Search

Diabetic retinopathy (DR) is one of the most common retinal vascular diseases and one of the main causes of blindness worldwide. Early detection and treatment can effectively delay vision decline and even blindness in patients with DR. In recent years, artificial intelligence (AI) models constructed by machine learning and deep learning (DL) algorithms have been widely used in ophthalmology research, especially in diagnosing and treating ophthalmic diseases, particularly DR. Regarding DR, AI has mainly been used in its diagnosis, grading, and lesion recognition and segmentation, and good research and application results have been achieved. This study summarizes the research progress in AI models based on machine learning and DL algorithms for DR diagnosis and discusses some limitations and challenges in AI research.

[INLINE:1] Alzheimer’s disease (AD) is affected by genetic factors. Polymorphisms in the glutathione S-transferase omega-1 (Gsto1) gene have been shown by genetic correlation analyses performed in different ethnic populations to be genetic risk factors for AD. Gene expression profile data from BXD recombinant inbred mice were used in combination with genetic and bioinformatic analyses to characterize the mechanisms underlying regulation of Gsto1 variation regulation and to identify network members that may contribute to AD risk or progression. Allele-specific assays confirmed that variation in Gsto1 expression is controlled by cis-expression quantitative trait loci. We found that Gsto1 mRNA levels were related to several central nervous system traits, such as glial acidic fibrillary protein levels in the caudate putamen, cortical gray matter volume, and hippocampus mossy fiber pathway volume. We identified 2168 genes whose expression was highly correlated with that of Gsto1. Some genes were enriched for the most common neurodegenerative diseases. Some Gsto1-related genes identified in this study had previously been identified as susceptibility genes for AD, such as APP, Grin2b, Ide, and Psenen. To evaluate the relationships between Gsto1 and candidate network members, we transfected astrocytes with Gsto1 siRNA and assessed the effect on putative downstream effectors. We confirmed that knockdown of Gsto1 had a significant influence on Pa2g4 expression, suggesting that Pa2g4 may be a downstream effector of Gsto1, and that both genes interact with other genes in a network during AD pathogenesis.

Background: The prognosis of and occurrence of complications in patients with different clinical features of cirrhosis differ, and cirrhosis with different etiologies has varying clinical characteristics. The aim of this study was to describe the liver function markers, hepatic complications, and psychological features differentiating patients with hepatitis B virus (HBV) infection-related and alcohol-related cirrhosis. Materials and Methods: This was a retrospective and observational study that analyzed the medical data of inpatients with alcohol-related or HBV infection-related cirrhosis from May 2014 to May 2020. Markers of liver function, portal hypertension, and psychological symptoms were compared between the two groups. Results: Patients with alcohol-related cirrhosis showed higher Self-Rating Anxiety Scale scores and prevalence of hypoproteinemia, fatty liver, and depression than those with HBV infection-related cirrhosis (all P < 0.05). After adjustment for potential confounders, patients with alcohol-related cirrhosis also showed higher risks of increased total cholesterol (odds ratio [OR] =2.671, 95% confidence interval [CI]: 1.160–6.151, P = 0.021), increased high-density lipoprotein-cholesterol (OR = 2.714, 95% CI: 1.009–7.299, P = 0.048), and fatty liver (OR = 2.713, 95% CI: 1.002–7.215, P = 0.048); however, splenomegaly and splenectomy were significantly associated with HBV infection-related cirrhosis (OR = 2.320, 95% CI: 1.066–5.050, P = 0.034). Conclusion: Patients with alcohol-related cirrhosis were more likely to develop hyperlipidemia, fatty liver, and psychological symptoms, whereas those with HBV-related cirrhosis had a higher risk of splenomegaly.