Download PDF
Exp Clin Endocrinol Diabetes 2016; 124(01): 34-38
DOI: 10.1055/s-0035-1565175
Article
© Georg Thieme Verlag KG Stuttgart · New York

Multiple Linear Regression and Artificial Neural Network to Predict Blood Glucose in Overweight Patients

J. Wang   *
1   Department of Infection and Liver Diseases, Liver Research Center, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
,
F. Wang   *
2   Beijing Hui-Long-Guan Hospital, Peking University, Beijing, China
,
Y. Liu   *
3   Wenzhou Medical University, Wenzhou, China
,
J. Xu
4   The Affiliated Wenling Hospital of Wenzhou Medial University, Wenling, China
,
H. Lin
3   Wenzhou Medical University, Wenzhou, China
,
B. Jia
5   Inner Mongolia Medical University, Hohhot, China
,
W. Zuo
6   Ningbo Fourth Hospital, Xiangshan, China
,
Y. Jiang
6   Ningbo Fourth Hospital, Xiangshan, China
,
L. Hu
8   Department of Pharmacy, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
,
F. Lin
7   Laboratory of Internal Medicine, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang Province, China
› Author Affiliations
Further Information

Publication History

received 03 June 2015
first decision 26 October 2015

accepted 28 October 2015

Publication Date:
21 January 2016 (online)

Also available at
    Permissions and Reprints

Abstract

Background: Overweight individuals are at higher risk for developing type II diabetes than the general population. We conducted this study to analyze the correlation between blood glucose and biochemical parameters, and developed a blood glucose prediction model tailored to overweight patients.

Methods: A total of 346 overweight Chinese people patients ages 18–81 years were involved in this study. Their levels of fasting glucose (fs-GLU), blood lipids, and hepatic and renal functions were measured and analyzed by multiple linear regression (MLR). Based the MLR results, we developed a back propagation artificial neural network (BP-ANN) model by selecting tansig as the transfer function of the hidden layers nodes, and purelin for the output layer nodes, with training goal of 0.5×10−5.

Results: There was significant correlation between fs-GLU with age, BMI, and blood biochemical indexes (P<0.05). The results of MLR analysis indicated that age, fasting alanine transaminase (fs-ALT), blood urea nitrogen (fs-BUN), total protein (fs-TP), uric acid (fs-BUN), and BMI are 6 independent variables related to fs-GLU. Based on these parameters, the BP-ANN model was performed well and reached high prediction accuracy when training 1 000 epoch (R=0.9987).

Conclusions: The level of fs-GLU was predictable using the proposed BP-ANN model based on 6 related parameters (age, fs-ALT, fs-BUN, fs-TP, fs-UA and BMI) in overweight patients.

Key words

glucose - overweight - regression - BP-ANN

* Jiajia Wang, Fan Wang and Yanlong Liu made equal contribution.


 

  • References

  • 1 Manyanga T, El-Sayed H, Doku DT et al. The prevalence of underweight, overweight, obesity and associated risk factors among school-going adolescents in seven African countries. BMC public health 2014; 14: 887
    CrossrefPubMedSearch in Google Scholar
  • 2 Seo DC, Niu J. Trends in underweight and overweight/obesity prevalence in Chinese youth, 2004–2009. International journal of behavioral medicine 2014; 21: 682-690
    CrossrefPubMedSearch in Google Scholar
  • 3 Yan WL, Li XS, Wang Q et al. Overweight, high blood pressure and impaired fasting glucose in Uyghur, Han, and Kazakh Chinese children and adolescents. Ethnicity & health 2014; 1-11
    PubMedSearch in Google Scholar
  • 4 Vikoren LA, Nygard OK, Lied E et al. A randomised study on the effects of fish protein supplement on glucose tolerance, lipids and body composition in overweight adults. The British journal of nutrition 2013; 109: 648-657
    CrossrefPubMedSearch in Google Scholar
  • 5 Almoosawi S, Tsang C, Ostertag LM et al. Differential effect of polyphenol-rich dark chocolate on biomarkers of glucose metabolism and cardiovascular risk factors in healthy, overweight and obese subjects: a randomized clinical trial. Food & function 2012; 3: 1035-1043
    CrossrefPubMedSearch in Google Scholar
  • 6 Pannacciulli N, De Mitrio V, Marino R et al. Effect of glucose tolerance status on PAI-1 plasma levels in overweight and obese subjects. Obesity research
    PubMed
  • 7 Xiao C, Giacca A, Carpentier A et al. Differential effects of monounsaturated, polyunsaturated and saturated fat ingestion on glucose-stimulated insulin secretion, sensitivity and clearance in overweight and obese, non-diabetic humans. Diabetologia 2006; 49: 1371-1379
    CrossrefPubMedSearch in Google Scholar
  • 8 Flint A, Gregersen NT, Gluud LL et al. Associations between postprandial insulin and blood glucose responses, appetite sensations and energy intake in normal weight and overweight individuals: a meta-analysis of test meal studies. The British journal of nutrition 2007; 98: 17-25
    CrossrefPubMedSearch in Google Scholar
  • 9 Batty GD, Kivimaki M, Smith GD et al. Obesity and overweight in relation to mortality in men with and without type 2 diabetes/impaired glucose tolerance: the original Whitehall Study. Diabetes care 2007; 30: 2388-2391
    CrossrefPubMedSearch in Google Scholar
  • 10 Holst-Schumacher I, Nunez-Rivas H, Monge-Rojas R et al. Insulin resistance and impaired glucose tolerance in overweight and obese Costa Rican schoolchildren. Food and nutrition bulletin 2008; 29: 123-131
    CrossrefPubMedSearch in Google Scholar
  • 11 Kuk JL, Kilpatrick K, Davidson LE et al. Whole-body skeletal muscle mass is not related to glucose tolerance or insulin sensitivity in overweight and obese men and women. Applied physiology, nutrition, and metabolism=Physiologie appliquee, nutrition et metabolisme 2008; 33: 769-774
    PubMedSearch in Google Scholar
  • 12 Chung HK, Chae JS, Hyun YJ et al. Influence of adiponectin gene polymorphisms on adiponectin level and insulin resistance index in response to dietary intervention in overweight-obese patients with impaired fasting glucose or newly diagnosed type 2 diabetes. Diabetes care 2009; 32: 552-558
    CrossrefPubMedSearch in Google Scholar
  • 13 Jones LM, Meredith-Jones K, Legge M. The effect of water-based exercise on glucose and insulin response in overweight women: a pilot study. Journal of women’s health 2009; 18: 1653-1659
    CrossrefPubMedSearch in Google Scholar
  • 14 Sharma M, Gupta U, Padam A et al. Glucose tolerance in overweight and obese North Indian adolescents. Indian journal of pediatrics 2011; 78: 1407-1409
    CrossrefPubMedSearch in Google Scholar
  • 15 Power C, Thomas C. Changes in BMI, duration of overweight and obesity, and glucose metabolism: 45 years of follow-up of a birth cohort. Diabetes care 2011; 34: 1986-1991
    CrossrefPubMedSearch in Google Scholar
  • 16 Velasquez-Mieyer PA, Cowan PA, Neira CP et al. Assessing the risk of impaired glucose metabolism in overweight adolescents in a clinical setting. The journal of nutrition, health & aging 2008; 12: 750S-757S
    PubMedSearch in Google Scholar
  • 17 Nur MM, Newman IM, Siqueira LM. Glucose metabolism in overweight Hispanic adolescents with and without polycystic ovary syndrome. Pediatrics 2009; 124: e496-e502
    CrossrefPubMedSearch in Google Scholar
  • 18 Hartman ML, Goodson JM, Barake R et al. Salivary glucose concentration exhibits threshold kinetics in normal-weight, overweight, and obese children. Diabetes, metabolic syndrome and obesity: targets and therapy 2015; 8: 9-15
    PubMedSearch in Google Scholar
  • 19 Shi P, Yang W, Yu Q et al. Overweight, gestational weight gain and elevated fasting plasma glucose and their association with macrosomia in chinese pregnant women. Maternal and child health journal 2014; 18: 10-15
    CrossrefPubMedSearch in Google Scholar
  • 20 Jiang S, Fang Q, Yu W et al. Genetic variations in APPL2 are associated with overweight and obesity in a Chinese population with normal glucose tolerance. BMC medical genetics 2012; 13: 22
    PubMedSearch in Google Scholar
  • 21 Zhang Y, Yang J, Zheng M et al. Clinical characteristics and predictive factors of subclinical diabetic nephropathy. Experimental and clinical endocrinology & diabetes: official journal, German Society of Endocrinology [and] German Diabetes Association 2015; 123: 132-138
    PubMedSearch in Google Scholar
  • 22 Ma J, Cai J, Lin G et al. Development of LC-MS determination method and back-propagation ANN pharmacokinetic model of corynoxeine in rat. Journal of chromatography B, Analytical technologies in the biomedical and life sciences 2014; 959: 10-15
    PubMedSearch in Google Scholar
  • 23 Xu JF, Xu J, Li SZ et al. Transmission risks of schistosomiasis japonica: extraction from back-propagation artificial neural network and logistic regression model. PLoS neglected tropical diseases 2013; 7: e2123
    CrossrefPubMedSearch in Google Scholar
  • 24 Yamaguchi M, Kaseda C, Yamazaki K et al. Prediction of blood glucose level of type 1 diabetics using response surface methodology and data mining. Medical & biological engineering & computing 2006; 44: 451-457
    CrossrefPubMedSearch in Google Scholar
  • 25 Zecchin C, Facchinetti A, Sparacino G et al. Jump neural network for online short-time prediction of blood glucose from continuous monitoring sensors and meal information. Computer methods and programs in biomedicine 2014; 113: 144-152
    CrossrefPubMedSearch in Google Scholar
  • 26 Katayama T, Sato T, Minato K. A blood glucose prediction system by chaos approach. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Annual Conference 2004; 1: 750-753
    PubMedSearch in Google Scholar
  • 27 Pivetta T, Isaia F, Trudu F et al. Development and validation of a general approach to predict and quantify the synergism of anti-cancer drugs using experimental design and artificial neural networks. Talanta 2013; 115: 84-93
    CrossrefPubMedSearch in Google Scholar
  • 28 Larde B, Wang DC, Revell A et al. The development of artificial neural networks to predict virological response to combination HIV therapy. Antivir Ther 2007; 12: 15-24
    PubMedSearch in Google Scholar
  • 29 Qaderi A, Dadgar N, Mansouri H et al. Modeling and prediction of cytotoxicity of artemisinin for treatment of the breast cancer by using artificial neural networks. SpringerPlus 2013; 2: 340
    CrossrefPubMedSearch in Google Scholar
  • 30 Wesolowski M, Suchacz B, Konieczynski P. The application of artificial neural networks for the selection of key thermoanalytical parameters in medicinal plants analysis. Combinatorial chemistry & high throughput screening 2003; 6: 811-820
    CrossrefPubMedSearch in Google Scholar
  • 31 Wang X, Wang S, Lin F et al. Pharmacokinetics and tissue distribution model of cabozantinib in rat determined by UPLC-MS/MS. Journal of chromatography B, Analytical technologies in the biomedical and life sciences 2015; 983-984C: 125-131
    PubMedSearch in Google Scholar
  • 32 Trost SG, Zheng YL, Pfeiffer KA et al. Artificial neural networks to predict physical activity type and energy expenditure in children and adolescents. Med Sci Sport Exer 2012; 44: 216-217
    PubMedSearch in Google Scholar
  • 33 Laverdy OG, Hueb WA, Sprandel MC et al. Effects of glycemic control upon serum lipids and lipid transfers to HDL in patients with type 2 diabetes mellitus: novel findings in unesterified cholesterol status. Experimental and clinical endocrinology & diabetes: official journal, German Society of Endocrinology [and] German Diabetes Association 2015; 123: 232-239
    PubMedSearch in Google Scholar
  • 34 Preciado-Puga MC, Malacara JM, Fajardo-Araujo ME et al. Markers of the progression of complications in patients with type 2 diabetes: a one-year longitudinal study. Experimental and clinical endocrinology & diabetes: official journal, German Society of Endocrinology [and] German Diabetes Association 2014; 122: 484-490
    PubMedSearch in Google Scholar