The proposed machine learning model outperformed existing methods in terms of accuracy and robustness for predicting the risk of heart disease.
Advanced machine learning models demonstrate superior accuracy and robustness for predicting heart disease risk, potentially aiding clinical decision-making.
This research study outlines the advanced mapping techniques used for predicting the risk of heart disease. It compares the classification algorithms like random forest, logistic regression, and decision trees to determine the most reliable approach. The performance of these models is evaluated using metrics such as specificity, sensitivity, accuracy, and AUC-ROC. This study highlights the interpretability of the models by analyzing the key factors that influence the risk of heart diseases. The proposed machine learning model outperforms existing methods in terms of accuracy and robustness. The findings support the application of the proposed model in clinical settings to identify high-risk groups earlier, assist healthcare providers in the process of decision-making and improve patient outcomes.
Chandrika et al. (2024) studied Heart disease. Machine learning models (random forest, logistic regression, decision trees) vs. Existing methods was evaluated on Model performance (specificity, sensitivity, accuracy, and AUC-ROC). The proposed machine learning model outperformed existing methods in terms of accuracy and robustness for predicting the risk of heart disease.