Exploring the Effectiveness of Various Machine Learning Models in Predicting Heart Failure: A Comparative Study

The major cause of human mortality worldwide is cardiovascular disease, and lowering the mortality rate depends on early detection and intervention. By examining huge datasets of patient data to find similarities, machine learning algorithms can be a key player in the prediction of cardiovascular disease. This study compares the effectiveness of popular machine learning algorithms. The algorithms were examined, and accuracy, precision, recall, and overall performance were measured. The study's findings demonstrated that all the algorithms performed well in terms of foretelling heart disease, with accuracies above 85%. The KNN (K Nearest Neighbour) machine algorithm, with accuracy, precision, and recall values of 97.6%, 98%, and 98%, respectively, achieved the best overall performance. The effect of Min Max normalization on the effectiveness of the algorithms was also examined in the study. The data is scaled using the min-max normalization method to a range from 0 to 1. The study's findings demonstrated that the normalization caused a slight decline in overall performance. The results of this study could be used to create machine learning models for predicting heart disease that are more precise and effective. As a result, mortality may be decreased through improved heart disease early detection and treatment.