Title | ||
---|---|---|
Comparative study of existing personalized approaches for identifying important gene markers and for risk estimation in Type2 Diabetes in Italian population. |
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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/s12530-013-9083-8 | Evolving Systems |
Keywords | Field | DocType |
Personalized modeling, Neuro-fuzzy inference system, Type 2 diabetes, Genes related to type 2 diabetes, TWNFI | Transduction (machine learning),Population,Diabetes mellitus,Disease,Computer science,Artificial intelligence,Chronic disease,Machine learning,Inference system,Genetic marker | Journal |
Volume | Issue | ISSN |
6 | 1 | 1868-6486 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anju Verma | 1 | 19 | 2.70 |
Maurizio Fiasché | 2 | 49 | 9.23 |
Maria Cuzzola | 3 | 19 | 4.12 |
Giuseppe Irrera | 4 | 5 | 1.61 |