A multifactorial analysis of obesity as CVD risk factor: Use of neural network based methods in a nutrigenetics context

BackgroundObesity is a multifactorial trait, which comprises an independent risk factor for cardiovascular disease (CVD). The aim of the current work is to study the complex etiology beneath obesity and identify genetic variations and/or factors related to nutrition that contribute to its variability. To this end, a set of more than 2300 white subjects who participated in a nutrigenetics study was used. For each subject a total of 63 factors describing genetic variants related to CVD (24 in total), gender, and nutrition (38 in total), e.g. average daily intake in calories and cholesterol, were measured. Each subject was categorized according to body mass index (BMI) as normal (BMI ≤ 25) or overweight (BMI > 25). Two artificial neural network (ANN) based methods were designed and used towards the analysis of the available data. These corresponded to i) a multi-layer feed-forward ANN combined with a parameter decreasing method (PDM-ANN), and ii) a multi-layer feed-forward ANN trained by a hybrid method (GA-ANN) which combines genetic algorithms and the popular back-propagation training algorithm.ResultsPDM-ANN and GA-ANN were comparatively assessed in terms of their ability to identify the most important factors among the initial 63 variables describing genetic variations, nutrition and gender, able to classify a subject into one of the BMI related classes: normal and overweight. The methods were designed and evaluated using appropriate training and testing sets provided by 3-fold Cross Validation (3-CV) resampling. Classification accuracy, sensitivity, specificity and area under receiver operating characteristics curve were utilized to evaluate the resulted predictive ANN models. The most parsimonious set of factors was obtained by the GA-ANN method and included gender, six genetic variations and 18 nutrition-related variables. The corresponding predictive model was characterized by a mean accuracy equal of 61.46% in the 3-CV testing sets.ConclusionsThe ANN based methods revealed factors that interactively contribute to obesity trait and provided predictive models with a promising generalization ability. In general, results showed that ANNs and their hybrids can provide useful tools for the study of complex traits in the context of nutrigenetics.

[1]  Konstantina S. Nikita,et al.  An integrated web-based platform for the provision of personalized advice in people at high risk for CVD , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[2]  Satoru Miyano,et al.  Case-control study of binary disease trait considering interactions between SNPs and environmental effects using logistic regression , 2004, Proceedings. Fourth IEEE Symposium on Bioinformatics and Bioengineering.

[3]  Taizo Hanai,et al.  Artificial neural network predictive model for allergic disease using single nucleotide polymorphisms data. , 2002, Journal of bioscience and bioengineering.

[4]  T. Pearson,et al.  Nutritional interventions in cardiovascular disease: New challenges and opportunities , 2000, Current atherosclerosis reports.

[5]  Muin J. Khoury,et al.  Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes , 2010, BMC Medical Informatics Decis. Mak..

[6]  George P. McCabe,et al.  The Practice of Business Statistics , 2004 .

[7]  D. Arveiler,et al.  Polymorphisms of the tumour necrosis factor‐α gene, coronary heart disease and obesity , 1998, European journal of clinical investigation.

[8]  J. H. Moore,et al.  Multifactor-dimensionality reduction reveals high-order interactions among estrogen-metabolism genes in sporadic breast cancer. , 2001, American journal of human genetics.

[9]  Claude Bouchard,et al.  Genes, Fat Intake, and Cardiovascular Disease Risk Factors in the Quebec Family Study , 2007, Obesity.

[10]  Andrew C Heath,et al.  Genetic and Environmental Contributions to BMI in Adolescent and Young Adult Women , 2009, Obesity.

[11]  C. Dolea,et al.  World Health Organization , 1949, International Organization.

[12]  Joseph T. Glessner,et al.  From Disease Association to Risk Assessment: An Optimistic View from Genome-Wide Association Studies on Type 1 Diabetes , 2009, PLoS genetics.

[13]  Jasmina Arifovic,et al.  Using genetic algorithms to select architecture of a feedforward artificial neural network , 2001 .

[14]  Jason H. Moore,et al.  The Interaction of Four Genes in the Inflammation Pathway Significantly Predicts Prostate Cancer Risk , 2005, Cancer Epidemiology Biomarkers & Prevention.

[15]  K Clark,et al.  The effect of age on the association between body-mass index and mortality. , 1998, Journal of insurance medicine.

[16]  D Curtis,et al.  Assessing Optimal Neural Network Architecture for Identifying Disease‐associated Multi‐marker Genotypes using a Permutation Test, and Application to Calpain 10 Polymorphisms Associated with Diabetes , 2003, Annals of human genetics.

[17]  Bill C White,et al.  Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases , 2003, BMC Bioinformatics.

[18]  C. Aguilar-Salinas,et al.  Association of PPARG2 Pro12Ala Variant with Larger Body Mass Index in Mestizo and Amerindian Populations of Mexico , 2007, Human biology.

[19]  Marylyn D. Ritchie,et al.  Multilocus Analysis of Hypertension: A Hierarchical Approach , 2004, Human Heredity.

[20]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[21]  Michael R. Chernick,et al.  Introductory Biostatistics for the Health Sciences , 2003 .

[22]  Abdesslam Boutayeb,et al.  International Journal for Equity in Health the Burden of Non Communicable Diseases in Developing Countries , 2005 .

[23]  Laurent Briollais,et al.  Methodological issues in detecting gene-gene interactions in breast cancer susceptibility: a population-based study in Ontario , 2007, BMC medicine.

[24]  Spyretta Golemati,et al.  Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks. , 2007, Ultrasound in medicine & biology.

[25]  Jason H. Moore,et al.  Multifactor dimensionality reduction software for detecting gene-gene and gene-environment interactions , 2003, Bioinform..

[26]  M. Zarif Yeganeh,et al.  Nutrigenomics and Nutrigenetics , 2010, Iranian journal of public health.

[27]  H. K. Lee,et al.  Erratum to: Common genetic polymorphisms in the promoter of resistin gene are major determinants of plasma resistin concentrations in humans , 2004, Diabetologia.

[28]  B. Popkin,et al.  An overview on the nutrition transition and its health implications: the Bellagio meeting , 2002, Public Health Nutrition.

[29]  D. McGee,et al.  Body mass index and mortality: a meta-analysis based on person-level data from twenty-six observational studies. , 2005, Annals of epidemiology.

[30]  K. Lunetta,et al.  Identifying SNPs predictive of phenotype using random forests , 2005, Genetic epidemiology.

[31]  Wei J Chen,et al.  Genetic and Environmental Influences on Adiponectin, Leptin, and BMI Among Adolescents in Taiwan: A Multivariate Twin/Sibling Analysis , 2008, Twin Research and Human Genetics.

[32]  Konstantina S. Nikita,et al.  Analysis of postprandial lipemia as a Cardiovascular Disease risk factor using genetic and clinical information: An Artificial Neural Network perspective , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[33]  F. Rasmussen,et al.  Physical activity, diet and gene–environment interactions in relation to body mass index and waist circumference: The Swedish Young Male Twins Study , 2006, Public Health Nutrition.

[34]  Bootstrap Methods and Permutation Tests * , 2022 .

[35]  Hiroyuki Honda,et al.  Artificial neural network approach for selection of susceptible single nucleotide polymorphisms and construction of prediction model on childhood allergic asthma , 2004, BMC Bioinformatics.

[36]  Rosalynn D Gill,et al.  Improved weight management using genetic information to personalize a calorie controlled diet , 2007, Nutrition journal.

[37]  A. Danchin,et al.  Organised Genome Dynamics in the Escherichia coli Species Results in Highly Diverse Adaptive Paths , 2009, PLoS genetics.

[38]  J. H. Moore,et al.  Multifactor-dimensionality reduction shows a two-locus interaction associated with Type 2 diabetes mellitus , 2004, Diabetologia.

[39]  Ralph B D'Agostino,et al.  Overweight and obesity as determinants of cardiovascular risk: the Framingham experience. , 2002, Archives of internal medicine.

[40]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[41]  J. Stengård,et al.  Genes, Environment, and Cardiovascular Disease , 2003, Arteriosclerosis, thrombosis, and vascular biology.

[42]  Amy K Ferketich.  Introductory Biostatistics for the Health Sciences , 2004 .

[43]  H. Delisle,et al.  Obesity and cardio-metabolic risk factors in urban adults of Benin: Relationship with socio-economic status, urbanisation, and lifestyle patterns , 2008, BMC public health.

[44]  E. Rimm,et al.  Commentary: Obesity and cardiovascular disease risk among the young and old--is BMI the wrong benchmark? , 2006, International journal of epidemiology.

[45]  Jon Wakefield,et al.  Bayesian mixture modeling of gene‐environment and gene‐gene interactions , 2009, Genetic epidemiology.

[46]  A. G. Heidema,et al.  The challenge for genetic epidemiologists: how to analyze large numbers of SNPs in relation to complex diseases , 2006, BMC Genetics.

[47]  Konstantina S. Nikita,et al.  SCAPEVIEWER: preliminary results of a landscape perception classification system based on neural network technology , 2005 .

[48]  Marylyn D. Ritchie,et al.  GPNN: Power studies and applications of a neural network method for detecting gene-gene interactions in studies of human disease , 2006, BMC Bioinformatics.