Key result
Improved Bat algorithm neural network outperforms standard algorithms, detecting MI from ECGs with ~99% accuracy.
Why the study?
Accurate detection of myocardial infarction from ECG signals requires effective feature extraction methods to improve classifier performance.
Does the Improved Bat algorithm improve the performance of a neural network classifier in detecting myocardial infarction from ECG signals?
Population
ECG signals for detection of myocardial infarction
Comparison
Improved Bat algorithm feature extraction vs non-optimized features
Design
Other study applying feature extraction and neural network classification
Authors
Loading...
May support ECG-based MI screening; leaves open prospective validation before clinical adoption.
Does the Improved Bat algorithm improve the performance of a neural network classifier in detecting myocardial infarction from ECG signals?
Absolute Event Rate: 98.9% vs 58.7%
The Improved Bat algorithm enhances feature extraction from ECG signals, thereby improving the performance of neural network classifiers in detecting myocardial infarction.
Padmavathi Kora (2015) studied Myocardial infarction (n=13). Improved Bat algorithm (IBA) with Levenberg-Marquardt neural network vs. Standard Bat algorithm (BA) was evaluated on Classification accuracy. The Improved Bat algorithm combined with a Levenberg-Marquardt neural network achieved a classification accuracy of 98.9% for detecting myocardial infarction from ECG signals, outperforming the standard Bat algorithm.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: