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

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.

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.

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.

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.