Why the study?
Heart disease is the leading global cause of death, but healthcare systems lack effective tools to uncover hidden patterns from large, complex datasets.
Machine learning algorithms, particularly random forest and SVM, demonstrate strong predictive performance for estimating heart disease probability using a public dataset.
Heart disease is the leading cause of death globally, requiring advanced predictive knowledge and skills. Healthcare systems lack effective analysis tools to uncover hidden patterns. Using Kaggle’s dataset, an automated method aims to predict disease occurrences using data mining techniques, reducing costs and waiting times. Heart disease risk demands a sizable dataset that is excessively large and complex toprocess and analyze using traditional methods. Our goal is to identify an effective and precise method for estimating the probability of heart illness. The experimental results show the highest accuracy, Area under curve is best achieved by the random forest classifier which is about 83.96%, 92.35%, and the highest F1 score is achieved by SVM which is about 80.7%.
No takes yet. Share an insight, caveat, or question.
Pillai et al. (2023) studied Heart disease. Machine learning algorithms (Random Forest, SVM) was evaluated on Accuracy, Area under curve, and F1 score for estimating the probability of heart illness.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: