Objectives: This study aimed to use deep learning to identify glaucoma and normal eyes in groups with high myopia using fundus photographs. Methods: Patients who visited Tri-Services General Hospital from 1 November 2018 to 31 October 2022 were retrospectively reviewed. Patients with high myopia (spherical equivalent refraction of ≤−6.0 D) were included in the current analysis. Meanwhile, patients with pathological myopia were excluded. The participants were then divided into the high myopia group and high myopia glaucoma group. We used two classification models with the convolutional block attention module (CBAM), an attention mechanism module that enhances the performance of convolutional neural networks (CNNs), to investigate glaucoma cases. The learning data of this experiment were evaluated through fivefold cross-validation. The images were categorized into training, validation, and test sets in a ratio of 6:2:2. Grad-CAM visual visualization improved the interpretability of the CNN results. The performance indicators for evaluating the model include the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results: A total of 3088 fundus photographs were used for the deep-learning model, including 1540 and 1548 fundus photographs for the high myopia glaucoma and high myopia groups, respectively. The average refractive power of the high myopia glaucoma group and the high myopia group were −8.83 ± 2.9 D and −8.73 ± 2.6 D, respectively (p = 0.30). Based on a fivefold cross-validation assessment, the ConvNeXt_Base+CBAM architecture had the best performance, with an AUC of 0.894, accuracy of 82.16%, sensitivity of 81.04%, specificity of 83.27%, and F1 score of 81.92%. Conclusions: Glaucoma in individuals with high myopia was identified from their fundus photographs.

Age-related macular degeneration (AMD) is a vision-threatening age-associated disease. The retinal pigment epithelial (RPE) cells phagocytose and digest photoreceptor outer segment (POS). Incomplete digestion of POS leads to lipofuscin accumulation, which contributes to the pathology of the AMD. Autophagy could help reduce the amount of lipofuscin accumulation. In the present study, we evaluated the effects of glucosamine (GlcN), a natural supplement, on the induction of autophagy and POS-derived lipofuscin-like autofluorescence (LLAF) in ARPE-19 cells in vitro, and investigated the potential molecular pathway involved. Our results revealed that GlcN had no effect on phagocytosis of POS at the lower doses. GlcN treatment induced autophagy in cells. GlcN decreased the LLAF in native POS-treated cells, whereas malondialdehyde or 4-hydroxynonenal-modified POS attenuated this effect. 3-Methyladenine inhibited GlcN-induced autophagy and attenuated the effect of GlcN on the decrease of the native POS-derived LLAF. Furthermore, GlcN induced the phosphorylation of AMP-activated protein kinase (AMPK) and inhibited the phosphorylation of mammalian target of rapamycin (mTOR), whereas Compound C inhibited these effects of GlcN. Altogether, these results suggest that GlcN decreased the native POS-derived LLAF through induction of autophagy, at least in part, by the AMPK–mTOR pathway. This mechanism has potential for the preventive treatment of lipofuscin-related retinal degeneration such as AMD.

Purpose: Diabetic macular edema (DME) is a common cause of vision impairment and blindness in patients with diabetes. However, vision loss can be prevented by regular eye examinations during primary care. This study aimed to design an artificial intelligence (AI) system to facilitate ophthalmology referrals by physicians.Methods: We developed an end-to-end deep fusion model for DME classification and hard exudate (HE) detection. Based on the architecture of fusion model, we also applied a dual model which included an independent classifier and object detector to perform these two tasks separately. We used 35,001 annotated fundus images from three hospitals between 2007 and 2018 in Taiwan to create a private dataset. The Private dataset, Messidor-1 and Messidor-2 were used to assess the performance of the fusion model for DME classification and HE detection. A second object detector was trained to identify anatomical landmarks (optic disc and macula). We integrated the fusion model and the anatomical landmark detector, and evaluated their performance on an edge device, a device with limited compute resources.Results: For DME classification of our private testing dataset, Messidor-1 and Messidor-2, the area under the receiver operating characteristic curve (AUC) for the fusion model had values of 98.1, 95.2, and 95.8%, the sensitivities were 96.4, 88.7, and 87.4%, the specificities were 90.1, 90.2, and 90.2%, and the accuracies were 90.8, 90.0, and 89.9%, respectively. In addition, the AUC was not significantly different for the fusion and dual models for the three datasets (p = 0.743, 0.942, and 0.114, respectively). For HE detection, the fusion model achieved a sensitivity of 79.5%, a specificity of 87.7%, and an accuracy of 86.3% using our private testing dataset. The sensitivity of the fusion model was higher than that of the dual model (p = 0.048). For optic disc and macula detection, the second object detector achieved accuracies of 98.4% (optic disc) and 99.3% (macula). The fusion model and the anatomical landmark detector can be deployed on a portable edge device.Conclusion: This portable AI system exhibited excellent performance for the classification of DME, and the visualization of HE and anatomical locations. It facilitates interpretability and can serve as a clinical reference for physicians. Clinically, this system could be applied to diabetic eye screening to improve the interpretation of fundus imaging in patients with DME.

We conducted a retrospective group study to evaluate the potential systemic risk factors for major postoperative complications of cataract surgery. Individuals diagnosed with (n = 2046) and without (n = 8184) serious complications after cataract surgery were matched 1:4 for age, sex, and index date obtained using Taiwan’s National Health Insurance Research Database. The outcome was defined as at least one new inpatient or outpatient diagnosis of systemic disease one year before the index date. The effect of demographic data on postoperative complications was also analyzed in the multivariable model. Data were analyzed using univariate and multivariate conditional logistic regression models to calculate odds ratios (ORs) and 95% confidence intervals of the risk of developing serious complications. After the entire study interval, the major postoperative complications of cataract surgery were associated with the following systemic diseases: hypertension (adjusted OR (aOR) = 2.329, p < 0.001), diabetes mellitus (aOR = 2.818, p < 0.001), hyperlipidemia (aOR = 1.702, p < 0.001), congestive heart failure (aOR = 2.891, p < 0.001), rheumatic disease (aOR = 1.965, p < 0.001), and kidney disease needing hemodialysis (aOR = 2.942, p < 0.001). Additionally, demographic data including old age, higher urbanization level, higher level of care, and more frequent inpatient department visits were associated with a higher rate of postoperative complications. In conclusion, metabolic syndrome, chronic heart failure, end-stage renal disease, rheumatic disease, older age, and frequent inpatient department visits are correlated with the development of severe postoperative complications of cataract surgery. Therefore, cataract surgery patients should be informed about a higher possibility of postoperative complications.

Background: Ankylosing spondylitis (AS) is a chronic inflammatory disease. Excess cardiovascular risks were well recognized in patients with AS and were attributed to prolonged systemic inflammation. Uveitis is one of the most common extra-articular symptoms of AS and is also considered an indicator of systemic inflammation. This study aimed to investigate whether uveitis was a risk factor for developing acute myocardial infarction (AMI) in patients with AS using the National Health Insurance Research Database (NHIRD).Methods: Data were collected from the NHIRD over a fifteen-year period. Variables were analyzed using the Pearson chi-square test and Fisher’s exact test. Risk factors for the occurrence of AMI were examined by calculating hazard ratio. Kaplan-Meier analysis was performed to compare the cumulative incidence of AMI in the uveitis and non-uveitis cohorts.Results: A total of 5905 patients with AS were enrolled, including 1181 patients with uveitis (20%) and 4724 patients without uveitis (80%). The Kaplan–Meier method with the log-rank test showed that the uveitis group had a significantly higher cumulative hazard for patients with AMI than the non-uveitis group (p < 0.001). The adjusted hazard ratio (aHR) of AMI was higher in the uveitis group than in the non-uveitis group (aHR = 1.653, p < 0.001). Stratified analysis revealed that patients with uveitis had an increased risk of developing AMI regardless of their sex (male/female aHR = 1.688/1.608, p < 0.001). Patients with uveitis in all age groups were independently associated with an increased risk of developing AMI compared to those without uveitis (20–39 years/40–59 years/≥ 60 years, aHR = 1.550, 1.579, 3.240, p < 0.001). Patients with uveitis had a higher probability of developing AMI regardless of comorbidities. Uveitis patients with comorbidities had a higher risk of developing AMI compared to uveitis patients without comorbidities.Conclusion: Uveitis is a significant risk factor for developing AMI in patients with AS. Physicians should be aware of the potential cardiovascular risk in AS patients with uveitis, especially simultaneously with other traditional risk factors of AMI. Further prospective studies are needed to elucidate the underlying mechanism between uveitis and AMI in patients with AS.

Background: Uveitis, a sight-threatening ocular inflammatory state, is associated with autoimmune diseases and systemic inflammation. This prolonged systemic inflammation may cause plaque formation in coronary arteries, subsequently resulting in acute coronary syndrome (ACS).Methods: This retrospective, population-based study (15-year period) used the Longitudinal Health Insurance Database based on the National Health Insurance Research Database in Taiwan. Chi-square and Student’s t-tests were used to examine differences between the study and comparison cohorts for categorical and continuous variables, respectively. Fine and Gray’s competing risk model was used to determine the hazard ratio of the risk of ACS. Furthermore, the cumulative risk of ACS was determined using Kaplan-Meier analysis.Results: A total of 1,111 patients with AS and uveitis were enrolled in this study cohort, and 4,444 patients with AS without uveitis were enrolled in the comparison cohort. After adjustment for age, sex, and comorbidities, patients with AS and uveitis demonstrated an increased risk of ACS compared to those without uveitis (adjusted hazard ratio: 1.675, p<0.001). In addition, Kaplan-Meier analysis revealed that patients with AS and uveitis had a significantly higher risk of ACS than those without uveitis (p<0.001). Age, diabetes mellitus, hypertension, hyperlipidemia, chronic obstructive pulmonary disease, asthma, and systemic steroids were significant risk factors for ACS. Both anterior uveitis and posterior segment involvement were associated with an increased risk of ACS in patients with AS. All-cause mortality was higher in the uveitis group (9.81%) than in the non-uveitis group (8.10%) (p=0.015).Conclusion: Our analysis revealed that uveitis could potentially be a predictor of ACS in patients with AS. However, further prospective controlled studies are required to assess the association between uveitis and ACS in patients with AS.