A Model Based Approach On Gene Expression Profiling Of Colorectal Cancer And Normal Mucosa Using Logistic Regression, Artificial Neural Network And Structural Equation Modelling

Colorectal cancer is one of the leading biomedical issues of concern. Our understanding of the disease has improved using microarray expression data analysis over last few decades. Therefore, it is of interest to design conceptual statistical models to analyze volumes of data to glean useful information. We used data from the open source Gene Expression Omnibus database containing information on160 normal mucosa tissues and 203 CRCs. The model described in this report selected 44 candidate genes exceeding 4-fold threshold expression. The reliability was determined using Cronbach’s alpha measurement for further statistical analysis. Structural Equation Modelling and binary logistic regression and neural networks were used to incur the strength of association of genes with the disease outcome.

[1]  Liang Hu,et al.  Prognostic value of carbonic anhydrase VII expression in colorectal carcinoma , 2015, BMC Cancer.

[2]  R. Elble,et al.  Loss of CLCA4 Promotes Epithelial-to-Mesenchymal Transition in Breast Cancer Cells , 2013, PloS one.

[3]  B. Liu,et al.  The Transition from Proliferation to Differentiation in Colorectal Cancer Is Regulated by the Calcium Activated Chloride Channel A1 , 2013, PloS one.

[4]  J L Pater,et al.  Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients. , 2006, European journal of cancer care.

[5]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[6]  Michael R. Mullen,et al.  Structural equation modelling: guidelines for determining model fit , 2008 .

[7]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[8]  Detmar W. Straub,et al.  Structural Equation Modeling and Regression: Guidelines for Research Practice , 2000, Commun. Assoc. Inf. Syst..

[9]  S. Mulaik,et al.  EVALUATION OF GOODNESS-OF-FIT INDICES FOR STRUCTURAL EQUATION MODELS , 1989 .

[10]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.

[11]  P. Bentler,et al.  Cutoff criteria for fit indexes in covariance structure analysis : Conventional criteria versus new alternatives , 1999 .

[12]  H. Haapasalo,et al.  Carbonic anhydrase VII–a potential prognostic marker in gliomas , 2011 .

[13]  Wen-Hsien Ho,et al.  Genetic-algorithm-based artificial neural network modeling for platelet transfusion requirements on acute myeloblastic leukemia patients , 2011, Expert Syst. Appl..

[14]  Peter M. Bentler,et al.  EQS : structural equations program manual , 1989 .

[15]  Paulo J. G. Lisboa,et al.  The Use of Artificial Neural Networks in Decision Support in Cancer: a Systematic Review , 2005 .

[16]  D. Sargent,et al.  Comparison of artificial neural networks with other statistical approaches , 2001, Cancer.