Key result
ECG feature extraction using MFCC and KNN classification achieved 84% accuracy, 85% sensitivity, and 84% specificity in identifying myocardial infarction from normal signals.
Why the study?
Accurate feature extraction of ECG signals is essential to diagnose cardiovascular diseases and produce better identification of abnormal cardiac activity.
Does MFCC feature extraction and KNN classification accurately identify myocardial infarction from ECG signals?
Does MFCC feature extraction and KNN classification accurately identify myocardial infarction from ECG signals?
MFCC feature extraction combined with KNN classification shows promising accuracy (84%) in detecting myocardial infarction from ECG signals.
No takes yet. Share an insight, caveat, or question.
May aid automated MI screening from ECG; extends ML-based signal classification in cardiology.
Yusuf et al. (2019) studied Myocardial infarction (n=100). MFCC feature extraction and KNN classification was evaluated on Classification accuracy, sensitivity, and specificity. ECG feature extraction using MFCC and KNN classification achieved 84% accuracy, 85% sensitivity, and 84% specificity in identifying myocardial infarction from normal signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: