Prediction of Cardiovascular Disease by Feature Selection and Machine Learning Techniques

Cardiovascular diseases (CVDs) are prevalent in the population and often lead to fatalities. Recent polls indicate that the death rate is increasing due to people's increased use of tobacco, high blood pressure, cholesterol, and obesity. These factors also exacerbate the severity of the disease. Therefore, it is crucial to conduct research on the variations of these factors and their impact on CVD. To prevent further disease progression and reduce mortality rates, it is essential to utilize current procedures. Various techniques, such as AI and data mining, are available to predict CVD precursors and detect their behavior patterns in large amounts of data. The results of these forecasts will assist clinical experts in decision-making and early diagnosis, reducing the likelihood of patient fatalities. This study investigates and comments on the Exhaustive Feature Selection (EFS) and Sequential Feature Selection (SFS) techniques and the results obtained using them with various classifiers. The paper also provides an overview of the current methods based on features and algorithms used.