Intelligent diagnosis of cardiac disease prediction using machine learning

Abstract

Cardiac disease have become worldwide common public health issue, mainly due to lack of awareness of health, poor lifestyle and poor consumption. Practitioners may have different concerns when it comes to disease diagnosis, which result in different decisions and actions. On the other hand, even in the specific case of a typical disease the amount of information available is so massive that it can be difficult to make accurate and reliable decisions. With adequate patient and non-patient medical constraints, it is possible to accurately predict how likely it is that a person with heart disease and to obtain potential information from these systems. A mechanized framework for therapeutic analysis would also dramatically increase medical considerations and reduce costs. We developed a framework in this exploration that can understand the principles of predicting the risk profile of patients with the clinical data parameters. In this article, four machine learning algorithms and one neural network algorithm were used to compare performance measurements to cardiac diseases identification. We evaluated the algorithms with respect to accuracy, precision, recall and F1 settings to achieve the ability to predict cardiac attacks. The results show our method achieved 98 percent accuracy by neural network algorithm to predict cardiac diseases.