AimsTo predict the vault and the EVO-implantable collamer lens (ICL) size by artificial intelligence (AI) and big data analytics.MethodsSix thousand two hundred and ninety-seven eyes implanted with an ICL from 3536 patients were included. The vault values were measured by the anterior segment analyzer (Pentacam HR). Permutation importance and Impurity-based feature importance are used to investigate the importance between the vault and input parameters. Regression models and classification models are applied to predict the vault. The ICL size is set as the target of the prediction, and the vault and the other input features are set as the new inputs for the ICL size prediction. Data were collected from 2015 to 2020. Random Forest, Gradient Boosting and XGBoost were demonstrated satisfying accuracy and mean area under the curve (AUC) scores in vault predicting and ICL sizing.ResultsIn the prediction of the vault, the Random Forest has the best results in the regression model (R2=0.315), then follows the Gradient Boosting (R2=0.291) and XGBoost (R2=0.285). The maximum classification accuracy is 0.828 in Random Forest, and the mean AUC is 0.765. The Random Forest predicts the ICL size with an accuracy of 82.2% and the Gradient Boosting and XGBoost, which are also compatible with 81.5% and 81.8% accuracy, respectively.ConclusionsRandom Forest, Gradient Boosting and XGBoost models are applicable for vault predicting and ICL sizing. AI may assist ophthalmologists in improving ICL surgery safety, designing surgical strategies, and predicting clinical outcomes.

The posterior corneal surface, measured using the Pentacam, was stable after SMILE in the long-term follow-up. The cause of the slight backward change of PCE and PTE needs further study. [J Refract Surg. 2017;33(2):84-88.].

Purpose:The objective of this study is to investigate changes in corneal densitometry after accelerated transepithelial corneal collagen cross-linking (ATE-CXL) for patients with progressive keratoconus (KC).Methods:Seventeen progressive KC patients who underwent ATE-CXL (KC group) were examined and compared against 17 non-KC myopes (control group). For the KC group, corneal topography and densitometry were evaluated preoperatively and at 1, 6, and 12 months postoperatively. Manifest refraction spherical equivalent and best spectacle-corrected distant visual acuity were assessed preoperatively and at 12 months postoperatively. These parameters were also evaluated in the control group.Results:Preoperatively, in the KC group, the densitometry values of the total layer over the annular diameters (Φ) 0 to 2 and Φ 2 to 6 mm were 18.47 ± 1.81 and 16.62 ± 1.60, respectively. In the control group, the values were 14.98 ± 1.18 and 13.39 ± 1.33, respectively, significantly lower than those of the KC group (both post hoc P values < 0.001). At postoperative month 12, the densitometry values of Φ 0 to 2 and Φ 2 to 6 mm of the total layer in the KC group were 16.88 ± 1.57 and 15.28 ± 1.40, which were significantly lower than the preoperative values (post hoc P = 0.012 and 0.030, respectively). However, they were still higher than those of the myopes (post hoc P = 0.002 and 0.001, respectively).Conclusions:KC patients have much higher corneal densitometry values than myopes without KC. The KC patients' corneal densitometry values decreased significantly when measured at 12 months after ATE-CXL. However, they remain higher than those of the myopes.