Prediction of heart disease using machine learning: State of the art and future direction

Abstract

Heart disease detection is done here using a number of sample data taken from various sources. We have to use different machine learning technique to detect whether a given data is cancer infected or not. An ingenious technique that allows many technologies to learn from themselves. It is an instance of artificial learning that enables computers to function like humans. Machine learning aims for computers to learn on their own without any human interruption. When united with IoT, it has a high capability to grasp things. It has ability to change the mortgage market. It has accurate data analysis and has very sharp business intelligence. Machine learning has four fundamental steps to create a model. First, a training dataset is selected and prepared, then an algorithm has to be selectedto apply to the training dataset. After this, the algorithm is trained to create the model and, lastly using and improving the model. Machine learning consists of various techniques like supervised learning algorithms, unsupervised learning algorithms, reinforcementmachine learning, and semi-supervised machine learning. To create any machine learning model there are few python libraries that are always needed. They are pandas, NumPy, skleam, and matplotlib. If there is a need to evaluate the performance of a machine learning algorithm, the train test split technique can be used. To create a graph/plot, pyplot which is a matplotlib module comes in handy. It can help in creating bar graphs, pie charts, histograms, scatter plots,and 3D plotting. In the model, we are using a few functions like standardscaler () function, classification report, and confusion matrix. In the end, we are getting a required plot that will show us the accuracy of our model. Results are shown at last and conclusions are derived.