Optimizing Refractive Outcomes of SMILE: Artificial Intelligence versus Conventional State-of-the-Art Nomograms.

PURPOSE: AI (artificial intelligence)-based methodologies have become established tools for researchers and physicians in the entire field of ophthalmology. However, the potential of AI to optimize the refractive outcome of keratorefractive surgery by means of machine learning (ML)-based nomograms has not been exhausted yet. In this study, we wanted to comprehensively compare state-of-the-art conventional nomograms for Small-Incision-Lenticule-Extraction (SMILE) with a novel ML-based nomogram regarding both their spherical and astigmatic predictability. METHODS: A total of 1,342 eyes were analyzed for creation of three different nomograms based on a linear model (LM), a generalized additive mixed model (GAMM) and an artificial-neuronal-network (ANN), respectively. A total of 16 patient- and treatment-related features were included. Each model was trained by 895 eyes and validated by the remaining 447 eyes. Predictability was assessed by the difference between attempted and achieved change in spherical equivalent (SE) and the difference between target induced astigmatism (TIA) and surgically induced astigmatism (SIA). The root mean squared error (RMSE) of each model was computed as a measure of overall model performance. RESULTS: The RMSE of LM, GAMM and ANN were 0.355, 0.348 and 0.367 for the prediction of SE and 0.279, 0.278 and 0.290 for the astigmatic correction, respectively. By applying the created models, the theoretical yield of eyes within ±0.50 D of SE from target refraction improved from 82 to 83% (LM), 84% (GAMM) and 83% (ANN), respectively. Astigmatic outcomes showed an improvement of eyes within ±0.50 D from TIA from 90 to 93% (LM), 93% (GAMM) and 92% (ANN), respectively. Subjective manifest refraction was the single most influential covariate in all models. CONCLUSION: Machine learning endorsed the validity of state-of-the-art linear and non-linear SMILE nomograms. However, improving the accuracy of subjective manifest refraction seems warranted for optimizing ±0.50 D SE predictability beyond an apparent methodological 90% limit.

Determinants of Subjective Quality of Vision After Phakic Intraocular Lens Implantation.

PURPOSE: To evaluate postoperative subjective quality of vision in patients who underwent Implantable Collamer Lens (ICL) (STAAR Surgical) implantation for correction of myopia and to identify potential predictive parameters. METHODS: In this single-center cross-sectional study, a total of 162 eyes of 81 patients (58 women, 23 men) who underwent ICL implantation were analyzed. The Quality of Vision (QOV) questionnaire was used to assess patient-reported outcomes. Baseline characteristics (eg, age), treatment parameters (eg, surgical corrected refraction), and refractive (eg, residual refraction) and visual (eg, uncorrected distance visual acuity) outcomes were analyzed regarding their effect on QOV. RESULTS: Mean age was 33.3 ± 7.0 years (range: 21 to 51 years) and mean preoperative spherical equivalent was -8.42 ± 2.49 diopters (D) (range: -3.25 to -14.38 D). After a mean postoperative follow-up period of 19 ± 14 months (range: 6 to 54 months), the safety index score was 1.23 ± 0.21 and the efficacy index score was 1.17 ± 0.22. The mean QOV scores were 35.5 ± 11.3, 32.2 ± 11.1, and 23.3 ± 16.1 for frequency, severity, and bothersomeness, respectively. The most frequently experienced symptoms were halos (90.1%) and glare (66.7%). Halos appeared in 66.7% of the patients "occasionally" and 5 of them (6.2%) experienced them "very often." Only 1 patient (1.2%) classified halos as "very bothersome." Patients older than 36 years reported visual symptoms more frequently (P < .05) and showed higher bothersomeness scores (P = .01). CONCLUSIONS: Halos are the most commonly perceived long-term visual disturbance after myopic ICL implantation with a central hole. Visual symptoms can persist more than 6 months postoperatively, causing only minor disturbances in most cases. Older patients seem more prone to experiencing these symptoms. [J Refract Surg. 2022;38(5):280-287.].