Table 1 Acceptability and usability assessment in the internal and external test set (n = 4592 and 360 curves, respectively)
From: Deep learning for spirometry quality assurance with spirometric indices and curves
Task | Balanced accuracy (%) | Sensitivity (%) | Specificity (%) | PPV (%) | NPV (%) |
|---|---|---|---|---|---|
Internal test set | |||||
FEV1 Acceptability | 95.1 | 97.8 | 92.4 | 99.6 | 69.6 |
FEV1 Usability | 92.4 | 99.4 | 85.4 | 99.7 | 72.2 |
FVC Acceptability | 93.6 | 97.5 | 89.6 | 98.9 | 79.4 |
FVC Usability | 94.3 | 99.5 | 89.0 | 99.8 | 74.7 |
External test set | |||||
FEV1 Acceptability | 97.7 | 99.6 | 95.8 | 98.0 | 99.1 |
FEV1 Usability | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |
FVC Acceptability | 95.4 | 99.6 | 91.3 | 94.9 | 99.2 |
FVC Usability | 100.0 | 100.0 | 100.0 | 100.0 | 100.0 |