PurposeTo investigate the changes in dry eye symptoms and clinical signs and corneal sensitivity after small incision lenticule extraction (SMILE) and femtosecond LASIK (femto-LASIK).DesignProspective, non-randomized comparative study.MethodsThe study included a total of 71 eyes of 71 patients; the SMILE group comprised 38 eyes of 38 patients, and the femto-LASIK group comprised 33 eyes of 33 patients. Ocular Surface Disease Index (OSDI), Tear film breakup time (TBUT), the Schirmer test without anesthesia (S1T), corneal fluorescein staining, and central corneal sensation were evaluated before surgery and at 1 week, 1 month, 3 months, and 6 months after surgery.ResultsOSDI scores in both groups were increased immediately and returned to preoperative level at 1 month after surgeries. The TBUT values in both groups were reduced after surgeries relative to their preoperative scores. Patients in SMILE group were less likely to have corneal staining compared with those in the femto-LASIK group ([odds ratio] OR = 0.50, 95% [confidence interval] CI 0.28 to 0.93, P = 0.03). Central corneal sensitivity was decreased at all postoperative time points in both groups. However, the central corneal sensation scores in the SMILE group were greater than that in the femto-LASIK group at all of the postoperative time points (all P<0.05).ConclusionsSMILE surgeries resulted in a short-term increase in dry eye symptoms, tear film instability, and loss of corneal sensitivity. Furthermore, SMILE surgeries have superiority over femto-LASIK in lower risk of postoperative corneal staining and less reduction of corneal sensation.

This study suggests that, although mild decentration occurred in the early learning curve, good visual outcomes were achieved after the SMILE surgery. Special efforts to minimize induced vertical coma are necessary.

Implanting an autologous lenticule obtained by small incision lenticule extraction for hyperopia might be safe, effective, and stable, but its predictability should be improved in the future.

Applanation time (applanation 1) and deformation amplitude (as measured with the CorVis ST tonometer) may be helpful in assessing corneal biomechanical changes after corneal refractive surgery. The relations between these parameters should be discussed in further studies.

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.