Assessment of the Metabolic Syndrome in Children and Adolescents in Birjand, Iran: A Data Mining Approach

Document Type : Machine learning-Sadoghi

Authors

• Fatemeh Taheri ¹
• Vahide Babaiyan ²
• Mohsen Saffarian ³
• Seyed Mahmood Kazemi ³
• Kokab Namakin ¹
• Toba Kazemi ⁴
• Azra Ramezankhani ⁵

¹ Cardiovascular Diseases Research Centre, Department of Pediatric, Birjand University of Medical Sciences, Birjand, Iran.

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

³ Department of Industrial Engineering, Birjand University of Technology, Birjand, Iran

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

⁵ Prevention of Metabolic Disorders Research Center, Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran

10.22067/cke.2021.63297.0

Abstract

Metabolic Syndrome (MS) is the collection of risk factors for coronary artery disease (CAD). It is responsible for cardiovascular disease (CVD), type 2 diabetes, cancer, renal and mental diseases with the transition from childhood to adulthood. The MS is increasing in recent decades in different societies, especially in Iran. This study was conducted to determine the predictive factors of MS in children and adolescents in Birjand (Capital of South Khorasan Province, Iran) using a data mining approach. The four different analyses for females and males (6-11 and 12-18 year-old groups) were carried out using three popular decision tree models. The most important prognostic factors for MS were high level of TG and low level of DBP and HDL in 6-11-year-old group, and high level of waist circumference (WC) and low level of TG for 12-18-year-old group. The most important factors were TG and HDL in females and WC and TG in males. Raising teens and families' awareness of the risk factors, screening children and teens, monitoring and controlling the risk factors through life style correction such as more physical activity and healthy eating are recommended.

Keywords

• Index Terms
• Metabolic Syndrome
• Data Mining
• Decision Tree
• School-Age Population

Main Subjects

• Machine learning

---

References

• Silveira, C. Buonani , P. Monteiro, A. Mello, B. M. Antunes, and I. F. Freitas Júnior, “Metabolic Syndrome: Criteria for Diagnosing in Children and Adolescents”, Endocrinol Metab Synd, Vol. 2, no.3, pp. 118, 2013.
• Kelishadi, S. Hovsepian, M. Qorbani, F. Jamshidi, Z. Fallah, S. Djalalinia, “National and sub-national prevalence, trend, and burden of cardiometabolic risk factors in Iranian children and adolescents 1990 – 2013”, Arch Iran Med, Vol. 17, pp. 71-80, 2014.
• Jari, M. Qorbani, , M. E. Motlagh, R. Heshmat, G. Ardalan, and R. elishadi, “Association of overweight and obesity with mental distress in Iranian adolescents: The CASPIAN-III study”, Int J Prev Med, Vol. 5, no.3, pp. 256-261, 2014.
• Kelishadi, S. Hovsepian, S. Djalalinia, F. Jamshidi, and M. Qorbani, “A systematic review on the prevalence of metabolic syndrome in Iranian children and adolescents”, J Res Med Sci, Vol. 21, pp. 88, 2016.
• Taheri, T. Chahkandi, T. Kazemi, and B. Bijari, “Prevalence of Obesity and Overweight among Adolescents of Birjand, East of Iran”, Iranian Journal of Diabetes and Obesity, Vol. 6, pp. 176-181,  2014.
• W.-H. Tan, K.-B. Ooi, L.-Y. Leong, and B. Lin, “Predicting the drivers of behavioral intention to use mobile learning: A hybrid SEM-Neural Networks approach”, Computers in Human Behavior, Vol. 36, pp. 198-213, 2014.
• Lee, H. Lee, J. R. Choi, and S. B. Koh, Scientific Reports, “Development and Validation of Prediction Model for Risk Reduction of Metabolic Syndrome by Body Weight Control: A Prospective Population-based Study”, Scientific Reports, Vol. 10, no. 1, pp. 1-9, 2020.
• -S. Yu, Y.-J. Lin, C.-H. Lin, S.-T. Wang, S.-Y. Lin, S. H. Lin, et al., “Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study”, JMIR Med Inform, Vol. 8, no. 3, pp. e17110, 2020.
• Tang, T. Zhao, N. Huang, W. Lin, Z. Luo, and C. Ling, “Identification of Traditional Chinese Medicine Constitutions and Physiological Indexes Risk Factors in Metabolic Syndrome: A Data Mining Approach”, Evidence-Based Complementary and Alternative Medicine, Vol. 2019, 2019.
• A. Kakudi, C. K. Loo, F. M. Moy, L. C. Kau, and K. Pasupa, “Diagnosis of Metabolic Syndrome using Machine Learning, Statistical and Risk Quantification Techniques: A Systematic Literature Review”, Malaysian Journal of Computer Science, Vol. 34, No. 3, pp. 221-241, 2021.
• Khashayar, R. Heshmat, M. Qorbani, M. Motlagh, T. Aminaee, G. Ardalan, “Metabolic Syndrome and cardiovascular Risk Factors in a National Sample of Adolescent Population in the Middle East and North Africa:The CASPIAN III study”, International Journal of Endocrinology, pp. ID702095,8 pages, 2013.
• Chiti, F. Hoseinpanah, Y. Mehrabi, and F. Azizi, “The Prevalence of MS  in Adolescents  with Varying Degreesof  Body  Weight:  Tehran  Lipid  and  Glucose  Study TLGS”, Iranian  Journal  of endocrinology  Metabolism, Vol. 11, no. 6, pp. 625-637, 2010.
• E. Mehairi, A. A. Khouri, M. M. Naqb, S. J. Muhairi, F. A. Maskari, N. Nagelkerke, “Emirati adolescents: A school-based study”, PLoS One, Vol. 8, no. 2, pp. e56159, 2013.
• L. Abdulwahab, Prevalence of Metabolic Syndrom among male Kuwaiti Adolescents aged 10-19 years, Health, Vol. 5, pp. 938-942, 2013.
• K. Hong, N. H. Trang, and M. J. Dibley, “Prevalence of metabolic syndrome and factor analysis of cardiovascular risk clustering among adolescents in Ho Chi Minh City”, Vietnam, Prev Med, Vol. 55, no. 5, pp. 409-411, 2012.
• Yu, L. Zhao, J. Ma, J. Piao, J. Zhang, X. Hu, “Prevalence of MS among 7- 17year- old overweight and obese children and adolescents, Wei Sheng Yan Jiu”, Journal of Hygiene Research, Vol. 41, no. 3, pp. 410-413, 2012
• Rosini, S. A. Z. Oppermann Moura, R. D. Rosini, M. J. Machado, and da Silva, E. L, “Metabolic Syndrome and Importance of Associated Variables in Children and Adolescents in Guabiruba - SC, Brazil”, Arq Bras Cardiol, Vol. 105, pp. 37-44, 2015.
• Setayeshgar, S. J. Whiting, and H. A. Vatanparast, “Metabolic Syndrome in Canadian Adults and Adolescents: Prevalence and Associated Dietary Intake”, ISRN Obesity, Vol. 2012, pp. ID 816846, 8 pages, 2012
• Chandola, E. Brunner, and M. Marmot, “Chronic stress at work and the metabolic syndrome: prospective study”, Bmj, Vol. 332, no. 7540, pp. 521-525, 2006.
• Ramezankhani, A. Kabir, O. Pournik, F. Azizi,  and F. Hadaegh, “Classification-based data mining for identification of risk patrns associated with hypertension in Middle Eastern population: A 12-year longitudinal study”, Medicine, Vol. 95, no. 35, 2016.
• Hadavandi, J. Shahrabi, and Y. Hayashi, “SPMoE: a novel subspace-projected mixture of experts model for multi-target regression problems”, Soft Computing, Vol. 20, no. 5, pp. 2047-2065, 2016.
• Hadavandi, J. Shahrabi, and S. Shamshirband, “A novel Boosted-neural network ensemble for modeling multi-target regression problems”, Engineering Applications of Artificial Intelligence, Vol. 45, no. 2015, pp. 204-219, 2015.
• Kazemi, E. Hadavandi, S. Shamshirband, and S. Asadi, “A novel evolutionary-negative correlated mixture of experts model in tourism demand estimation”, Computers in Human Behavior, Vol. 64, no. 2016, pp. 641-655, 2016.
• Ramezankhani, E. Hadavandi, O. Pournik, J. Shahrabi, F. Azizi, and F. Hadaegh, “Decision tree-based modelling for identification of potential interactions between type 2 diabetes risk factors: a decade follow-up in a Middle East prospective cohort study”, BMJ open, Vol 6, No. 12, pp. e013336, 2016.
• Worachartcheewan, C. Nantasenamat, C. Isarankura-Na-Ayudhya, P. Pidetcha, and V. Prachayasittikul, “Identification of metabolic syndrome using decision tree analysis”, Diabetes Research and Clinical Practice, Vol. 90. no. 1, pp. e15-e18, 2010.
• V. Chawla, A. Lazarevic, L. O. Hall, and K. W. Bowyer, “SMOTEBoost: Improving prediction of the minority class in boosting,” European Conference on Principles of Data Mining and Knowledge Discovery in Knowledge Discovery in Databases: PKDD 2003, ed: Springer, pp. 107-119, 2003.
• Ramezankhani, O. Pournik, J. Shahrabi, F. Azizi, F. Hadaegh,and Khalili, D, “The impact of oversampling with SMOTE on the performance of 3 classifiers in prediction of type 2 diabetes”, Medical Decision Making, Vol. 36, no. 1, pp. 137-144, 2014.
• Chawla, K. Bowyer, L. Hall, and K. WP, “SMOTE: Synthetic Minority Over-Sampling Technique”, Journal of Artificial Intelligence Research, Vol. 16, pp. 321-357, 2002.
• Breiman, J. Friedman, C. J. Stone, and R. A. Olshen, “Classification and regression trees: CRC press”, ISBN 9780412048418 - CAT# C4841, 1984.
• V. Kass, “An exploratory technique for investigating large quantities of categorical data”, Applied statistics, Vol. 29, no. 2, pp.119-127, 1980.
• -Y. Loh, and Y.-S. Shih, “Split selection methods for classification trees”, Statistica sinica, Vol. 7, no. 4, pp. 815-840, 1997.
• Bekkar, H. K. Djemaa, and T. A. Alitouche, 2013. “Evaluation Measures for Models Assessment over Imbalanced Data Sets,” Journal of Information Engineering and Applications, Vol. 3, no. 10, pp. 27-38, 2013.
• Rosset, “Model selection via the AUC”, in Proceedings of the twenty-first international conference on Machine learning, pp. 89, 2004.
• Hovsepian, R. Kelishadi, S. Djalalinia, F. Farzadfar, S. h. Naderimagham, and M. Qorbani, “Prevalence of dyslipidemia in Iranian children and adolescents: A systematic review”, J Res Med Sci, Vol. 20, no. 5, pp. 503-521, 2015.
• Taheri, T. Chahkandi, T. Kazemi, B. Bijari, M. Zardast, and K. Namakin, “Lipid Profiles and Prevalence of Dyslipidemia in Eastern Iranian Adolescents, Birjand, Iran”, J Med Sci, Vol. 40, no. 4, pp. 341-348, 2015.
• Bijari, F. Taheri, T.Chahkandi, T. Kazemi, K. Namakin, and M. Zardast, “The Relationship between Serum Lipids and Obesity among Elementary School”, Journal of Research in Health Sciences, Vol. 15, no. 2, pp. 83-87, 2015.
• Rashidi, S. P. Payami, S. M. Latifi, M. Karandish, A. Armaghan Moravej, M. Aminzadeh, “Prevalence of metabolic syndrome and its correlated factors among children and adolescents of Ahvaz aged 10 – 19”, Journal of Diabetes & Metabolic Disorders, Vol. 13, no. 1, pp. 1-6, 2014.
• Kim, and W. So, “Prevalence of Metabolic Syndrome among Korean Adolescents According to the National Cholesterol Education Program”, Adult Treatment Panel III and International Diabetes Federation, Nutrients, Vol. 8, no. 10, 2016.
• Bhalavi, P. Deshmukh, M. Atram, K. Goswami, and N. Garg, “Prevalence of metabolic syndrome and cardio-metabolic risk factors in the adolescents of Rural Wardha”, International Journal of Biomedical Research, Vol. 5, no. 12, pp. 754-757, 2014.
• Rashidi, F. farzad, B. Ghaderian, H. B. Shahbazian, M. Latifi, M. Karandish, “Prevalence of Metabolic Syndrome and Its Predicting Factors in Type 2 Diabetic Patients in Ahvaz”, JUNDISHAPUR SCIENTIFIC MEDICAL JOURNAL. Vol. 11, no. 2, pp. 163-175, 2012.
• Aaron, J. Kelly, D. R. Steinberge, J. R. Jacobs, H. ChingPing, and A. Moran, “Predicting Cardiovascular Risk in Young Adulthood from Metabolic Syndrome, its Component Risk Factors, and a Cluster Score in Childhood”, Int J Pediatr Obes, Vol. 6, no. 0, pp. 283-289, 2011.
• Santoro, A. Amato, A. Grandone, C. Brienza, V. varese, N. Tartaglione, “Predicting Metabolic in Obese Children and Adolescents Look, Measure and Ask”, Obese Facts, Vol. 6, no. 1, pp. 48-56, 2013.
• Hirschler, C. Aranda, M. D. L. Calcagno, G. Maccalini, and M. Jadzinsky, “Can Waist Circumference Identify Children With the Metabolic Syndrome?”, Arch Pediatr Adolesc Med, Vol. 159, no. 8, pp. 740-744, 2005.