A hybrid model for heart disease prediction using recurrent neural network and long short term memory

Cardiac and cardiovascular diseases are among the most prevalent and dangerous ailments that influence human health. The detection of cardiac disease in its early stages by the use of early-stage symptoms is a major problem in today’s environment. As a result, there is a demand for a technology that can identify cardiac disease in a non-invasive manner while also being less expensive. In this research we have developed a hybrid deep learning methodology for the categorization of cardiac disease. Classifying synthetic data using RNN and LSTM hybrid approaches has been done using different cross-validations. The system’s performance also be evaluated using a variety of machine learning methods and soft computing approaches. During the classification process, RNN employs three separate activation functions. To balance the data, certain pre-processing methods were used to sort and classify the data. The extraction of features has been done using relational, bigram, and density-based approaches. We employed a variety of machine learning and deep learning methods to assess system performance throughout the trial. The accuracy of each algorithm’s categorization is shown in the results section. As a result, we can say that deep hybrid learning is more accurate than either classic deep learning or machine learning techniques used alone. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.