TY  - JOUR
AB  - 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.
AU  - Luft, N.*
AU  - Mohr, N.*
AU  - Spiegel, E.
AU  - Marchi, H.
AU  - Siedlecki, J.*
AU  - Harrant, L.*
AU  - Mayer, W.J.*
AU  - Dirisamer, M.*
AU  - Priglinger, S.G.*
C1  - 68891
C2  - 53747
CY  - 530 Walnut Street, Ste 850, Philadelphia, Pa 19106 Usa
SP  - 252–259
TI  - Optimizing refractive outcomes of SMILE: Artificial intelligence versus conventional state-of-the-art nomograms.
JO  - Curr. Eye Res.
VL  - 49
IS  - 3
PB  - Taylor & Francis Inc
PY  - 2024
SN  - 0271-3683
ER  - 

TY  - JOUR
AB  - Purpose: Measurement of the exact intraocular pressure (IOP) is essential in glaucoma diagnosis and follow-up, thus all therapeutic options affect IOP in order to win sighted lifetime. As it is known that corneal properties of glaucoma patients differ from normal subjects, the present study aimed to investigate the influence of CCT on rebound tonometry (ICT, ICare Pro) in glaucoma and ocular hypertension patients in dependency of age additionally considering different times of day. Methods: Three hundred sixty-two eyes of 190 subjects were included: 339 open-angle glaucoma and 23 ocular hypertension. IOP was measured at 5 different times of day (6 a.m., 12 a.m., 4 p.m., 9 p.m., and 0 p.m.) by Goldmann applanation tonometry (GAT) and Icare Pro rebound tonometry in a sitting position. Central corneal thickness was measured by central ultrasonic pachymetry (Pachymeter SP-100). Δ ICT was calculated as the difference of GAT, corrected according to age and CCT, and ICT, respectively at each time point. Results: All different GAT time points data correlated significantly (p < .05) with ICT time points. An age effect was observed on overall ICT (p = .02). A decrease of ICT was observed with increasing age. The within differences among ICT repeated measurements were significant as well. Additionally, repeated means of Δ ICT correlated significantly with age and CCT. Intercepts and coefficients were offered for each time point, respectively. GLM model yielded a relation between MD (dependent variable) and age together with CCT (age: p < .0001) and (CCT: p = .043). Conclusions: IOP measurements with ICare Pro were shown to be dependent on age, CCT and time of day in glaucoma and ocular hypertension patients. Thus, aging, corneal biomechanical properties and circadian rhythms should be taken into consideration when adjusting IOP.
AU  - Hohberger, B.*
AU  - Sommerfeld, C.*
AU  - Lucio, M.
AU  - Bergua, A.*
C1  - 57843
C2  - 48112
CY  - 530 Walnut Street, Ste 850, Philadelphia, Pa 19106 Usa
SP  - 668-674
TI  - ICare Pro: Age dependent effect of central corneal thickness on intraocular pressure in glaucoma and ocular hypertension patients.
JO  - Curr. Eye Res.
VL  - 45
IS  - 6
PB  - Taylor & Francis Inc
PY  - 2020
SN  - 0271-3683
ER  -