Background: In recent years, with the rapid development of machine learning (ML), it has gained widespread attention from researchers in clinical practice. ML models appear to demonstrate promising accuracy in the diagnosis of complex diseases, as well as in predicting disease progression and prognosis. Some studies have applied it to ophthalmology, primarily for the diagnosis of pathologic myopia and high myopia-associated glaucoma, as well as for predicting the progression of high myopia. ML-based detection still requires evidence-based validation to prove its accuracy and feasibility. Objective: This study aims to discern the performance of ML methods in detecting high myopia and pathologic myopia in clinical practice, thereby providing evidence-based support for the future development and refinement of intelligent diagnostic or predictive tools. Methods: PubMed, Cochrane, Embase, and Web of Science were thoroughly retrieved up to September 3, 2023. The prediction model risk of bias assessment tool was leveraged to appraise the risk of bias in the eligible studies. The meta-analysis was implemented using a bivariate mixed-effects model. In the validation set, subgroup analyses were conducted based on the ML target events (diagnosis and prediction of high myopia and diagnosis of pathological myopia and high myopia-associated glaucoma) and modeling methods. Results: This study ultimately included 45 studies, of which 32 were used for quantitative meta-analysis. The meta-analysis results unveiled that for the diagnosis of pathologic myopia, the summary receiver operating characteristic (SROC), sensitivity, and specificity of ML were 0.97 (95% CI 0.95-0.98), 0.91 (95% CI 0.89-0.92), and 0.95 (95% CI 0.94-0.97), respectively. Specifically, deep learning (DL) showed an SROC of 0.97 (95% CI 0.95-0.98), sensitivity of 0.92 (95% CI 0.90-0.93), and specificity of 0.96 (95% CI 0.95-0.97), while conventional ML (non-DL) showed an SROC of 0.86 (95% CI 0.75-0.92), sensitivity of 0.77 (95% CI 0.69-0.84), and specificity of 0.85 (95% CI 0.75-0.92). For the diagnosis and prediction of high myopia, the SROC, sensitivity, and specificity of ML were 0.98 (95% CI 0.96-0.99), 0.94 (95% CI 0.90-0.96), and 0.94 (95% CI 0.88-0.97), respectively. For the diagnosis of high myopia-associated glaucoma, the SROC, sensitivity, and specificity of ML were 0.96 (95% CI 0.94-0.97), 0.92 (95% CI 0.85-0.96), and 0.88 (95% CI 0.67-0.96), respectively. Conclusions: ML demonstrated highly promising accuracy in diagnosing high myopia and pathologic myopia. Moreover, based on the limited evidence available, we also found that ML appeared to have favorable accuracy in predicting the risk of developing high myopia in the future. DL can be used as a potential method for intelligent image processing and intelligent recognition, and intelligent examination tools can be developed in subsequent research to provide help for areas where medical resources are scarce. Trial Registration: PROSPERO CRD42023470820; https://tinyurl.com/2xexp738

Purpose Pathological myopia causes irreversible damage, yet early changes in high myopia patients with tessellated fundus are often overlooked. The identification of such patients relies on OCT and fundus imaging, but early detection is difficult. Therefore, we developed and validated machine learning models using lifestyle and clinical parameters. Methods Cross-sectional data were collected from high myopia patients with tessellated fundus at the First Affiliated Hospital of Guangxi Medical University (May 2023–July 2024). Data were split (7:3) into training and test sets. Five-fold cross-validation within the training set was used during LASSO regression to select key variables. Machine learning models, including Random Forest, Support Vector Machine, Linear Support Vector Machine, and XGBoost, were constructed. Model performance was evaluated by AUC, sensitivity, specificity, calibration curves, and decision curve analysis. Results 529 eyes were analyzed. Key modeling variables included education level, daily iPad usage time, daily reading time, daily reading time while lying down, lamp light source, daily outdoor activity time, spherical equivalent, axial length, corneal thickness, lens thickness, extent of PPA involvement, maximum radius of PPA, horizontal disc diameter, and disc tilt ratio. In the test set, the AUCs of the Random Forest, Support Vector Machine, Linear Support Vector Machine, and XGBoost models were 0.834, 0.815, 0.765, and 0.839, respectively. Both the training and test sets demonstrated good calibration and high clinical applicability. Conclusions Machine learning models using lifestyle and clinical parameters can effectively screen for early pathological changes in high myopia with tessellated fundus, offering an auxiliary tool for clinicians.

Small-incision lenticule extraction (SMILE) is a widely used procedure for correcting myopia and myopic astigmatism. However, variability in refractive outcomes, particularly astigmatic correction, remains a concern. This study aimed to compare visual, refractive, and optical outcomes of SMILE planned with a VISULYZE-generated nomogram versus a conventional nomogram in patients with moderate myopia and astigmatism. This retrospective comparative study included 120 eyes from 60 consecutive patients. Eyes were allocated to groups at the eye level, with both eyes from the same patient potentially included and independently assigned to either the VISULYZE-generated nomogram group (60 eyes) or the conventional nomogram group (60 eyes). Visual acuity, refractive outcomes, astigmatic axis deviation, and higher-order aberrations (HOAs) were evaluated preoperatively and at 3 months postoperatively. Statistical analyses accounted for inter-eye correlation using mixed-effects models to properly consider the independence of observations. Preoperative demographic and refractive characteristics were comparable between groups. At 3 months postoperatively, a higher proportion of eyes in the VISULYZE-generated nomogram group achieved uncorrected distance visual acuity (UDVA) of 20/20 or better than in the conventional group. With respect to astigmatic axis deviation and residual astigmatism, the VISULYZE group showed numerical trends toward closer alignment, although differences did not reach statistical significance. Postoperative increases in total HOAs and coma were observed in both groups, with smaller increases in the VISULYZE group. Changes in spherical aberration and trefoil were minimal and comparable between groups. SMILE planned with a VISULYZE-generated nomogram was associated with differences in early visual, refractive, and optical outcomes compared with conventional nomogram planning. VISULYZE-generated nomogram group has lower HOAS. Both groups' total HOAs and coma increases postoperatively, with smaller increases in the VISULYZE group.

Purpose: Early identification of pathological changes in high myopia (HM) with tessellated fundus (TF) remains challenging. To address this, a diagnostic nomogram was developed and validated to aid clinical screening of pathologic myopia (PM) in HM patients with TF. Patients and Methods: A cross-sectional study was performed at The First Affiliated Hospital of Guangxi Medical University between May 10, 2023, and March 31, 2024. Patients with HM, defined as a spherical refractive error of ≤ − 6.0 D or an axial length of ≥ 26.5 mm, who presented with TF were enrolled. The collected clinical data were randomly divided into training and validation sets at a 7:3 ratio. A diagnostic nomogram was constructed from independent predictive factors. Its discrimination, calibration, and clinical utility were assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Results: Data from 418 eyes with TF were included in this study. Independent predictors for PM, in descending order of association, were axial length, optic disc tilt ratio, spherical equivalent, education level, and extent of peripapillary atrophy. The nomogram demonstrated robust performance in both sets. In the training set, the area under the ROC curve (AUC) was 0.851 (95% CI: 0.808– 0.895), with a sensitivity of 0.775 and a specificity of 0.736. In the validation set, the AUC was 0.827 (95% CI: 0.755– 0.900), with a sensitivity of 0.773 and a specificity of 0.700. Conclusion: This simple predictive model, developed and validated using common interpretable clinical and fundus imaging features, serves as a valuable tool for screening PM in HM patients with TF.

Objective: This cross-sectional study, based on the National Health and Nutrition Examination Survey (NHANES), investigated the association between the serum albumin-to-globulin (A/G) ratio and diabetic retinopathy (DR). Methods: We used data from the NHANES 2001-2020 and included adult participants with diabetes who completed standardized questionnaires, physical examinations, and laboratory assessments. Multivariate logistic regression models were used to evaluate the association between serum A/G ratio and DR. Restricted cubic spline (RCS) analysis was used to assess potential nonlinear relationships. Subgroup and interaction analyses were conducted to examine the robustness of the results. Receiver operating characteristic (ROC) curves were used to evaluate the predictive performance of the A/G ratio. Results: Among 5,868 adult participants with diabetes, 1,268 had DR. After full adjustment, the results showed that a higher A/G ratio was significantly associated with lower odds of DR [OR (95% CI): 0.66 (0.47,0.93)]. The association was linear (P for nonlinear = 0.276) and consistent across most subgroups, with a significant interaction for cardiovascular disease (P for interaction = 0.019). The A/G ratio showed limited discriminatory ability for DR (AUC = 0.632). Conclusions: A higher serum A/G ratio is associated with lower odds of DR. The findings suggest that the serum A/G ratio may reflect inflammatory and metabolic conditions associated with DR. Further prospective studies are needed to verify these findings and explore the underlying mechanisms.