Apdullah Yayık, Yakup Kutlu, Gökhan Altan
Our study concerns with automated predicting of congestive heart failure (CHF) through the analysis of electrocardiography (ECG) signals. A novel machine learning approach, regularized hessenberg decomposition based extreme learning machine (R-HessELM), and feature models; squared, circled, inclined and grid entropy measurement were introduced and used for prediction of CHF. This study proved that inclined entropy measurements features well represent characteristics of ECG signals and together with R-HessELM approach overall accuracy of 98.49% was achieved.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Electrocardiography (ECG) | CHF database | Accuracy | 98.49 | Inclined Entropy (R-HessELM) |
| Electrocardiography (ECG) | CHF database | Precision | 98.05 | Inclined Entropy (R-HessELM) |
| Electrocardiography (ECG) | CHF database | Sensitivity | 98.3 | Inclined Entropy (R-HessELM) |
| Medical waveform analysis | CHF database | Accuracy | 98.49 | Inclined Entropy (R-HessELM) |
| Medical waveform analysis | CHF database | Precision | 98.05 | Inclined Entropy (R-HessELM) |
| Medical waveform analysis | CHF database | Sensitivity | 98.3 | Inclined Entropy (R-HessELM) |