Key result
Artificial Neural Networks and Support Vector Machines were implemented to classify ECG signals for the detection of myocardial infarction, though specific performance metrics were not reported.
Why the study?
Can Artificial Neural Networks and Support Vector Machines accurately classify ECG signals to detect Myocardial Infarction?
Can Artificial Neural Networks and Support Vector Machines accurately classify ECG signals to detect Myocardial Infarction?
This study explores the use of machine learning algorithms (ANN and SVM) for the automated detection of myocardial infarction from ECG signals.
Answers are grounded in this paper and cite their sources.
Machine learning ECG classifiers for MI are feasible; leaves open accuracy and clinical validation pending unreported metrics.
One of the most common form of cardiac abnormality is Myocardial Infarction (heart attack) arises when the artery connecting the heart is blocked and there is no sufficient blood or oxygen, which makes the cells present in that region of the heart to die. This paper aims to process and classify an ECG signal as healthy subject or subject diagnosed with Myocardial Infarction (MI) using Artificial Neural Networks (ANN) and SVM (Support Vector Machine). LIBSVM1 is utilized for the classification with SVM and backpropogation artificial neural networks with varying hidden layers and nodes are also implemented for performance analysis.
No takes yet. Share an insight, caveat, or question.
Nitin Aji Bhaskar (2015) studied Myocardial Infarction. Artificial Neural Networks (ANN) and Support Vector Machine (SVM) was evaluated on Classification of ECG signal as healthy or Myocardial Infarction. Artificial Neural Networks and Support Vector Machines were implemented to classify ECG signals for the detection of myocardial infarction, though specific performance metrics were not reported.
Synapse has enriched 10 related papers. Consider them for comparative context: