Dataset Information

Artificial intelligence-based nomogram for small-incision lenticule extraction.

ABSTRACT:

Background

Small-incision lenticule extraction (SMILE) is a surgical procedure for the refractive correction of myopia and astigmatism, which has been reported as safe and effective. However, over- and under-correction still occur after SMILE. The necessity of nomograms is emphasized to achieve optimal refractive results. Ophthalmologists diagnose nomograms by analyzing the preoperative refractive data with their individual knowledge which they accumulate over years of experience. Our aim was to predict the nomograms of sphere, cylinder, and astigmatism axis for SMILE accurately by applying machine learning algorithm.

Methods

We retrospectively analyzed the data of 3,034 eyes composed of four categorical features and 28 numerical features selected from 46 features. The multiple linear regression, decision tree, AdaBoost, XGBoost, and multi-layer perceptron were employed in developing the nomogram models for sphere, cylinder, and astigmatism axis. The scores of the root-mean-square error (RMSE) and accuracy were evaluated and compared. Subsequently, the feature importance of the best models was calculated.

Results

AdaBoost achieved the highest performance with RMSE of 0.1378, 0.1166, and 5.17 for the sphere, cylinder, and astigmatism axis, respectively. The accuracies of which error below 0.25 D for the sphere and cylinder nomograms and 25° for the astigmatism axis nomograms were 0.969, 0.976, and 0.994, respectively. The feature with the highest importance was preoperative manifest refraction for all the cases of nomograms. For the sphere and cylinder nomograms, the following highly important feature was the surgeon.

Conclusions

Among the diverse machine learning algorithms, AdaBoost exhibited the highest performance in the prediction of the sphere, cylinder, and astigmatism axis nomograms for SMILE. The study proved the feasibility of applying artificial intelligence (AI) to nomograms for SMILE. Also, it may enhance the quality of the surgical result of SMILE by providing assistance in nomograms and preventing the misdiagnosis in nomograms.

SUBMITTER: Park S

PROVIDER: S-EPMC8063457 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo quantitatively evaluate outcomes after small incision lenticule extraction (SMILE) combined with allogeneic intrastromal lenticule inlay for hyperopia with astigmatism.MethodsIt's a retrospective cohort study. Twenty-four eyes of 15 patients with more than 0.75 diopters (D) of astigmatism in hyperopic eyes were enrolled in this study. The hyperopic eye with astigmatism was first treated with SMILE to correct astigmatism; then a lenticule was extracted from a donor myopic eye and subsequently implanted into the hyperopic eye with astigmatism. Patients were examined preoperatively and 1 day, 1 week, 1,3 months and 1 year after surgery. The main outcome measures were the uncorrected and corrected distance visual acuity (UDVA and CDVA), uncorrected near visual acuity (UNVA), spherical equivalent (SE), corneal topography, anterior segment optical coherence topography (OCT) and ocular response analyzer (ORA) parameters: corneal hysteresis (CH) and corneal resistance factor (CRF). Repeated-measures analyses of variance (ANOVA) and post hoc tests were used to analyze data of different follow-up visits.ResultsThe mean preoperative cylinder was 1.95±1.04(D). The UDVA (from 0.37±0.23 to 0.09±0.09), UNVA (from 0.49±0.21 to 0.08±0.06), SE (from +7.42±3.12 to -0.75±0.79) and astigmatism (+1.95±1.04 to -0.65±0.63) postoperatively were obviously better than those before surgery. Five eyes (26.3%) gained one line of CDVA, and 3 eyes (15.8%) gained two lines of CDVA one year after surgery compared with preoperative levels. The average corneal curvature was changed from (43.19±4.37) D to (49.19±3.87) D one year after surgery. The anterior segment OCT images of corneas with lenticule inlays at each follow-up visit showed that the implanted lenticule was shaped like a crescent in the corneal stroma. The CH and CRF didn't change significantly after surgery (p = 0.189 and p = 0.107respectively).ConclusionsSMILE combined with intrastromal lenticule inlay can be used to correct high hyperopia with astigmatism with good safety, efficacy and reproducibility.

Project description:PurposeThis study aimed to evaluate the efficacy of small-incision lenticule extraction (SMILE) in improving vision and visual quality and correcting astigmatism for the treatment of high astigmatism.MethodsEligible studies and studies comparing the efficacy of SMILE with femtosecond laser-assisted laser in situ keratomileusis (FS-LASIK) or transepithelial photorefractive keratectomy (T-PRK) for high astigmatism (≥2.00 D) were identified in PubMed, Embase, and the Cochrane Central Register of Controlled Trials, searched from their inception to 29 May 2022. The references of all searched studies were checked as supplements. The risk of bias was evaluated for each eligible study. The literature was screened according to the inclusion and exclusion criteria, and relative data were extracted. Data were extracted and analyzed by ReviewManager 5.4. The primary outcome was post-operative uncorrected distance visual acuity (UDVA). The secondary outcomes included corneal aberrations and vector parameters. The weight mean difference (WMD) and their 95% confidence intervals (95% CI) were used to assess the strength of the association.ResultsA total of six studies including 380 astigmatism eyes were involved, with 211 high-astigmatism eyes and 31 low-astigmatism eyes undergoing SMILE surgery, 94 high-astigmatism eyes undergoing FS-LASIK surgery, and 44 high-astigmatism eyes undergoing T-PRK surgery. Compared with non-SMILE, SMILE induced more astigmatism (weighted mean difference [WMD] = -0.07, 95% CI [-0.12 to -0.02], P = 0.005) and fewer sphere aberrations (WMD = -0.12, 95% CI [-0.17 to -0.08], P < 0.00001). The post-operative UDVA, sphere, spherical equivalent (SE), and higher order aberrations in different surgeries were likewise equivalent. The difference vector and index of success were significantly higher, and the surgically induced astigmatism vector, correction index, and magnitude of error were significantly lower in SMILE.ConclusionThis meta-analysis suggests that SMILE, FS-LASIK, and T-PRK show excellent efficacy, predictability, and safety for myopia. SMILE exhibited less astigmatism refraction predictability and less surgically induced spherical aberrations. There may be more under-correction in SMILE. More randomized, prospective, and large sample-sized studies are needed to confirm these conclusions in the long term.