An Early Detection of Heart Disease using Machine Learning(recurrent neural network)

Abstract

People are obsessed with daily life, work, and other things while neglecting their health. Due to the hurried lifestyle and disregard for the health, the number of people getting sick every day is increasing. The majority of the population is afflicted with an illness such as heart disease. Heart diseaseshave been the leading cause of death on the globe during the last several decades, and have risen to become the highest existing condition on the earth. As a result, a reliable, accurate, and practical approach to the diagnosis of such disorders in time for adequate treatment is required. Numerous machine learning algorithms have recently been used by several researchers to aid the medical system and experts in the detection of heart-related disorders. To simplify the examination of large and complicated datasets, Machine Learning (ML) methods and techniques have been used on a variety of medical datasets. This research examines the performance of a variety of models based on such methods and techniques. Researchers use a variety of data sets and machine learning approaches to analyze large amounts of complicated medical data, assisting doctors in the prediction of heart disease. We'll provide support for RNN, Logistic Regression, and ANN methods. These algorithms are used to predict heart disease based on features. The efficacy of different machine learning methods is compared in this research. The objective of this study is to use a machine learning technique to estimate cardiac disease and then analyze the results .

CARDPSoML: Comparative approach to analyze and predict cardiovascular disease based on medical report data and feature fusion approach

“…Numerous evaluation metrics, including accuracy, precision, recall, and F1‐score, can be computed from the confusion matrix. These metrics include data on the overall performance of the classifier, including the proportion of examples that are properly classified as positive (TP) and negative (TN) and wrongly classified as positive (FP) and negative (FN) 30 …”