Key result
Both MLP and HMLP networks achieved high testing accuracies (99.2% and 99.4%, respectively) for profiling myocardial infarction history, but MLP reduced computational requirements by up to 30%.
Why the study?
Damaged heart tissue from myocardial infarction modifies normal sinus rhythm detectable by ECG, prompting characterization of prior myocardial infarction using QRS power ratio features and neural networks.
Does MLP or HMLP network provide better classification accuracy and computational efficiency for profiling myocardial infarction history from ECGs?
Does MLP or HMLP network provide better classification accuracy and computational efficiency for profiling myocardial infarction history from ECGs?
MLP networks provide highly accurate classification of myocardial infarction history from ECGs with lower computational requirements than HMLP networks.
MLP enables efficient ECG-based MI history profiling in practice; extends neural network applications in cardiology by showing computational savings at equivalent accuracy.
Narrowing of coronary arteries caused by cholesterol deposits deprives heart tissues of oxygen. In prolonged conditions, these will result in myocardium infarction. The presence of damage tissues modifies the normal sinus rhythm and this can be detected using electrocardiogram (ECG). Hence, this paper characterized history of myocardial infarction from survivors using QRS power ratio features from the ECG. Subsequent profiling is performed using multilayered perceptron (MLP) and hybrid multilayered perceptron (HMLP) networks. ECG with history of anterior and inferior infarctions, along with healthy controls is obtained from PTB Diagnostic ECG Database. The signal is initially pre-processed and the power ratio features are extracted for low- and mid-frequency components. The features are then used as input vector to the MLP and HMLP networks. The optimized MLP has attained accuracies of 99.2% for training and 98.0% for testing. Meanwhile, the optimized HMLP managed to achieve accuracies of 99.4% for training and 97.8% for testing. Despite the similarities in network performance, MLP provides a better alternative due to the reduced computational requirements by as much as 30%.
No takes yet. Share an insight, caveat, or question.
Gani et al. (2020) studied Myocardial infarction history (n=87). Multilayered perceptron (MLP) network vs. Hybrid multilayered perceptron (HMLP) network was evaluated on Classification accuracy on testing dataset. Both MLP and HMLP networks achieved high testing accuracies (99.2% and 99.4%, respectively) for profiling myocardial infarction history, but MLP reduced computational requirements by up to 30%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: