Data Mining Perspective: Prognosis of Life Style on Hypertension
and Diabetes
Abdullah
Aljumah and Mohammad Siddiqui
College
of Computer Engineering and Sciences, Salman bin Abdulaziz University,
Kingdom of Saudi Arabia.
Abstract: In the present era, the data mining techniques
are widely and deeply useful as decision support systems in the fields of
health care systems. The proposed research is an interdisciplinary work of
informatics and health care, with the help of data mining techniques to predict
the relationship among interventions of hypertension and diabetes. As the study
shows persons who have diabetes can have chances of hypertension and vice
versa. In the present work we would like to approach the life style
intervention of hypertension and diabetes and their effects using data mining. Life
style intervention plays a vital role to control these diseases. The
intervention includes the risk factor like diet, weight, smoking cessation and
exercise. The regression technique is used in which dependent and independent
variables are defined. The four interventions are treated as independent
variables and two diseases hypertension and diabetes are dependent variables.
We have established the relationship between hypertension and diabetes, using
the data set of Non Communicable Disease NCD report of Saudi Arabia, World
Health Organisation’s (WHO). The Oracle Data Miner (ODM) tool is used to
analyse the data set. Predictive data analysis gives the result that
interventions weight control and exercise have the direct relationship between
them in both the diseases.
Keywords: Oracle data mining tool, prediction, regression, support vector
machine, hypertension, diabetes.
Received April 10,
2014; accepted June 23, 2014