The diagnosis of heart disease in most cases depends on a complex combination of
clinical and pathological data; this complexity leads to excessive medical costs affecting
the quality of the medical care (Wu et al., 2002). According to WHO, one-third of the
population worldwide die due to heart disease and heart disease is found to be the
leading cause of death in developing countries. According to the American Heart
Association report, one-third of the American adults have one or more types of heart
diseases. Computational biology is often applied to the process of translating biological
knowledge into clinical practice, as well as to understand biological phenomena from
the clinical data. The key contribution of computational biology is the discovery of
biomarkers in heart disease. This process involves development of a predictive model
and integration of different types of data and knowledge for diagnostic purposes.
Further, this process requires the design and combination of different methodologies
from statistical analysis and data mining (Thuraisingham, 2000; and Rajkumar and
Reena, 2010).
In the past decades, data mining has played an important role in heart disease
research. Finding the hidden medical information from the different expression
between the healthy and the heart disease individuals in the existed clinical data is a
useful approach to the study of heart disease classification. Heart disease classification
provides critical basis for the therapy of patients. Statistics and machine learning are
two main approaches which have been applied to predict the status of heart disease
based on the clinical data (Palaniappan and Awang, 2008; and Anbarasi et al., 2010).
|
