In health care, automatic disease diagnosis is a precious tool because of limited observation of the expert and uncertainties in medical knowledge. Progresses in medical information technology have enabled healthcare industries to automatically collect huge quantity of data through clinical laboratory examinations. To explore these data, the past few years have envisaged the use of Computer Aided Diagnosis (CAD) systems in many hospitals and screening sites. Machine learning techniques are gradually introduced to construct the CAD systems owing to its well-built capability of extracting complex relationships in the biomedical data. Data mining is a pioneering and attractive research area due to its vast application areas and task primitives. Data classification is one of the most important tasks in data mining. Feature Selection is also known as Attribute selection which selects subset of features from original set by removing the irrelevant and redundant features. This paper focus on the literature review of two feature selection techniques namely, filter approach and wrapper approach.