 321-357, 2002.
[36] R. A. Fisher, “The statistical utilization of multiple measurements,” Annals of eugenics, vol. 8, no. 4, pp. 376-386, 1938.
[37] K. Fukunaga, Introduction to statistical pattern recognition: Elsevier, 2013.
[38] A. Tharwat, T. Gaber, A. Ibrahim, and A. E. Hassanien, “Linear discriminant analysis: A detailed tutorial,” AI communications, vol. 30, no. 2, pp. 169-190, 2017.
[39] G. T. Reddy, M. P. K. Reddy, K. Lakshmanna, R. Kaluri, D. S. Rajput, G. Srivastava, and T. Baker, “Analysis of dimensionality reduction techniques on big data,” IEEE Access, vol. 8, pp. 54776-54788, 2020.
[40] A. M. Martínez, and A. C. Kak, “Pca versus lda,” IEEE transactions on pattern analysis and machine intelligence, vol. 23, no. 2, pp. p. 228-233, 2001.
[41] L. Breiman, J. Friedman, C. J. Stone, and R. A. Olshen, Classification and regression trees: CRC press, 1984.
[42] S. García, D. Molina, M. Lozano, and F. Herrera, “A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: a case study on the CEC’2005 special session on real parameter optimization,” Journal of Heuristics, vol. 15, no. 6, pp. 617-644, 2009.
[43] J. W. Johnson, “A Heuristic Method for Estimating the Relative Weight of Predictor Variables in Multiple Regression,” Multivariate Behav Res, vol. 35, no. 1, pp. p. 1-19, 2000.
[44] J. C. Eisenmann, K. R. Laurson, K. D. DuBose, B. K. Smith, and J. E. Donnelly, “Construct validity of a continuous metabolic syndrome score in children.,” Diabetology & metabolic syndrome, vol. 2, no. 1, pp. 8, 2010.
[45] F. Taheri , K. Namakin, M. Zardast, T. Chahkandi , T. Kazemi , and B. Bijari, “ Cardiovascular Risk Factors: A Study on the Prevalence of MS among 11-18 Years Old School Children in East of Iran, 2012,” Nutr Food SCI Res, vol. 2, no. 1, pp. 27-34, 2015.
[46] B. Battaloglu Inanc, “Metabolic Syndrome in School Children in Mardin, South-Eastern of Turkey,” Eurasian J Med, vol. 46, no. 3, pp. 156-163, 2014.
[47] W. Ahrens, L. A. Moreno, S. Mårild, D. Molnár, A. Siani, and S. De Henauw, “Metabolic syndrome in young children: definitions and results of the IDEFICS study,” Int J Obes (Lond), vol. 38, no. Suppl 2, pp. S4-s14, 2014.
[48] N. Rizk, M. Amin, and M. Yousef, “A pilot study on metabolic syndrome and its associated features among Qatari school children,” Int J Gen Med, vol. 4, pp. 521-525, 2011.
[49] A. Z. Iqbal, S. Basharat , and A. Basharat “Prevalence of the metabolic syndrome and its component abnormalities among school age Pakistani children,” J Ayub Med Coll Abbottabad, vol. 26, no. 2, pp. 194-199, 2014.
[50] G. Shafiee, R. Kelishadi , R. Heshmat, M. Qorbani, M. E. Motlagh , and T. Aminaee, “First report on the validity of a continuous Metabolic Syndrome score as an indicator for Metabolic Syndrome in a national sample of paediatric population—the CASPIAN-III study,” Endokrynol Pol, vol. 64, no. 4, pp. 278-284, 2013.
[51] F. Costa Teixeira, F. E. Felix Pereira , A. Fernandes Pereira , and B. Gonçalves Ribeiro “Metabolic syndrome's risk factors and its association with nutritional status in school children,” Prev Med Rep, vol. 6, no. 2017, pp. 27-32, 2017.
[52] C. Cadenas-Sanchez , J. R. Ruiz, I. Labayen, I. Huybrechts, Y. Manios, and M. González-Gross,  “Prevalence of Metabolically Healthy but Overweight/Obese Phenotype and Its Association With Sedentary Time, Physical Activity, and Fitness.,” J Adolesc Health., vol. 61, no. 1, pp. 107-114, 2017.
[53] I. S. Okosun, J. M. Boltri, R. Lyn, and M. Davis-Smith “Continuous metabolic syndrome risk score, body mass index percentile, and leisure time physical activity in American children,” J Clin Hypertens (Greenwich), vol. 1, no. 2, pp. 636-644, 2010.
[54] T. Cohen, T. Hazell, C. A. Vanstone, C. Rodd, and H. A. Weiler, “A family-centered lifestyle intervention for obese six- to eight-year-old children: results from a one-year randomized controlled trial conducted in Montreal, Canada,” Can J Public Health, vol. 107, no. 4-5, pp. 453-460, 2016.
[55] R. M. Mantovani, N. P. Rocha, D. M. Magalhães, I. G. Barbosa , A. L. Teixeira, and A. C. Simões E Silva “Early changes in adipokines from overweight to obesity in children and adolescents,” J Pediatr (Rio J), vol. 92, no. 6, pp. 624-630, 2016.
[56] S. M. Barbalho, M. Oshiiwa, F. C. Sato Fontana, E. Ribeiro Finalli , M. Paiva Filho , and A. P. Machado Spada, “Metabolic syndrome and atherogenic indices in school children: A worrying panorama in Brazi,” Diabetes Metab Syndr, vol. S1871-4021, no. 17, pp. 30003-30006, 2017.