Table 3.
Prediction performance of different models for fungal keratitis.
| Author | Type of study | Sample size (case number) | Type of IK | Diagnostic model | Sensitivity (95% CI) | Specificity (95% CI) | Accuracy (95% CI) | AUC (95% CI) |
|---|---|---|---|---|---|---|---|---|
| Current study | Retrospective & prospective | 1916 (1916) | FK, BK, VK, AK | Binary logistic regression | 90.7 (77.4, 100.0) | 89.9 (75.0, 100.0) | 90.5 (80.5, 100.0) | 90.3 (80.8, 99.8) |
| Saini et al.14 | Retrospective | 63 (63) | FK, BK | Artifical neural network | 76.5 | 100.0 | 76.5 | – |
| Hung et al.15 | Retrospective | 1330 (580) | FK, BK | DenseNet161 | 65.8 (41.5, 65.8) | 87.3 (86.0, 95.3) | 65.8 | 85.0 |
| Kuo et al.16 | Retrospective | 288 (288) | FK, BK, VK, AK | DenseNet | 71.1 (62.1, 78.6) | 68.4 (61.1, 74.9) | 69.4 | 65.0 |
| Wang et al.17 | Retrospective | 1923 (1923) | FK, BK, VK | InceptionV3 | – | – | 77.3a | 93.5 |
| Ghosh et al.18 | Retrospective | 2167 (194) | FK, BK | DeepKeratitis | 77.0 (81.0, 83.0) | – | – | 90.4 |
| Koyama et al.19 | Retrospective | 4306 (362) | FK, BK, VK, AK | ResNet50 | – | – | 83.0 | 85.6 |
a
Means the data not obtained directly but could calculate based on the sufficient data provided in the paper; IK: infectious keratitis; AUC: the area under the receiver operating characteristic curve.