Nazli Ucunoglu1, Arinze Akutekwe2, Turgay Isbir3
1. Department of Molecular Medicine, Institute of Health Sciences, Yeditepe University, Kayısdag, 34755, Istanbul, Turkey.
2. Bio-Health Informatics Research Group, Faculty of Technology, De Montfort University, LE1 9BH, Leicester,UK.
3. Department of Medical Biology, Faculty of Medicine, Yeditepe University, Kayısdag, 34755, Istanbul, Turkey.
Abstract: Hypertension is a chronic medical condition that the blood pressure in the arteries is elevated. Hypertension can lead to damaged organs, as well as several illnesses, such as renal failure (kidney failure), aneurysm, heart failure, stroke, or heart attack. In our investigation, ten subsets were designed for male hypertension patient and control group. In this paper we apply t-test and entropy feature selection methods using 2fold and 5fold cross validation as our model selection methods with K-Nearest neighbour classifier. Among these groups, 3 number of biomarkers set were chosen (1,3,9) for 4 tables (t-test; 2-fold and 5-fold; entropy; 2-fold and 5-fold). From these biomarker sets which has the highest accuracy which is the measurement used for the classifier assessment was analysed and taken to the best models for each sub-set table. Each sub-set tables were analysed with each other and we tried to find the most appropriate biomarker. The defined biomarker was searched within database in order to find relationship with the illness. Consequently, highly recurrent and highly accurate candidate genes can be further analysed for becoming a biomarker. Further analysis (both database and wet study) can be suggested for the highly recurrent genes like Hs. 683236 (null), Hs. 475902, 420541, 656129, 647705 and 657792.
Keywords: Hypertension, t-test, entropy, K-Nearest neighbour classifier, biomarker.
Pages: 28 – 34 | Full PDF Paper