The aim is to develop a machine learning prediction model for the diagnosis of glaucoma and an explanation system for a specific prediction. Clinical data of the patients based on a visual field test, a retinal nerve fiber layer optical coherence tomography (RNFL OCT) test, a general examination including an intraocular pressure (IOP) measurement, and fundus photography were provided for the feature selection process. Five selected features (variables) were used to develop a machine learning prediction model. The support vector machine, C5.0, random forest, and XGboost algorithms were tested for the prediction model. The performance of the prediction models was tested with 10-fold cross-validation. Statistical charts, such as gauge, radar, and Shapley Additive Explanations (SHAP), were used to explain the prediction case. All four models achieved similarly high diagnostic performance, with accuracy values ranging from 0.903 to 0.947. The XGboost model is the best model with an accuracy of 0.947, sensitivity of 0.941, specificity of 0.950, and AUC of 0.945. Three statistical charts were established to explain the prediction based on the characteristics of the XGboost model. Higher diagnostic performance was achieved with the XGboost model. These three statistical charts can help us understand why the machine learning model produces a specific prediction result. This may be the first attempt to apply “explainable artificial intelligence” to eye disease diagnosis.

Polyhexamethylene guanidine phosphate (PHMG-p), a widely used disinfectant component in household humidifiers, has been implicated in various health issues, including pulmonary toxicity. Many people use humidifiers to improve dry eye disease (DED). The current study was performed to elucidate the effect of PHMG-p on eye dryness in a rat model using metabolomics. Male Sprague Dawley rats were exposed to PHMG-p (0.1% and 0.3%) following a previously established DED induction model using scopolamine hydrobromide and desiccation stress. Ocular surface damage was assessed using corneal fluorescein staining, tear volume measurement, and tear break-up time (TBUT). Plasma and urine samples were analyzed using ¹H-NMR-based metabolomics to identify metabolic alterations associated with PHMG-P-p exposure and DED pathogenesis. PHMG-p exposure exacerbated DED symptoms, as evidenced by a significant reduction in tear volume, shorter TBUT, and increased corneal damage compared to the control group. Metabolomic profiling identified distinct metabolic changes in PHMG-p-exposed groups, including alterations in glutamate, glycine, citrate, and succinate metabolism. These metabolic changes correlated with increased levels of inflammatory cytokines such as IL-1β, IL-6, and TNF-α in the corneal and lacrimal gland tissues. Our findings suggest that PHMG-p exposure contributes to DED pathophysiology by inducing metabolic disturbances and inflammatory responses in the ocular surface. This study highlights the need for further investigation into the potential risks of PHMG-p exposure on ocular health and provides novel insights into the metabolic underpinnings of DED.

Various machine-learning schemes have been proposed to diagnose glaucoma. They can classify subjects into ‘normal’ or ‘glaucoma’-positive but cannot determine the severity of the latter. To complement this, researchers have proposed statistical indices for glaucoma risk. However, they are based on a single examination indicator and do not reflect the total severity of glaucoma progression. In this study, we propose an integrated glaucoma risk index (I-GRI) based on the visual field (VF) test, optical coherence tomography (OCT), and intraocular pressure (IOP) test. We extracted important features from the examination data using a machine learning scheme and integrated them into a single measure using a mathematical equation. The proposed index produces a value between 0 and 1; the higher the risk index value, the greater the risk/severity of glaucoma. In the sanity test using test cases, the I-GRI showed a balanced distribution in both glaucoma and normal cases. When we classified glaucoma and normal cases using the I-GRI, we obtained a misclassification rate of 0.07 (7%). The proposed index is useful for diagnosing glaucoma and for detecting its progression.

Purpose: Tisochrysis lutea is a marine microalga known for its anticancer and antioxidant properties. This study aimed to investigate the efficacy and safety of T. lutea in adults with dry eye symptoms.Methods: One hundred participants with dry eye symptoms were enrolled and divided into two groups: one received T. lutea powder (test group), and the other received control food (placebo, control group) for 12 weeks. Subsequently, the measurements of ocular surface disease index (OSDI), tear secretion (Schirmer’s test), tear break-up time (TBUT), corneoconjunctival staining, and safety assessments were compared between the test and control groups.Results: In terms of the OSDI score, the value for the test group decreased by 6.51 points after 12 weeks of T. lutea powder intake, compared with baseline, whereas that in the control group decreased by 2.88 points, demonstrating a significant difference between the two groups (p = 0.002). The results of Schirmer's test also showed significant improvements: in the test group, the result for the right eye increased by 1.33 ± 3.71 after 12 weeks (p = 0.020), and that for the left eye increased by 1.93 ± 3.33 (p = 0.0003). However, no significant increases in the results were observed in the control group. Additionally, TBUT showed a significant increase from baseline in the right eye of the test group after 6 weeks of T. lutea powder intake (p = 0.043).Conclusions: After 12 weeks of consumption in the powdered form, T. lutea improved the symptoms of dry eye and increased tear production. Therefore, T. lutea can be used as an eye supplement for adults with dry eye symptoms.

Purpose: To compare ocular biometry measurements obtained using optical low-coherence reflectometry (OLCR), swept-source optical coherence tomography (SS-OCT), and A-scan devices in eyes with cataracts and to evaluate prediction error based on the difference between the predicted refraction and the postoperative spherical equivalent.Methods: This study included 40 eyes from 31 patients who underwent cataract surgery. Keratometry, axial length, and anterior chamber depth were measured using the HBM-1®, IOL Master 700®, PacScan 300A®, and KR-1® autokeratorefractometer. Intraocular lens (IOL) power was calculated using the Barrett Universal II formula. Mean absolute prediction error, defined as the absolute difference between the predicted refraction and the postoperative spherical equivalent measured using an autorefractor 4 ± 2 weeks after cataract surgery, was compared between the HBM-1® and IOL Master 700®.Results: Mean keratometry differed significantly among the HBM-1®, IOL Master 700®, and KR-1® autokeratorefractometer (p < 0.01). Mean axial length did not differ significantly among the HBM-1®, IOL Master 700®, and PacScan 300A® (p = 0.29). Mean anterior chamber depth differed significantly among the HBM-1®, IOL Master 700®, and PacScan 300A® (p < 0.01). Mean absolute prediction error did not differ significantly between the HBM-1® and IOL Master 700® (p = 0.756).Conclusions: Keratometry and anterior chamber depth differed significantly among the devices, whereas axial length and mean absolute prediction error did not differ significantly. Differences in corneal curvature measurements among devices should be considered when planning toric IOL implantation.

Ultraviolet (UV) radiation, a form of non-ionizing radiation, poses a significant threat to ocular health, and is classified by wavelength into UVA, UVB, and UVC, each category is absorbed by different eye tissues, leading to acute and chronic diseases. This review analyzes the toxic mechanisms of each UV wavelength on the cornea, lens, and retina and examines the pathological effects of major diseases, such as photokeratitis, cataracts, pterygium, and age-related macular degeneration, based on recent research. Furthermore, this study aimed to provide scientific evidence for preventing UV-induced eye damage by outlining the role of sunglasses in effective UV protection and presenting the criteria for their proper selection.