Abstract
Coronary artery disease (CAD) has been ranked as the top cause of death by world health organization in many countries especially Asia. In Malaysia, 22.18% of total deaths are caused by CAD. In this paper, our focus is to review possible types of data mining algorithms applied for processing of clinical attributes as well as their classification to identify normal and CAD patients in minimal time with optimized accuracy. Various combinations of these techniques and variation have adverse effects as well as increased performance, which will be covered in this paper. Data selection for designing a detection system also varies the system performance and it can be dealt with using standard data sets with relevant feature to ease detection of abnormalities with maximum detection rate.
Original language | English |
---|---|
Pages (from-to) | 6679-6685 |
Number of pages | 7 |
Journal | ARPN Journal of Engineering and Applied Sciences |
Volume | 10 |
Issue number | 15 |
Publication status | Published - 2015 |
Externally published | Yes |
Keywords
- Classification
- Cleveland dataset
- Coronary artery disease (CAD)
- Feature processing
- Irvine (UCI)
- Supervised learning
- University of california