An Intelligent Hybrid Inference System for Monitoring of Heart Disease

Abstract

In the healthcare system, the most crucial and vital issue is the procedure of heart disease diagnosis as the patient's life is only dependent on it, and it can reduce the disease at a particular level. However, in many cases, the selected procedure results in wrong and unexpected results or even lead to a patient’s death. Hence, the most challenging task in the medical domain is a diagnosis of heart disease done by medical professionals. In this technical era, the role of artificial intelligence in the healthcare system is considerable and appraisable. Therefore, this study introduced a model which has the capability to monitor heart disease by using a hybrid methodology of machine learning, i.e., neuro fuzzy approach. In the developed intelligent hybrid inference system, there are total input variables which are utilized to classify the disease into different stages. The system generates the output, which provides the three different stages or levels of the disease. Moreover, according to this generated outcome, professional doctors of the heart can make a wise decision for the patient and also can choose the best procedure for the treatment corresponding to the disease’s stage. The k-fold cross validation method is utilized to do the partitioning of the dataset and for testing purposes. The performance of the system is also calculated, and according to those results, the presented inference model accurately forecasts the stage of the heart disease from which a patient is suffering with an accuracy of 98.90 percent.