Abstract
Extraction of knowledge from healthcare database becomes one of the most important issues in data mining. There is a wealth of hidden information within healthcare data that can be used to support clinical decisionmaking in addition to useful information that can help healthcare provider to predict diseases before it occurs. Diabetes is one of chronic disease with high prevention in Saudi society and a major health issue worldwide. According to the International Diabetes Federation, there are 387 million diabetic people worldwide in 2014, and this number expected to increase by +202 million by 2035. Saudi Arabia is one of the countries with high prevention of diabetes, where 25% of people suffering from diabetes. In this paper, we propose a utilization of knowledge discovery on healthcare data, in particular building a diabetes early warning system, to predict diabetes's risk factors that can cause that disease or increase the risk of developing diabetes in non-diabetic patients. Three data mining algorithms have been used; RIPPER, C4.5 decision tree, and AdaBoost (Meta algorithm). As a result of applying these algorithms in real diabetes data sets, a prediction model were constructed with high prediction accuracy. In addition, the extracted rules are consistent with medical studies. The signatures/models generated from the data mining algorithms can be used in building an early warning system that can benefit healthcare sector in providing prevention and control programs for community health improvement.