Key result
A SMOTE-based artificial neural network, without the need for feature engineering, outperformed other machine learning models and existing systems in predicting heart attacks.
Why the study?
Heart attack prediction using machine learning faces challenges including massive resource utilization, extensive preprocessing, costly feature engineering, and class imbalance.
A SMOTE-based artificial neural network without feature engineering provides a highly reliable and cost-effective solution for predicting heart attacks using imbalanced datasets.
No takes yet. Share an insight, caveat, or question.
Problems in applying machine learning to cardiac data persist; leaves open the need for rigorous validation before clinical adoption.
Waqar et al. (2021) studied Heart attack. SMOTE-based artificial neural network vs. Other machine learning algorithms and existing systems was evaluated on Heart attack prediction. A SMOTE-based artificial neural network, without the need for feature engineering, outperformed other machine learning models and existing systems in predicting heart attacks.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: