The week's pick
Reseach Article
Effective Values of Physical Features for Type-2 Diabetic and Non-diabetic Patients Classifying Case Study: Shiraz University of Medical Sciences
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 9 - Number 7 |
| Year of Publication: 2015 |
| Authors: S. Vahid Farrahi, Mohammad Mehdi Masoumi, Marzieh Ahmadzadeh, Pezhman Shafikhani |
10.5120/ijais2015451429
|
S. Vahid Farrahi, Mohammad Mehdi Masoumi, Marzieh Ahmadzadeh, Pezhman Shafikhani . Effective Values of Physical Features for Type-2 Diabetic and Non-diabetic Patients Classifying Case Study: Shiraz University of Medical Sciences. International Journal of Applied Information Systems. 9, 7 ( September 2015), 1-6. DOI=10.5120/ijais2015451429
Abstract
Currently, one of the major issues regarding diabetes is its early detection. In this research, the dataset, which has been provided by Shiraz University of Medical Sciences, based on National Type-2 Diabetes Prevention and Control Program in Iran, used for finding an answer to a key question. In this program, there are some standard danger factors based on the physical features, which indicate whether a person is susceptible to diabetes (some people are unaware of their disease) or not, such as Body Mass Index (BMI). The World Health Organization (WHO) mentioned standard values for the danger factors which are based on the physical features, based on those; people who are suspicious for diabetes (considering their physical features) are referred back to the lab to take the Fasting Blood Sugar Test (FBS). The key question is that which values of physical features separate the diabetic and non-diabetic people more accurately, in Iran or more specifically in Shiraz. Classification is one of the data mining techniques, which can classify diabetic and non-diabetic people. Decision tree is a classification technique that can provide generalized rules based on the tree. In this paper, C4.5 decision tree algorithm has been used for rules generation. The extracted rules mention different values of physical features than the standard values.
References
- M. Khajehei, and F. Etemady, "Data Mining and Medical Research Studies." pp. 119-122.
- K. Rajesh, and V. Sangeetha, “Application of data mining methods and techniques for diabetes diagnosis,” International Journal of Engineering and Innovative Technology (IJEIT), vol. 2, no. 3, 2012.
- M. Alavinia, M. Ghotbi, A. Mahdavi Hezareh, A. Kermanchi, A. Nasli, and S. Yarahmadi, "Regulations of the Type-2 Diabetes National Prevention and Control Program," Ministry of Health and Medical Education, 2012.(Language in Persian)
- "Iran Diabets Society," http://ids.org.ir/index.php/fa/explore/layouts/diabets123.(Language in Persian)
- M. Lichman. "UCI Machine Learning Repository," http://archive.ics.uci.edu/ml.
- M. Patil, R. Joshi, and D. Toshniwal, "Association rule for classification of type-2 diabetic patients." pp. 330-334.
- A. A. Al Jarullah, "Decision tree discovery for the diagnosis of type II diabetes." pp. 303-307.
- B. M. Patil, R. C. Joshi, and D. Toshniwal, “Hybrid prediction model for Type-2 diabetic patients,” Expert systems with applications, vol. 37, no. 12, pp. 8102-8108, 2010.
- T. Pang-Ning, M. Steinbach, and V. Kumar, "Introduction to data mining." p. 74.
- J. R. Quinlan, C4. 5: programs for machine learning: Elsevier, 2014.
- R. Jain, D. Menasce, L. W. Dowdy, V. A. Almeida, C. U. Smith, and L. G. Williams, “The Art of Computer Systems Performance Analysis: Techniques,” 2010.
Index Terms
Keywords