Hybrid feature selection technique for prediction of cardiovascular diseases

Diagnosing a disease consumes a part of time, needs high technical methods but nowadays the smart technologies have been grown rapidly in the field of healthcare industries and also it improves the routine life of the patients, reduces the amount of work, treatment cost in the health care organization. Diseases prediction is one of the major challenges faced by society nowadays. The recent survey also stated that the death rate is remarkably high in CAD because most of the people are affected by cardiovascular diseases. Prediction and diagnosis of cardiovascular diseases is very essential nowadays to reduce the death rate and diagnosing it preliminary stage itself. In earlier studies, they worked with machine learning techniques to predict the diseases, but they are not given proper attention to identifying the feature with the help of proper feature selection methods. This paper proposed a new-found feature selection technique HRFLC (RANDOM FOREST + ADABOOST + PEARSON COEFFICIENT). This method helps to predict the diseases in a very efficient manner, and it improves the accuracy level in prediction.