Recognition of Heart Disease Based on Primitive Parameters Using Machine Learning Model

Cardiovascular diseases (CVDs) have a significant worldwide impact, affecting millions of victims. The complex nature of these conditions requires modern treatments to address them effectively. In order to forecast certain diseases, machine learning algorithms take into account factors like age, gender, and blood pressure, amongst other characteristics. To enhance the usefulness of these algorithms, it is necessary to carefully choose their characteristics in an ideal manner. Various techniques, in order to identify the necessary traits, many techniques, including Recursive Feature Elimination, the least absolute shrinkage and selection operator, Relief approach, and mutual data, are being applied. Methods from the field of machine learning (ML) such as random forest, logistical regression, and K-nearest neighbours (KNN) are frequently employed in the process of predicting cardiovascular disease (CVD). These approaches have demonstrated beneficial effects and may be used to enhance the health of patients through early diagnosis. This study proposes an integrated approach that blends feature selection approaches with machine learning techniques in order to enhance cardiovascular disease prediction. Several methodologies have been evaluated in order to determine the most effective approach for predicting cardiovascular illnesses.