Key result
Deep neural network classifier outperforms standard methods in CAD classification accuracy, sensitivity, and specificity.
Why the study?
Existing methods for diagnosing coronary artery disease have limitations in accuracy, sensitivity, and specificity that motivate evaluation of alternative classifiers.
Does a deep neural network classifier improve classification performance compared to other methods in coronary artery disease datasets?
Does a deep neural network classifier improve classification performance compared to other methods in coronary artery disease datasets?
A deep neural network classifier provides an easily accessible and cost-effective alternative for diagnosing coronary artery disease with improved accuracy, sensitivity, and specificity.
Answers are grounded in this paper and cite their sources.
Offers a promising computational approach for CAD classification; leaves open real-world clinical utility pending validation.
In this study, a deep neural network classifier is proposed for the classification of coronary artery disease medical data sets. The proposed classifier is tested on reference CAD data sets from the literature and also compared with popular representative classification methods regarding its classification performance. Experimental results show that the deep neural network classifier offers much better accuracy, sensitivity and specificity rates when compared with other methods. The proposed method presents itself as an easily accessible and cost-effective alternative to currently existing methods used for the diagnosis of CAD and it can be applied for easily checking whether a given subject under examination has at least one occluded coronary artery or not.
No takes yet. Share an insight, caveat, or question.
Çalışkan et al. (2017) studied Coronary artery disease. Deep neural network classifier vs. Popular representative classification methods was evaluated on Classification performance (accuracy, sensitivity, and specificity). A deep neural network classifier demonstrated better accuracy, sensitivity, and specificity for the classification of coronary artery disease compared with other popular classification methods.
Synapse has enriched 10 related papers. Consider them for comparative context: