Table 2 Performance metrics of the proposed deep learning-based lung sound analysis.
From: Deep Learning-Driven Early Diagnosis of Respiratory Diseases using CNN-RNN Fusion on Lung Sound Data
Lung Disease | No. of Samples | Sensitivity | Specificity | Recall | Precision | F1-Score | Accuracy (%) | AUC |
|---|---|---|---|---|---|---|---|---|
Healthy | 300 | 0.9673 | 0.9125 | 0.9702 | 0.9214 | 0.9417 | 93.3 | 0.9395 |
Pneumonia | 200 | 0.9023 | 0.9752 | 0.9004 | 0.9697 | 0.9401 | 93.8 | 0.9375 |
Asthma | 150 | 0.8746 | 0.9581 | 0.8803 | 0.9502 | 0.9104 | 91.7 | 0.9165 |
COPD | 100 | 0.9201 | 0.9674 | 0.9206 | 0.9703 | 0.944 | 94 | 0.9435 |
