The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power. 1. Introduction Obesity (body mass index > 29.9？kg/m2) has been considered a global public health problem due to its high prevalence and high morbidity [1]. In fact, the prevalence of obesity has increased substantially, both in developed and in under development countries. In the United States, for example, it is estimated that 35.5% of women and 32.2% of adult men present obesity [2]. The Brazilian Institute of Geography and Statistics (IBGE) indicates that 50.1% of men and 48% of women have overweight (25？kg/m2 ≤ BMI < 29.9？kg/m2), while 12.4% of men and 16.9% of women are suffering from obesity in Brazil [3]. The high risk attributed to obesity is related particularly to its association with increased risk factors for cardiovascular disease, notably hypertension [4, 5]. In order to adopt early preventive/therapeutic actions to minimize the risk of cardiovascular events in obese individuals, methods that can predict hypertension using low cost procedures are necessary, especially in underdeveloped and in developing countries. Body mass index (BMI), waist circumference (WC), hip circumference (HC), and waist-hip ratio (WHR) are among the most practical and cost effective measures for evaluation of obesity, with the advantage that both WC and WHR present positive correlations with the amount of visceral fat, and together
References
[1]
P. Hossain, B. Kawar, and M. Nahas, “Obesity and diabetes in the developing world—a growing challenge,” The New England Journal of Medicine, vol. 356, no. 3, pp. 213–215, 2007.
[2]
K. M. Flegal, M. D. Carroll, C. L. Ogden, and L. R. Curtin, “Prevalence and trends in obesity among US adults, 1999–2008,” Journal of the American Medical Association, vol. 303, no. 3, pp. 235–241, 2010.
[3]
IBGE-Instituto Brasileiro de Geografia e Estatística, “POF, 2008-2009: desnutri？？o cai e peso das crian？as Brasileiras ultrapassa padr？o internacional,” 2010, http://saladeimprensa.ibge.gov.br/noticias?view=noticia&id=1&busca=1&idnoticia=1699.
[4]
G. Gürsoy, S. Ulu, Y. Acar et al., “Relation of resist？n w？th obesity and some cardiovascular risk factors in hypertensive women,” Journal of Research in Medical Sciences, vol. 17, no. 5, pp. 443–447, 2012.
[5]
E. Ugwuja, N. Ogbonna, A. Nwibo, and I. A. Onimawo, “Overweight and obesity, lipid profile and atherogenic indices among civil servants in Abakaliki, south eastern Nigeria,” Annals of Medical and Health Sciences Research, vol. 3, no. 1, pp. 13–18, 2013.
[6]
M. Dalton, A. J. Cameron, P. Z. Zimmet et al., “Waist circumference, waist-hip ratio and body mass index and their correlation with cardiovascular disease risk factors in Australian adults,” Journal of Internal Medicine, vol. 254, no. 6, pp. 555–563, 2003.
[7]
O. Perichart-Perera, M. Balas-Nakash, E. Schiffman-Selechnik, A. Barbato-Dosal, and F. Vadillo-Ortega, “Obesity increases metabolic syndrome risk factors in school-aged children from an urban school in Mexico City,” Journal of the American Dietetic Association, vol. 107, no. 1, pp. 81–91, 2007.
[8]
M. A. Abolfotouh, I. A. Al-Alwan, and M. A. Al-Rowaily, “Prevalence of metabolic abnormalities and association with obesity among Saudi college students,” International Journal of Hypertension, vol. 2012, Article ID 819726, 8 pages, 2012.
[9]
L. Yong, T. Guanghui, T. Weiwei, L. Liping, and Q. Xiaosong, “Can body mass index, waist circumference, waist-hip ratio and waist-height ratio predict the presence of multiple metabolic risk factors in Chinese subjects?” BMC Public Health, vol. 11, article 35, 2011.
[10]
J. B. Dixon, B. J. G. Strauss, C. Laurie, and P. C. O'Brien, “Smaller hip circumference is associated with dyslipidemia and the metabolic syndrome in obese women,” Obesity Surgery, vol. 17, no. 6, pp. 770–777, 2007.
[11]
Y. Wang, E. B. Rimm, M. J. Stampfer, W. C. Willett, and F. B. Hu, “Comparison of abdominal adiposity and overall obesity in predicting risk of type 2 diabetes among men,” American Journal of Clinical Nutrition, vol. 81, no. 3, pp. 555–563, 2005.
[12]
M. A. Beydoun, M. T. Kuczmarski, Y. Wang, M. A. Mason, M. K. Evans, and A. B. Zonderman, “Receiver-operating characteristics of adiposity for metabolic syndrome: the healthy aging in neighborhoods of diversity across the life span (HANDLS) study,” Public Health Nutrition, vol. 14, no. 1, pp. 77–92, 2011.
[13]
L. S. Erdreich and E. T. Lee, “Use of relative operating characteristic analysis in epidemiology. A method for dealing with subjective judgement,” American Journal of Epidemiology, vol. 114, no. 5, pp. 649–662, 1981.
[14]
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, Springer, Berlin, Germany, 2nd edition, 2009.
[15]
Y.-C. Lee, W.-J. Lee, Y.-C. Lin et al., “Obesity and the decision tree: predictors of sustained weight loss after bariatric surgery,” Hepatogastroenterology, vol. 56, no. 96, pp. 1745–1749, 2009.
[16]
P. Hertzman, “The cost effectiveness of orlistat in a 1-year weight-management programme for treating overweight and obese patients in Sweden: a treatment responder approach,” PharmacoEconomics, vol. 23, no. 10, pp. 1007–1020, 2005.
[17]
A. Bhattarai, V. Rus, and D. Dasgupta, “Classification of clinical conditions: a case study on prediction of obesity and its co-morbidities,” in Proceedings of the 10th International Conference on Intelligent Text Processing and Computational Linguistics (CICLING '09), Mexico City, Mexico, March 2009.
[18]
O. Regnier-Coudert, J. McCall, R. Lothian, T. Lam, S. McClinton, and J. N'Dow, “Machine learning for improved pathological staging of prostate cancer: a performance comparison on a range of classifiers,” Artificial Intelligence in Medicine, vol. 55, no. 1, pp. 25–35, 2012.
[19]
J. T. Pollettini, S. R. Panico, J. C. Daneluzzi, R. Tinós, J. A. Baranauskas, and A. A. Macedo, “Using machine learning classifiers to assist healthcare-related decisions: classification of electronic patient records,” Journal of Medical Systems, vol. 36, no. 6, pp. 3861–3874, 2012.
[20]
D. Page, “Predicting clinical events from electronic health records,” in Proceedings of the Microsoft Research Machine Learning Summit, Issy-les-Moulineaux, France, 2013.
[21]
K. Sharp, W. Wiegerinck, W. Burgers et al., “Searching for genetic dark matter,” in Proceedings of the Microsoft Research Machine Learning Summit, Issy-les-Moulineaux, France, 2013.
[22]
A. Criminisi, “Machine learning for medical image analysis,” in Proceedings of the Microsoft Research Machine Learning Summit, Paris, France, 2013.
[23]
J. T. Leek, “Predicting with trees. Coursera's data analysis class material,” 2013, https://github.com/jtleek/dataanalysis.
[24]
T. G. Lohman, A. F. Roche, and R. Martorell, Anthropometric Standardization Reference Manual, Human Kinetics Books, Champaign, Ill, USA, 1988.
[25]
H. Golino, “Women's dataset from the “Predicting increased blood pressure using machine learning” paper,” Figshare, 2013.
[26]
H. Golino, “Men's dataset from the “Predicting increased blood pressure using machine learning” paper,” Figshare, 2013.
[27]
B. D. Ripley, “Package “tree”: classification and regression trees. R package version 1.0-33,” 2013, http://cran.r-project.org/web/packages/tree.
[28]
P. Geurts, A. Irrthum, and L. Wehenkel, “Supervised learning with decision tree-based methods in computational and systems biology,” Molecular Biosystems, vol. 5, no. 12, pp. 1593–1605, 2009.
[29]
Harvard Obesity Prevention Source, Harvard School of Public Health, Cambridge, Mass, USA, http://www.hsph.harvard.edu/obesity-prevention-source/.
[30]
Ministério da Saúde, “Vigilancia de fatores de risco e prote？？o para doen？as cr？nicas por inquérito telef？nico,” Ministério da Saúde, Brasília, Brasil, 2011, http://portalsaude.saude.gov.br/portalsaude/arquivos/pdf/2012/Ago/22/vigitel_2011_final_0812.pdf.
[31]
M. L. Oliveira, Estimativa dos custos da obesidade para o sistema único de saúde do Brasil [Ph.D. thesis], UnB, Brasília, Brasil, 2013.
[32]
R. K. Dubey and E. K. Jackson, “Estrogen-induced cardiorenal protection: potential cellular, biochemical, and molecular mechanisms,” American Journal of Physiology, vol. 280, no. 3, pp. F365–F388, 2001.
[33]
J. E. Hall, “The kidney, hypertension, and obesity,” Hypertension, vol. 41, no. 3, part 2, pp. 625–633, 2003.
[34]
L. Landsberg, “Diet, obesity and hypertension: an hypothesis involving insulin, the sympathetic nervous system, and adaptive thermogenesis,” Quarterly Journal of Medicine, vol. 61, no. 236, pp. 1081–1090, 1986.
[35]
J. E. Hall, “Mechanisms of abnormal renal sodium handling in obesity hypertension,” American Journal of Hypertension, vol. 10, no. 5, part 2, pp. S49–S55, 1997.
[36]
V. Kotsis, S. Stabouli, S. Papakatsika, Z. Rizos, and G. Parati, “Mechanisms of obesity-induced hypertension,” Hypertension Research, vol. 33, no. 5, pp. 386–393, 2010.
[37]
J. E. Hall, A. A. da Silva, J. M. do Carmo et al., “Obesity-induced hypertension: role of sympathetic nervous system, leptin, and melanocortins,” Journal of Biological Chemistry, vol. 285, no. 23, pp. 17271–17276, 2010.
[38]
World Health Organization, “Obesity: preventing and managing the global epidemic,” Report of a WHO Consultation WHO Technical Report Series 894, WHO, Geneva, Switzerland, 2000.
[39]
G. Velasquez-Melendez, A. M. Pimenta, and G. Kac, “Epidemiologia do sobrepeso e da obesidade e seus fatores determinantes em Belo Horizonte (MG), Brasil: estudo transversal de base populacional,” Revista Panamericana de Salud Publica, vol. 16, no. 5, pp. 308–314, 2004.
[40]
World Health Organization, “Waist circumference and waist-hip ratio,” Report of a WHO Expert ConsultAtion, WHO, Geneva, Switzerland, 2008.
[41]
O. S. Adediran, P. B. Adebayo, and A. A. Akintunde, “Anthropometric differences among natives of Abuja living in urban and rural communities: correlations with other cardiovascular risk factors,” BMC Research Notes, vol. 6, article 123, 2013.
[42]
A. Misra, N. Vikram, R. Gupta, R. Pandey, V. Gupta, and J. Wasir, “Waist circumference cutoff points and action levels for Asian Indians for identification of abdominal obesity,” International Journal of Obesity, vol. 30, no. 1, pp. 106–111, 2006.
[43]
C. J. Dobbelsteyn, M. R. Joffres, D. R. MacLean, and G. Flowerdew, “A comparative evaluation of waist circumference, waist-to-hip ratio and body mass index as indicators of cardiovascular risk factors. The Canadian heart health surveys,” International Journal of Obesity, vol. 25, no. 5, pp. 652–661, 2001.
[44]
J. A. Gliner, N. Leech, and G. Morgan, “Problems with null hypothesis significance testing (NHST): what do the textbooks say?” Journal of Experimental Education, vol. 71, no. 1, pp. 83–92, 2002.
[45]
L. S. Erdreich and E. T. Lee, “Use of relative operating characteristic analysis in epidemiology. A method for dealing with subjective judgement,” American Journal of Epidemiology, vol. 114, no. 5, pp. 649–662, 1981.
[46]
Y.-C. Lee, W.-J. Lee, Y.-C. Lin et al., “Obesity and the decision tree: predictors of sustained weight loss after bariatric surgery,” Hepatogastroenterology, vol. 56, no. 96, pp. 1745–1749, 2009.
[47]
L. S. Barbosa, L. C. N. Scala, and M. G. Ferreira, “Associa？？o entre marcadores antropométricos de adiposidade corporal e hipertens？o arterial na popula？？o adulta de Cuiabá, Mato Grosso,” Revista Brasileira de Epidemiologia, vol. 12, no. 2, pp. 237–247, 2009.
[48]
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[49]
Global Health Organization, “Noncommunicable diseases,” 2013, http://www.who.int/gho/ncd/en/index.html.
