Structural, blood flow and functional changes in the macular area and the expression of aqueous humor factors in myopia.

Objective: To compare the macular area parameters and aqueous humor factors between myopia and emmetropia. Methods: Convenience sampling was used to select patients who visited the Changzhi Aier Eye Hospital's department of ophthalmology from December 2018 to December 2022 as the study participants. They were divided into three groups according to whether they were diagnosed as mild myopia myopic, highly myopic or not as follows: the mild myopia group (60 cases, 108 eyes), the high myopia group (46 cases, 78 eyes) and the healthy emmetropia group (40 cases, 65 eyes). The differences in the macular integrity (MI) assessment, optical coherence tomography and optical coherence tomography angiography parameters and aqueous humor factors were compared between the three groups. Results: AL in high myopia group was the highest, and that in emmetropia group was the lowest. The BCVA of mild myopia group was the highest. The RS in the high myopia group were significantly lowest in the three groups (26.42 ± 1.04 vs. 28.34 ± 0.76 vs. 31.92 ± 0.77) (F = 5.374, p = 0.013). The 63% BCEA, 95% BCEA and MI in the high myopia group were significantly highest (p < 0.05). The mean RPE thickness, mean CT and mean RT in the high myopia group were lowest (p < 0.05). The blood flow density were lowest in the superficial fovea, paracentral fovea and different subdivisions of the paracentral fovea in the high myopia group (p < 0.05). The VEGF concentration in the aqueous humor of the high myopia group was lowest (25.62 ± 17.43 vs. 32.45 ± 24.67 vs. 64.37 ± 21.14) (F = 9.237, p < 0.001). The MMP-2 concentration was highest (483 ± 201.48 vs. 410 ± 142.37 vs. 386 ± 154.34) (F = 5.542, p = 0.018). The VEGF concentration in the aqueous humor factor was negatively correlated with the AL in the myopia group (r = -0.438, p = 0.002), the MMP-2 concentration was positively correlated with the AL (r = 0.484, p = 0.010). Conclusion: Patients with high myopia showed decreased retinal light sensitivity, fixation stability, superficial blood flow density and retinal thickness compared with people with emmetropia. A decreased VEGF concentration and increased MMP-2 concentration in the aqueous humor factor have potential associations with the development of high myopia.

Cost-effectiveness analysis of artificial intelligence-based diabetic retinopathy screening in rural China based on the Markov model.

This study assessed the cost-effectiveness of different diabetic retinopathy (DR) screening strategies in rural regions in China by using a Markov model to make health economic evaluations. In this study, we determined the structure of a Markov model according to the research objectives, which required parameters collected through field investigation and literature retrieval. After perfecting the model with parameters and assumptions, we developed a Markov decision analytic model according to the natural history of DR in TreeAge Pro 2011. For this model, we performed Markov cohort and cost-effectiveness analyses to simulate the probabilistic distributions of different developments in DR and the cumulative cost-effectiveness of artificial intelligence (AI)-based screening and ophthalmologist screening for DR in the rural population with diabetes mellitus (DM) in China. Additionally, a model-based health economic evaluation was performed by using quality-adjusted life years (QALYs) and incremental cost-effectiveness ratios. Last, one-way and probabilistic sensitivity analyses were performed to assess the stability of the results. From the perspective of the health system, compared with no screening, AI-based screening cost more (the incremental cost was 37,257.76 RMB (approximately 5,211.31 US dollars)), but the effect was better (the incremental utility was 0.33). Compared with AI-based screening, the cost of ophthalmologist screening was higher (the incremental cost was 14,886.76 RMB (approximately 2,070.19 US dollars)), and the effect was worse (the incremental utility was -0.31). Compared with no screening, the incremental cost-effectiveness ratio (ICER) of AI-based DR screening was 112,146.99 RMB (15,595.47 US dollars)/QALY, which was less than the threshold for the ICER (< 3 times the per capita gross domestic product (GDP), 217,341.00 RMB (30,224.03 US dollars)). Therefore, AI-based screening was cost-effective, which meant that the increased cost for each additional quality-adjusted life year was merited. Compared with no screening and ophthalmologist screening for DR, AI-based screening was the most cost-effective, which not only saved costs but also improved the quality of life of diabetes patients. Popularizing AI-based DR screening strategies in rural areas would be economically effective and feasible and can provide a scientific basis for the further formulation of early screening programs for diabetic retinopathy.

Clinical evaluation of AI-assisted screening for diabetic retinopathy in rural areas of midwest China.

BACKGROUND: Although numerous studies have described the application of artificial intelligence (AI) in diabetic retinopathy (DR) screening among diabetic populations, studies among populations in rural areas are rare. The purpose of this study was to evaluate the application value of an AI-based diagnostic system for DR screening in rural areas of midwest China. METHODS: In this diagnostic accuracy study, diabetes mellitus (DM) patients in the National Basic Public Health Information Systems of Licheng County and Lucheng County of Changzhi city from July to December 2020 were selected as the target population. A total of 7824 eyes of 3933 DM patients were enrolled in this screening; the patients included 1395 males and 2401 females, with an average age of 19-87 years (63±8.735 years). All fundus photographs were collected by a professional ophthalmologist under natural pupil conditions in a darkroom using the Zhiyuan Huitu fundus image AI analysis software EyeWisdom. The AI-based diagnostic system and ophthalmologists were tasked with diagnosing the photos independently, and the consistency rate, sensitivity and specificity of the two methods in diagnosing DR were calculated and compared. RESULTS: The prevalence rates of DR according to the ophthalmologist and AI diagnoses were 22.7% and 22.5%, respectively; the consistency rate was 81.6%. The sensitivity and specificity of the AI system relative to the ophthalmologists' grades were 81.2% (95% confidence interval [CI]: 80.3% 82.1%) and 94.3% (95% CI: 93.7% 94.8%), respectively. There was no significant difference in diagnostic outcomes between the methods (χ2 = 0.329, P = 0.566, P>0.05), and the AI-based diagnostic system had high consistency with the ophthalmologists' diagnostic results (κ = 0.752). CONCLUSION: Our research demonstrated that DR patients in rural area hospitals can be screened feasibly. Compared with that of the ophthalmologists, however, the accuracy of the AI system must be improved. The results of this study might lend support to the large-scale application of AI in DR screening among different populations.

Discovery of microRNA expression profiles involved in regulating TGF-ß2 expression in the tears of dry eye patients.

BACKGROUND: To date, the difference in microRNA expression profiles in tears of dry eye patients and healthy people has not been reported. In current study, we evaluated the significance of microRNAs and transforming growth factor beta2 (TGF-ß2) in distinguishing dry eye. METHODS: A total of 138 patients with dry eye from October 2017 to October 2018 were selected. During the same period, 138 healthy persons were collected. All patients were followed up for 12 months through outpatient, telephone or medical records and the time of corneal injury was recorded. RESULTS: Compared with healthy people, TGF-ß2 concentrations in dry eye patients were significantly decreased (P < 0.05). Array analysis, predictive software and dual-luciferase reporter assays showed that miR-450b-5p, miR-1283 and miR-3671 can target TGF-ß2 expression. Tear miR-450b-5p, miR-1283 and miR-3671 concentrations were significantly higher in dry eye patients than healthy people. A logistic regression model combining miR-450b-5p, miR-1283, miR-3671 and TGF-ß2 was performed. This model presented a high discriminating value (AUC: 0.907, 0.876-0.939, P < 0.001) than any single indicator, and the sensitivity and specificity were 77.7% and 92.7%, respectively. Compared with the low miR-450b-5p, low miR-1283, low miR-3671 and high TGF-ß2 groups, the high miR-450b-5p, high miR-1283, high miR-3671 and low TGF-ß2 groups had a significantly higher probability of corneal injury (TGF-ß2: χ2 = 5.762, P = 0.016; miR-450b-5p: χ2 = 13.267, P < 0.001; miR-1283: χ2 = 19.431, P < 0.001; miR-3671: χ2 = 8.131, P = 0.004). CONCLUSION: Current model combining tear miR-450b-5p, miR-1283, miR-3671 and TGF-ß2 had important values in the identification of dry eye and was of great value in evaluating the risk of corneal injury.

Comparison of machine learning tools for the prediction of AMD based on genetic, age, and diabetes-related variables in the Chinese population.

INTRODUCTION: Age-related macular degeneration (AMD) is the main cause of visual impairment and the most important cause of blindness in older people. However, there is currently no effective treatment for this disease, so it is necessary to establish a risk model to predict AMD development. METHODS: This study included a total of 202 subjects, comprising 82 AMD patients and 120 control subjects. Sixty-six single-nucleotide polymorphisms (SNPs) were identified using the MassArray assay. Considering 14 independent clinical variables as well as SNPs, four predictive models were established in the training set and evaluated by the confusion matrix, area under the receiver operating characteristic (ROC) curve (AUROC). The difference distributions of the 14 independent clinical features between the AMD and control groups were tested using the chi-squared test. Age and diabetes were adjusted using logistic regression analysis and the "genomic-control" method was used for multiple testing correction. RESULTS: Three SNPs (rs10490924, OR = 1.686, genomic-control corrected p-value (GC) = 0.030; rs2338104, OR = 1.794, GC = 0.025 and rs1864163, OR = 2.125, GC = 0.038) were significant risk factors for AMD development. In the training set, four models obtained AUROC values above 0.72. CONCLUSIONS: We believe machine learning tools will be useful for the early prediction of AMD and for the development of relevant intervention strategies.