Research Article
Artificial Intelligence-Based Classification of Chest X-Ray Images into COVID-19 and Other Infectious Diseases
Table 4
Performance of combined models on training, internal validation, and external validation images.
| Sr. No. | Name of the model | Results of the internal validation | Results of the external validation (using all test set images combined) | Model type | Training accuracy () | Validation accuracy () | Validation loss | Normal () | COVID-19 () | New COVID-19 () | Non-COVID-19 () | Pneumonia () | TB () |
| 1 | Combined model 1 (24 epochs) | 100 | 93.8 | 0.126 | 73.63 | 56.92 | 42.62 | 53.85 | 96.39 | 75.38 | 2 | Combined model 2 (49 epochs) | 100 | 100 | 0.015 | 86.26 | 65.38 | 43.59 | 42.31 | 96.15 | 73.08 | 3 | Combined model 3 (101 epochs) | 100 | 93.8 | 0.524 | 85.71 | 70.77 | 51.28 | 51.92 | 93.99 | 74.62 |
|
|