Enhanced Tomographic Assessment to Detect Corneal Ectasia Based on Artificial Intelligence.

PURPOSE: To improve the detection of corneal ectasia susceptibility using tomographic data. DESIGN: Multicenter case-control study. METHODS: Data from patients from 5 different clinics from South America, the United States, and Europe were evaluated. Artificial intelligence (AI) models were generated using Pentacam HR (Oculus, Wetzlar, Germany) parameters to discriminate the preoperative data of 3 groups: stable laser-assisted in situ keratomileusis (LASIK) cases (2980 patients with minimum follow-up of 7 years), ectasia susceptibility (71 eyes of 45 patients that developed post-LASIK ectasia [PLE]), and clinical keratoconus (KC; 182 patients). Model accuracy was independently tested in a different set of stable LASIK cases (298 patients with minimum follow-up of 4 years) and in 188 unoperated patients with very asymmetric ectasia (VAE); these patients presented normal topography (VAE-NT) in 1 eye and clinically diagnosed ectasia in the other (VAE-E). Accuracy was evaluated with ROC curves. RESULTS: The random forest (RF) provided highest accuracy among AI models in this sample with 100% sensitivity for clinical ectasia (KC+VAE-E; cutoff 0.52), being named Pentacam Random Forest Index (PRFI). Considering all cases, the PRFI had an area under the curve (AUC) of 0.992 (94.2% sensitivity, 98.8% specificity; cutoff 0.216), being statistically higher than the Belin/Ambrósio deviation (BAD-D; AUC = 0.960, 87.3% sensitivity, 97.5% specificity; P = .006, DeLong's test). The optimized cutoff of 0.125 provided sensitivity of 85.2% for VAE-NT and 80% for PLE, with 96.6% specificity. CONCLUSION: The PRFI enhances ectasia diagnosis. Further integrations with corneal biomechanical parameters and with the corneal impact from laser vision correction are needed for assessing ectasia risk.

Why preoperative acuity predicts postoperative acuity in wavefront-guided LASIK.

PURPOSE: To critically evaluate the following clinical wisdom regarding custom (wavefront-guided) laser in situ keratomileusis (LASIK) that subjects with better-than-average best-corrected visual acuity (BCVA) before surgery have a greater risk of losing BCVA postoperatively than do subjects with worse-than-average BCVA before surgery. METHODS: High contrast BCVA was measured once before and 3 months after custom LASIK in one eye of 79 subjects. Preoperative spherical equivalent refractive error ranged between -1.00 and -10.38 D. The sample was divided into one of two subsamples: eyes that had better-than-average preoperative BCVA (<-0.11 logMAR) and eyes that had average or worse-than-average preoperative BCVA (≥-0.11 logMAR). Controls were implemented for retinal magnification and for the statistical phenomenon of regression to the mean of the preoperative acuity measurement. RESULTS: On average, for the entire sample, moving the correction from the spectacle plane to the corneal plane increased letter acuity 4.7% (1 letter, 0.02 logMAR). For each subsample, the percentage regression to the mean was 57.24%. After correcting for magnification effects and regression to the mean, eyes with better-than-average preoperative acuity had a small but significant gain in acuity (∼1 letter, p = 0.040) that was nearly identical to the gain for eyes with worse-than-average preoperative acuity (∼1.5 letters, p = 0.002). CONCLUSIONS: Custom LASIK produced a statistically significant gain in visual acuity after correction for magnification effects. Dividing the sample into two subsamples based on preoperative acuity confirmed the common clinical observation that eyes with better-than-average acuity tend to remain the same or lose acuity, whereas eyes with worse-than-average acuity tend to gain acuity. However, when only one acuity measurement is taken at a single time point and the sample is subsampled nonrandomly, this clinical observation is due to a statistical artifact (regression to the mean) and is not attributable to the surgery.

Comparison of night driving performance after wavefront-guided and conventional LASIK for moderate myopia.

PURPOSE: To compare preoperative and postoperative changes in simulated night driving performance after wavefront-guided (wLASIK) and conventional LASIK (cLASIK) for the treatment of moderate myopia. DESIGN: Retrospective, comparative study. PARTICIPANTS: All eyes of subjects with a preoperative manifest spherical equivalent (MSE) between -4.50 and -6.00 who underwent night driving simulator (NDS) testing from 2 clinical trials were entered into the study. This comprised 38 cLASIK patients (62 eyes; mean -5.46 diopters [D] MSE) and 21 wLASIK patients (36 eyes, mean -5.20 D MSE). METHODS: Patients' records were reviewed from 2 LASIK clinical trials that had similar enrollment criteria. One trial treated patients with conventional LASIK using a bladed microkeratome (cLASIK) and the other treated with a wavefront-guided profile using a femtosecond laser (wLASIK). In both trials, patients with moderate myopia were asked to participate in NDS testing. MAIN OUTCOME MEASURES: The detection and identification distances of road hazards were measured with and without a glare source before and 6 months after LASIK. Each eye was tested independently in best-corrected trial frames by a masked operator. RESULTS: In every category, there was a mean reduction in the preoperative to postoperative NDS performance after cLASIK (mean change, -21.3 to -27.9 ft, -6.5 to -8.5 m; 95% confidence interval [CI], -12.0 to -41.3 ft, -3.7 to -12.6 m); there was a corresponding mean improvement after wLASIK (mean change +15.0 to +29.1 ft, +4.6 to +8.9 m; 95% CI, +8.3 to +41.5 ft, +2.5 to +12.6 m). Significant differences between cLASIK and wLASIK NDS performance was observed in every category (P<0.;01, Tukey's honest significant difference for unequal numbers). A clinical relevant loss of NDS performance (>0.5 seconds) was observed in 32% to 38% of cLASIK eyes for all tasks, whereas only 0% to 3% of eyes had this loss after wLASIK. Between 2% and 7% of cLASIK eyes and 11% and 31% of eyes had a significant postoperative improvement in NDS performance in every task. CONCLUSIONS: Wavefront-guided LASIK to correct myopia combined with a femtosecond laser flap significantly improved mean night driving visual performance and was significantly better than cLASIK using a mechanical keratome.