<![CDATA[The heart is a vital organ in the human body, responsible for pumping blood throughout the body via the circulatory system. The heart is responsible for the delivery of oxygen and nutrients to tissues, as well as the removal of carbon dioxide and other waste products. Any disruption to the heart's functioning has the potential to be fatal to human survival. One such disruption is heart failure disease, also known as congestive heart failure (CHF). It is of the utmost importance to detect heart failure at an early stage. The early detection of heart failure disease can be achieved through the utilisation of machine learning, which can mitigate the low probability of this disease. This research employs a machine learning system based on artificial intelligence, utilising logistic regression and adaptive boosting (adaboost) algorithms. The research findings indicate that the classification of heart failure can be accurately determined using a range of parameters. The highest accuracy results, derived from this study, are 90% accuracy, 84% precision, 88% recall, and 88% F1-score. These results are exclusively attributable to the adaboost algorithm. In comparison to the logistic regression algorithm, the resulting accuracy is still below that of the adaboost algorithm, with the results being 86% accuracy, 76% precision, 79% recall, and 88% F1-score. It can therefore be concluded that the adaboost algorithm is more effective than the logistic regression algorithm in classifying heart failure disease. This is particularly the case when the selected data set exhibits an unbalanced number of labels.]]>
Copyrights © 2025
