Answers are grounded in this paper and cite their sources.
Demonstrates 98% accuracy in heart disease classification using a Levenberg-Marquardt-optimized neural network, indicating strong potential for automated clinical diagnostic tools.
This study explores the application of neural networks in heart disease diagnosis, hypothesizing that optimizing the Levenberg-Marquardt algorithm will significantly improve diagnostic accuracy compared to other methods. A dataset of 1190 instances and 11 parameters, obtained from Kaggle, was used. The network architecture was tested with one, two, and three hidden layer configurations, using logistic sigmoid activation functions in the hidden layers and a linear activation function in the output layer. The performance of the Levenberg-Marquardt-optimized network outperformed gradient descent and quasi-Newton BFGS methods, achieving a diagnostic accuracy of 98%. These findings support the hypothesis and highlight the potential of neural networks to improve clinical diagnosis of heart disease [23].
No takes yet. Share an insight, caveat, or question.
Morales et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: