Abstract
Chronic diseases, a major health problem throughout the world, are increasing and have very high prevalence. The current project suggests a method that can be used to predict the personalized risk of chronic disease such as type 2 diabetes and inform lifestyle recommendations based on clinical, nutritional and genetic variables. The main aim is to discover new knowledge and build a personalized risk prediction model using existing methods which can be used for disease prognosis and the improvement of human lifestyle and health. Clinical and genetic data has been used to build personalized model for Italian people living in Italy. Many different methods have been used to select few genes from 87 genes. TWNFI (Transductive neuro-fuzzy inference system) developed by Prof. Nikola Kasabov and Dr Qun Song (Song and Kasabov 2006) has been used to build personalized model and has been compared with other methods. It has been found that TWNFI not only gives highest accuracy, also gives weights of variables as per their importance for risk of disease and sets of rules which can be used for better prediction and recommendation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al-Lawati JA, Tuomilehto J (2007) Diabetes risk score in Oman: a tool to identify prevalent type 2 diabetes among Arabs of the Middle East. Diabetes Res Clin Pract 77:438–444
Brown JB, Palmer AJ, Bisgaard P, Chan W, Pedula K, Russell A (2000a) The Mt. hood challenge: cross-testing two diabetes simulation models. Diabetes Res Clin Pract 50(3):S57–S64
Brown JB, Russell A, Chan W, Pedula K, Aickin M (2000b) The global diabetes model: user friendly version 3.0. Diabetes Res Clin Pract 50(3):S15–S46
Cornelis M, Qi L, Zhang C, Kraft P, Manson JA, Cai T et al (2009) Joint effects of common genetic variants on the risk of type-2 diabetes in US. men and women of European ancestry. Ann Intern Med 150:541–550
Crodder G and Grossberg S (1990) Predicting the Mackey-Glass time series with cascade-correlation learning: 1990 Connectionist models summer school, Carnegie Mellon University
Cuzzola M, Fiasché M, Iacopino P, Messina G, Martino M, Console G, Fedele R, Massi D, Recchia AG, Irrera G, Morabito F (2012) A molecular and computational diagnostic approach identifies FOXP3, ICOS, CD52 and CASP1 as the most informative biomarkers in acute graft-versus-host disease. Haematologica 97(10):1532–1538
Eddy DM, Schlessinger L (2003a) Archimedes. A trial-validated model of diabetes. Diabetes Care 26(11):3093–3101
Eddy DM, Schlessinger L (2003b) Validation of the Archimedes diabetes model. Diabetes Care 26(11):3102–3110
Farmer JD, Sidorowitch JJ (1987) Predicting chaotic time series. Phys Rev Lett 59(7):845–848
Fiasché M, Cuzzola M, Irrera G, Iacopino P, Morabito FC (2011a) Advances in medical decision support systems for diagnosis of acute graft-versus-host disease: molecular and computational intelligence joint approaches. Frontiers Biol China 6(4):263–273. doi:10.1007/s11515-011-1124-8
Fiasché, M., Verma, A., Cuzzola, M., Morabito, F.C. And Irrera, G. (2011). Incremental—adaptive—knowledge based—learning for informative rules extraction in classification analysis of aGvHD. IFIP Advances in Information and Communication Technology, vol 363. AICT, Issue PART 1, pp. 361–371. DOI: 10.1007/978-3-642-23957-1_41
Goh L (2005) Computational methods for microarray gene expression analysis through integration and knowledge discovery. PhD thesis. Auckland University of Technology
Herman WH (2003) Diabetes Modelling. Diabetes Care 26(11):3182
Kasabov N. (2007) Evolving connectionist systems: The knowledge engineering approach 2nd edn. Springer, London
Kasabov N (2007b) Global, local and personalized modeling and profile discovery in bioinformatics: An integrated approach. Pattern Recognit Lett 28(6):673–685
Kasabov N (2008) Adaptive modeling and discovery in Bioinformatics: the evolving connectionist approach. Int J Intell Syst 23:545–555
Kasabov N, Song Q, Benuskova L, Gottgtroy P, Jain V, Verma A, Havukkala I, Rush E, Pears R, Tjahjana A, Hu R, MacDonell S (2008) Integrating local and personalized modeling with global ontology knowledge bases for biomedical and bioinformatics decision support, chapter In: Smolin et al (eds) computational intelligence in bioinformatics, Springer
King H, Rewers M (1993) Global estimates for prevalence of diabetes mellitus and impaired glucose tolerance in adults. WHO Ad Hoc diabetes reporting group. Diabetes Care 16(1):157–177
King H, Aubert RE, Herman WH (1998) Global burden of diabetes, 1995–2025. Diabetes Care 21(9):1414–1431
Lindstrom J, Tuomilehto J (2003) The diabetes risk score. A practical tool to predict type 2 diabetes risk. Diabetes Care 26(3):725–731
Mitchell MT, Keller R et al (1997) Explanation-based generalization: a unified view. Machine Learning 1(1):47–80
Schmittgen KJ, Livak TD (2001) Analysis of relative gene expression data using real-time quantitative PCR and the 2-[Delta][Delta]CT method. Methods 25(4):402–408
Schulze MB, Hoffmann K, Boeing H, Linseisen J, Rohrmann S, Mohlig M et al (2007) An accurate risk score based on anthropometric, dietary, and lifestyle factors to predict the development of type 2 diabetes. Diabetes Care 30(3):510–515
Song Q, Kasabov N (2006) TWNFI—a transductive neuro-fuzzy inference system with weighted data normalization for personalized modeling. Neural Netw 19(10):1591–1596
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Sys Man Cybern 15:116–132
The FIELD Study Investigators (2004) The need for a large-scale trial of fibrate therapy in diabetes: the rationale and design of the Fenofibrate Intervention and Event Lowering in Diabetes (FIELD) study. ISRCTN64783481. Cardiovasc Diabete 2004(3):9
Vapnik V (1998) Statistical Learning Theory: Wiley-InterScience, New York
Verma A, Fiasché M, Cuzzola M, Iacopino P, Morabito FC, Kasabov N (2009) Ontology based personalized modeling for type 2 diabetes risk analysis: An integrated approach. LNCS 5864(2):360–366. doi:10.1007/978-3-642-10684-2_40
Wild S, Roglic G, Green A, Sicree R, King H (2000) Global prevalence of diabetes. Estimates for the year 2000 and projections for 2030. Diabetes Care 27(5):1047–1053
Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353
Zadeh LA (1988) Fuzzy logic. IEEE Comput 21:83–93
Zimmet P, Alberti KGMM, Shaw J (2001) Global and societal implications of the diabetes epidemic. Nature 414:782–787
Acknowledgments
This study has been supported by Foundation of Research and Technology by TIF scholarship through an affiliate of Pacific Channel Limited and Knowledge Engineering and Discovery Research Institute, AUT. We would like to thank Prof. Nikola Kasabov for his continuous support and guidance throughout the project and ADSPEM and AVIS (Reggio Calabria) for the Recruitment of healthy donors.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Verma, A., Fiasché, M., Cuzzola, M. et al. Comparative study of existing personalized approaches for identifying important gene markers and for risk estimation in Type2 Diabetes in Italian population. Evolving Systems 6, 15–22 (2015). https://doi.org/10.1007/s12530-013-9083-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-013-9083-8