Table 3.
Classification performances of the system and the ophthalmologists on validation datasets 1 and 2.
Sensitivity (95% CI) | Specificity (95% CI) | AUC (95% CI) | P-value | |||||
---|---|---|---|---|---|---|---|---|
Set 1 | Set 2 | Set 1 | Set 2 | Set 1 | Set 2 | Set 1 | Set 2 | |
Grader 1 | 0.788 (0.773–0.802) | 0.794 (0.785–0.803) | 0.975 (0.969–0.980) | 0.983 (0.980–0.986) | N/A | N/A | 8.43e–9 | 9.04e–39 |
Grader 2 | 0.928 (0.918–0.937) | 0.603 (0.592–0.614) | 0.977 (0.971–0.982) | 0.968 (0.983–0.988) | N/A | N/A | 1.18e–4 | 9.04e–39 |
AI Model | 0.918 (0.908–0.927) | 0.914 (0.907–0.920) | 0.934 (0.925–0.942) | 0.922 (0.916–0.928) | 0.952 (0.945–0.968) | 0.966 (0.959–0.974) |
AUC area under the curve, CI confidence interval, AI artificial intelligence, Set 1: validation dataset 1, Set 2: validation dataset 2, N/A not available.