Published Paper Details:

It would be better if stats data on heart disease could be added here. For eg. According to WHO the number of people is reported to be suffering from heart disease, making it the most common disease worldwide. As we know that sometimes the lifestyle of human beings suffers from stress, anxiety, and depression, etc. The Detection of this disease is quite difficult in advance and it is challenging in medical science. The target of this paper is to understand certain machine learning models (MLMs) detection accuracy with classification techniques and limitations. Many researchers used certain machine learning models called classification techniques like naive bays (NB) decision tree (DT), Cooperative Neural-Network Ensembles (CNNEs) logistic regression (LR), Support Vector Machine (SVM), Least Square Twin Support Vector Machine (LSTSVM), k-Nearest Neighbor (KNN), Bays Net (BN), Artificial Neural Network (ANN) and Multi-Layer Perception (MLP).in general, we have a total of 50+ Features Attributes in the dataset. And we select the most appropriate features to detect the disease by using different features selection techniques to improve the accuracy. Maximum classification accuracy of 96.29% was achieved and we need to improve the accuracy with a minimum amount of time and try to develop single MLMs for detection and selection of precise features to improve the accuracy. Many researchers use hybrid approaches to combine two or more classification techniques (based on selected symptoms and features of a human being) in the layered form to improve the accuracy in terms of percentages. Sometimes it's not more effective and time-consuming. Hence, we need to develop flexible MLMs with feature selection and reduction techniques. Thus, the present study is focused on improving the accuracy. Also, include future perspectives or applications of your study.