Prediction model of artificial neural network for the risk of hyperuricemia incorporating dietary risk factors in a Chinese adult study

  • Jie Zeng
  • Junguo Zhang
  • Ziyi Li
  • Tianwang Li
  • Guowei Li
Keywords: hyperuricemia; dietary factors; artificial neural network; prediction model

Abstract

Background: Risk of hyperuricemia (HU) has been shown to be strongly associated with dietary factors. However, there is scarce evidence on prediction models incorporating dietary factors to estimate the risk of HU.

Objective: The aim of this study was to develop a prediction model to predict the risk of HU in Chinese adults based on dietary information.

Design: Our study was based on a cross-sectional survey, which recruited 1,488 community residents aged 18 to 60 years in Beijing from October 2010 to January 2011. The eligible participants were randomly divided into a training set (n1 = 992) and a validation set (n2 = 496) in the ratio of 2:1. We developed the prediction model in three stages. We first used a logistic regression model (LRM) based on the training set to select a set of dietary risk factors which were related to the risk of HU. Artificial neural network (ANN) was then used to construct the prediction model using the training set. Finally, we used receiver operating characteristic (ROC) curve analysis to assess the accuracy of the prediction model using training and validation sets.

Results: In the training set, the mean age of participants with and without HU was 39.3 (standard deviation [SD]: 9.65) and 38.2 (SD: 9.38) years, respectively. Patients with HU consisted of 101 males (77.7%) and 29 females (22.3%). The LRM found that food frequency (vegetables [odds ratio (OR) = 0.73], meat [0.72], eggs [0.80], plant oil [0.78], tea [0.51], eating habits (breakfast [OR = 1.28]), and the salty cooking style (OR = 1.33) were associated with risk of HU. In the ANN analysis, we selected a three-layer back propagation neural network (BPNN) model with 14, 3, and 1 neuron in the input, hidden, and output layers, respectively, as the best prediction model. The areas under the ROC of the training and validation sets were 0.827 and 0.814, respectively. HU would occur when the incidence probability is greater than 0.128. The indicators of accuracy, sensitivity, specificity, and Yuden Index suggested that the ANN model in our study is successful and valuable.

Conclusions: This study suggests that the ANN model could be used to predict the risk of HU in Chinese adults. Further prospective studies are needed to improve the accuracy and to generalize the use of model.

Downloads

Download data is not yet available.

References


  1. Liu L, Lou S, Xu K, Meng Z, Zhang Q, Song K. Relationship between lifestyle choices and hyperuricemia in Chinese men and women. Clin Rheumatol 2013; 32: 233–9. doi: 10.1007/s10067-012-2108-z

  2. Liu H, Zhang XM, Wang YL, Liu BC. Prevalence of hyperuricemia among Chinese adults: a national cross-sectional survey using multistage, stratified sampling. J Nephrol 2014; 27: 653–8. doi: 10.1007/s40620-014-0082-z

  3. Uaratanawong S, Suraamornkul S, Angkeaw S, Uaratanawong R. Prevalence of hyperuricemia in Bangkok population. Clin Rheumatol 2011; 30: 887–93. doi: 10.1007/s10067-011-1699-0

  4. Trifiro G, Morabito P, Cavagna L, Ferrajolo C, Pecchioli S, Simonetti M, et al. Epidemiology of gout and hyperuricaemia in Italy during the years 2005–2009: a nationwide population-based study. Ann Rheum Dis 2013; 72: 694–700. doi: 10.1136/annrheumdis-2011-201254

  5. Chen S, Guo X, Dong S, Yu S, Chen Y, Zhang N, et al. Association between the hypertriglyceridemic waist phenotype and hyperuricemia: a cross-sectional study. Clin Rheumatol 2017; 36: 1111–19. doi: 10.1007/s10067-017-3559-z

  6. Wang J, Qin T, Chen J, Li Y, Wang L, Huang H, et al. Hyperuricemia and risk of incident hypertension: a systematic review and meta-analysis of observational studies. PLoS One 2014; 9: e114259. doi: 10.1371/journal.pone.0114259

  7. Liu R, Han C, Wu D, Xia X, Gu J, Guan H, et al. Prevalence of hyperuricemia and gout in mainland China from 2000 to 2014: a systematic review and meta-analysis. BioMed Res Int 2015; 2015: 762820. doi: 10.1155/2015/762820

  8. Liu X, Huang S, Xu W, Zhou A, Li H, Zhang R, et al. Association of dietary patterns and hyperuricemia: a cross-sectional study of the Yi ethnic group in China. Food Nutr Res 2018; 62. doi: 10.29219/fnr.v62.1380

  9. Gao X, Qi L, Qiao N, Choi HK, Curhan G, Tucker KL, et al. Intake of added sugar and sugar-sweetened drink and serum uric acid concentration in US men and women. Hypertension 2007; 50: 306–12. doi: 10.1161/HYPERTENSIONAHA.107.091041

  10. Zhang M, Chang H, Gao Y, Wang X, Xu W, Liu D, et al. Major dietary patterns and risk of asymptomatic hyperuricemia in Chinese adults. J Nutr Sci Vitaminol 2012; 58: 339–45. doi: 10.3177/jnsv.58.339

  11. Tsai YT, Liu JP, Tu YK, Lee MS, Chen PR, Hsu HC, et al. Relationship between dietary patterns and serum uric acid concentrations among ethnic Chinese adults in Taiwan. Asia Pac J Clin Nutr 2012; 21: 263–70. PMID: 22507614.

  12. Yu KH, See LC, Huang YC, Yang CH, Sun JH. Dietary factors associated with hyperuricemia in adults. Semin Arthritis Rheum 2008; 37: 243–50. doi: 10.1016/j.semarthrit.2007.04.007

  13. Eller-Vainicher C, Zhukouskaya VV, Tolkachev YV, Koritko SS, Cairoli E, Grossi E, et al. Low bone mineral density and its predictors in type 1 diabetic patients evaluated by the classic statistics and artificial neural network analysis. Diabetes Care 2011; 34: 2186–91. doi: 10.2337/dc11-0764

  14. Disse E, Ledoux S, Betry C, Caussy C, Maitrepierre C, Coupaye M, et al. An artificial neural network to predict resting energy expenditure in obesity. Clin Nutr 2018; 37: 1661–9. doi: 10.1016/j.clnu.2017.07.017

  15. Shaabanpour Aghamaleki F, Mollashahi B, Nosrati M, Moradi A, Sheikhpour M, Movafagh A. Application of an artificial neural network in the diagnosis of chronic lymphocytic leukemia. Cureus 2019; 11: e4004. doi: 10.7759/cureus.4004

  16. Wang SS, Lay S, Yu HN, Shen SR. Dietary guidelines for Chinese residents (2016): comments and comparisons. J Zhejiang Univ Sci B 2016; 17: 649–56. doi: 10.1631/jzus.B1600341

  17. Hearty AP, Gibney MJ. Analysis of meal patterns with the use of supervised data mining techniques – artificial neural networks and decision trees. Am J Clin Nutr 2008; 88: 1632–42. doi: 10.3945/ajcn.2008.26619

  18. Gupta H, Gupta PK, Fang X, Miller WJ, Cemaj S, Forse RA, et al. Development and validation of a risk calculator predicting postoperative respiratory failure. Chest 2011; 140: 1207–15. doi: 10.1378/chest.11-0466

  19. Miles J SM. Appling regression and correlation: a guide for students. London: Sage; 2001.

  20. Mukamal KJ, Ding EL, Djousse L. Alcohol consumption, physical activity, and chronic disease risk factors: a population-based cross-sectional survey. BMC Public Health 2006; 6: 118. doi: 10.1186/1471-2458-6-118

  21. Montie JE, Wei JT. Artificial neural networks for prostate carcinoma risk assessment. An overview. Cancer 2001; 91: 1647–52. doi: 10.1002/1097-0142

  22. Grossi E. How artificial intelligence tools can be used to assess individual patient risk in cardiovascular disease: problems with the current methods. BMC Cardiovasc Disord 2006; 6: 20. doi: 10.1186/1471-2261-6-20

  23. Florkowski CM. Sensitivity, specificity, receiver-operating characteristic (ROC) curves and likelihood ratios: communicating the performance of diagnostic tests. Clin Biochem Rev 2008; 29(Suppl 1): S83–S87. PMCID: PMC2556590.

  24. Defernez M, Kemsley EK. Avoiding overfitting in the analysis of high-dimensional data with artificial neural networks (ANNs). Analyst 1999; 124: 1675–81. doi: 10.1039/a905556h

  25. Jahandideh S, Abdolmaleki P, Movahedi MM. Comparing performances of logistic regression and neural networks for predicting melatonin excretion patterns in the rat exposed to ELF magnetic fields. Bioelectromagnetics 2010; 31: 164–71. doi: 10.1002/bem.20541

  26. Yu JW, Yang TG, Diao WX, Cai XQ, Li T, Zhong H, et al. Epidemiological study on hyperuricemia and gout in Foshan areas, Guangdong province. Zhonghua Liu Xing Bing Xue Za Zhi 2010; 31: 860–2. PMID: 21162982.

  27. Pham NM, Yoshida D, Morita M, Yin G, Toyomura K, Ohnaka K, et al. The relation of coffee consumption to serum uric acid in Japanese men and women aged 49–76 years. J Nutr Metab 2010; 2010. doi: 10.1155/2010/930757

  28. Donmez C, Konac E. Might E-cadherin promoter polymorphisms of rs16260 and rs5030625 associate with the risk of nephrolithiasis? Springerplus 2016; 5: 1673. doi: 10.1186/s40064-016-3363-2

  29. Beydoun MA, Canas JA, Fanelli-Kuczmarski MT, Tajuddin SM, Evans MK, Zonderman AB. Genetic risk scores, sex and dietary factors interact to alter serum uric acid trajectory among African-American urban adults. Br J Nutr 2017; 117: 686–97. doi: 10.1017/S0007114517000411

  30. Li R, Yu K, Li C. Dietary factors and risk of gout and hyperuricemia: a meta-analysis and systematic review. Asia Pacific J Clin Nutr 2018; 27: 1344–56. doi: 10.6133/apjcn.201811_27(6).0022

  31. Xia Y, Xiang Q, Gu Y, Jia S, Zhang Q, Liu L, et al. A dietary pattern rich in animal organ, seafood and processed meat products is associated with newly diagnosed hyperuricaemia in Chinese adults: a propensity score-matched case-control study. Br J Nutr 2018; 119: 1177–84. doi: 10.1017/S0007114518000867

  32. Zhang Y, Liu Y, Qiu H. Association between dietary zinc intake and hyperuricemia among adults in the United States. Nutrients 2018; 10: 568. doi: 10.3390/nu10050568

  33. He FJ, Burnier M, Macgregor GA. Nutrition in cardiovascular disease: salt in hypertension and heart failure. Eur Heart J 2011; 32: 3073–80. doi: 10.1093/eurheartj/ehr194

  34. Liu CW, Chang WC, Lee CC, Chen KH, Wu YW, Hwang JJ. Hyperuricemia is associated with a higher prevalence of metabolic syndrome in military individuals. Mil Med 2018; 183: e391–95. doi: 10.1093/milmed/usy097

  35. Kou Y, Li Y, Ma H, Li W, Li R, Dang Z. Uric acid lowering effect of Tibetan medicine RuPeng15 powder in animal models of hyperuricemia. J Tradit Chin Med 2016; 36: 205–10. doi: 10.1016/s0254-6272(16)30028-0

  36. Zhang Y, Jin L, Liu J, Wang W, Yu H, Li J, et al. Effect and mechanism of dioscin from Dioscorea spongiosa on uric acid excretion in animal model of hyperuricemia. J Ethnopharmacol 2018; 214: 29–36. doi: 10.1016/j.jep.2017.12.004

  37. Deshmukh-Taskar PR, Nicklas TA, O'Neil CE, Keast DR, Radcliffe JD, Cho S. The relationship of breakfast skipping and type of breakfast consumption with nutrient intake and weight status in children and adolescents: the National Health and Nutrition Examination Survey 1999–2006. J Am Diet Assoc 2010; 110: 869–78. doi: 10.1016/j.jada.2010.03.023

  38. El-Zayadi AR, Selim O, Hamdy H, El-Tawil A, Moustafa H. Heavy cigarette smoking induces hypoxic polycythemia (erythrocytosis) and hyperuricemia in chronic hepatitis C patients with reversal of clinical symptoms and laboratory parameters with therapeutic phlebotomy. Am J Gastroenterol 2002; 97: 1264–65. doi: 10.1111/j.1572-0241.2002.05718.x

  39. Vaya A, Rivera L, Hernandez-Mijares A, Bautista D, Sola E, Romagnoli M, et al. Association of metabolic syndrome and its components with hyperuricemia in a Mediterranean population. Clin Hemorheol Microcirc 2015; 60: 327–34. doi: 10.3233/CH-141887

  40. Harrison RF, Kennedy RL. Artificial neural network models for prediction of acute coronary syndromes using clinical data from the time of presentation. Ann Emerg Med 2005; 46: 431–39. doi: 10.1016/j.annemergmed.2004.09.012

  41. Ozsen S, Kara S, Latifoglu F, Gunes S. A new supervised classification algorithm in artificial immune systems with its application to carotid artery Doppler signals to diagnose atherosclerosis. Comput Methods Programs Biomed 2007; 88: 246–55. doi: 10.1016/j.cmpb.2007.09.002

  42. Shahar D, Shai I, Vardi H, Brener-Azrad A, Fraser D. Development of a semi-quantitative food frequency questionnaire (FFQ) to assess dietary intake of multiethnic populations. Eur J Epidemiol 2003; 18: 855–61. doi: 10.1023/a:1025634020718

Published
2020-01-20
How to Cite
1.
Zeng J, Zhang J, Li Z, Li T, Li G. Prediction model of artificial neural network for the risk of hyperuricemia incorporating dietary risk factors in a Chinese adult study. fnr [Internet]. 2020Jan.20 [cited 2020Jun.4];64. Available from: https://foodandnutritionresearch.net/index.php/fnr/article/view/3712
Section
Original Articles