Diabetic macular edema (DME) is a significant complication of diabetes that impacts the eye and is a primary contributor to vision loss in individuals with diabetes. Early control of the related risk factors is crucial to reduce the incidence of DME. Artificial intelligence (AI) clinical decision-making tools can construct disease prediction models to aid in the clinical screening of the high-risk population for early disease intervention. However, conventional machine learning and data mining techniques have limitations in predicting diseases when dealing with missing feature values. To solve this problem, a knowledge graph displays the connection relationships of multi-source and multi-domain data in the form of a semantic network to enable cross-domain modeling and queries. This approach can facilitate the personalized prediction of diseases using any number of known feature data. In this study, we proposed an improved correlation enhancement algorithm based on knowledge graph reasoning to comprehensively evaluate the factors that influence DME to achieve disease prediction. We constructed a knowledge graph based on Neo4j by preprocessing the collected clinical data and analyzing the statistical rules. Based on reasoning using the statistical rules of the knowledge graph, we used the correlation enhancement coefficient and generalized closeness degree method to enhance the model. Meanwhile, we analyzed and verified these models’ results using link prediction evaluation indicators. The disease prediction model proposed in this study achieved a precision rate of 86.21%, which is more accurate and efficient in predicting DME. Furthermore, the clinical decision support system developed using this model can facilitate personalized disease risk prediction, making it convenient for the clinical screening of a high-risk population and early disease intervention.
The objective of this study was to characterize the choroidal morphology and vasculature in pachychoroid diseases (PCD). A total of 49 eyes with polypoidal choroidal vasculopathy (PCV), 43 eyes with neovascular age-related macular degeneration (nAMD), and 50 eyes with central serous chorioretinopathy (CSC), along with 80 healthy eyes, were enrolled in this nested case-control study. The swept-source optical coherent tomography (OCT), OCT angiography, and En face images were quantitatively analyzed. Multivariate logistic regression models showed that older age and increased vessel density (VD) in the choriocapillaris (CC) layer were independent risk factors for both PCV (page < 0.001, pVD = 0.004), and nAMD (page < 0.001, pVD = 0.005). Decreased VD in the Sattler’s layer was an independent risk factor for PCV (p = 0.014). Increased VD in the Haller’s layer was an independent risk factor for CSC (p = 0.001). The proportion of the diffuse type of collateral circulation in the Sattler’ layer in CSC group was significantly higher than in the other three groups (p < 0.001). We concluded that the involvement of the blood flow in the CC, Haller’s, and Sattler’s layers are differently affected in CSC, nAMD, and PCV eyes, indicating the different pathological mechanism underlying the phenotype of PCD. The age-dependent establishment of collateral circulation in the Sattler’s layer may play a compensatory role regarding ischemic injury in the development of PCD.
Background: Superficial temporal artery (STA)-middle cerebral artery (MCA) bypass surgery is now being widely used in moyamoya disease, and its therapeutic value in SICAO remains divergent. Methods: A systematic search was performed in PubMed, EMBASE, and Cochrane Databases in Feb. 2020 and updated in Jun. 2019. We have strict inclusion and exclusion criteria. Cochrane Bias Risk Assessment Tool was used to assess the quality of included RCTs. Review Manager 5.3 was used for analysis results in terms of comparing the STA-MCA bypass and BMT. For dichotomous variable outcomes, risk ratios (RRs) and 95% confidence intervals (95%CIs) were calculated for the assessment. Results: The total patient cohort consisted of 2419 patients, of whom 1188 (49.1%) patients had been grouped in STA-MCA bypass and 1231 (50.9%) patients had been divided into the BMT group. Mean follow-up of included patients was 29 months. The RR of the seven studies was 1.01, and the 95% confidence interval was .89–1.15, with statistical significance, Z = .13, P = .89, sustaining that STA-MCA bypass was not superior to BMT in symptomatic carotid artery occlusion disease. Conclusions: STA-MCA bypass and BMT were associated with similar rates of a composite of long-term stroke. And the risk of long-term overall stroke was mildly higher with BMT. At present, each patient should receive more precise treatment, by reasonably assessing the individual differences of each patient to reduce the recurrence rate of stroke.