Key result
Power ratio features from augmented limb leads achieved a higher testing classification accuracy of 93.3% compared to 89.4% for bipolar limb leads in distinguishing post-MI patients from healthy controls.
Why the study?
Does the use of power ratio features from augmented limb leads improve the classification accuracy of post-MI ECG compared to bipolar limb leads?
Observational (n=35)
Does the use of power ratio features from augmented limb leads improve the classification accuracy of post-MI ECG compared to bipolar limb leads?
Power ratio features from augmented limb leads combined with a k-nearest neighbor classifier can effectively distinguish between healthy controls and post-MI patients with high accuracy.
Augmented limb lead features merit prospective testing for post-MI ECG classification; leaves open translation to clinical practice.
Myocardial infarction (MI) is the irreversible necrosis of heart muscles caused by prolonged ischemic condition. Subsequently the presence of damaged tissues in post-MI patients is expected to have an effect on their electrocardiogram (ECG). Hence, this paper proposes characterization of post-MI ECG from bipolar and augmented limb leads. Data from patients of inferior and anterior MI, as well as healthy controls are acquired from PTB Diagnostic ECG Database. Noise removal is performed using band-pass filter. Power ratio is then extracted from energy spectral density of bipolar and augmented limb leads. Classification via k-nearest neighbor method revealed that features from the augmented limb leads outperform bipolar limb leads in terms of training and testing accuracies. Hence, power ratio features from the augmented limb leads exhibit higher degree of separation between the ECG classes.
No takes yet. Share an insight, caveat, or question.
Ali et al. (2018) conducted an observational in Myocardial Infarction (n=35). Power ratio features from augmented limb leads vs. Power ratio features from bipolar limb leads was evaluated on Testing classification accuracy using k-nearest neighbor (k=2). Power ratio features from augmented limb leads achieved a higher testing classification accuracy of 93.3% compared to 89.4% for bipolar limb leads in distinguishing post-MI patients from healthy controls.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: