Explore the vast range of titles available.

To evaluate the diagnostic accuracy of deep learning algorithms to identify age-related macular degeneration and to explore factors impacting the results for future model training. Diagnostic accuracy studies published in PubMed, EMBASE, the Cochrane Library, and ClinicalTrails.gov before 11 August 2022 which employed deep learning for age-related macular degeneration detection were identified and extracted by two independent researchers. Sensitivity analysis, subgroup, and meta-regression were performed by Review Manager 5.4.1, Meta-disc 1.4, and Stata 16.0. The risk of bias was assessed using QUADAS-2. The review was registered (PROSPERO CRD42022352753). The pooled sensitivity and specificity in this meta-analysis were 94% (P = 0, 95% CI 0.94-0.94, I2 = 99.7%) and 97% (P = 0, 95% CI 0.97-0.97, I2 = 99.6%), respectively. The pooled positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and the area under the curve value were 21.77(95% CI 15.49-30.59), 0.06 (95% CI 0.04-0.09), 342.41 (95% CI 210.31-557.49), and 0.9925, respectively. Meta-regression indicated that types of AMD (P = 0.1882, RDOR = 36.03) and layers of the network (P = 0.4878, RDOR = 0.74) contributed to the heterogeneity. Convolutional neural networks are mostly adopted deep learning algorithms in age-related macular degeneration detection. Convolutional neural networks, especially ResNets, are effective in detecting age-related macular degeneration with high diagnostic accuracy. Types of age-related macular degeneration and layers of the network are the two essential factors that impact the model training process. Proper layers of the network will make the model more reliable. More datasets established by new diagnostic methods will be used to train deep learning models in the future, which will benefit for fundus application screening, long-range medical treatment, and reducing the workload of physicians.

The Source Region of the Yangtze River (SRYR), located on the hinterland of the Tibetan Plateau (TP), is significantly affected by cryospheric components such as snow, permafrost and glaciers. Nevertheless, there remains a lack of consensus regarding the contribution of cryospheric meltwater to river runoff and its potential changes in a changing climate. This study quantifies the contributions of different types of cryospheric meltwater in the SRYR during 1961–2100 using a physically based cryospheric‐hydrological model. Results show that snowmelt, ground ice melt from thawing permafrost and glacier melt contributed 23%, 3%, and 6% to river runoff in the historical period, respectively. Due to cryospheric degradation as indicated by diminishing snow cover, thickening permafrost active layer and declining ice storage, the runoff contributions of all three types of cryospheric meltwater are projected to decline in a warming climate, with the tipping point of snowmelt runoff already reached in the historical period. The tipping point of glacier runoff is expected to be reached soon, near the 2030s, followed by the contributions of thawing permafrost later in this century. The total contribution of cryospheric meltwater to river runoff is expected to decline in the future, with meltwater from thawing permafrost replacing snowmelt as the dominant cryospheric meltwater component. Consequently, the drought mitigation capacity of cryospheric meltwater will diminish in the future, despite an expected increase in total river runoff. This study highlights the widespread risks of declining cryospheric meltwater supply both in the TP and in other cold region catchments in a warming climate.

Given the complexity of issuing, verifying, and trading green power certificates in China, along with the challenges posed by policy changes, ensuring that China’s green certificate market trading system receives proper mechanisms and technical support is crucial. This study presents a green power certificate trading (GC-TS) architecture based on an equilibrium strategy, which enhances the quoting efficiency and multi-party collaboration capability of green certificate trading by introducing Q-learning, smart contracts, and effectively integrating a multi-agent trading Nash strategy. Firstly, we integrate green certificate trading with electricity and carbon asset trading, constructing pricing strategies for the green certificate, carbon, and electricity trading markets; secondly, we design a certificate-electricity-carbon efficiency model based on ensuring the consistency of green certificates, green electricity, and carbon markets; then, to achieve diversified green certificate trading, we establish a multi-agent reinforcement learning game equilibrium model. Additionally, we propose an integrated Nash Q-learning offer with a smart contract dynamic trading joint clearing mechanism. Experiments show that trading prices have increased by 20%, and the transaction success rate by 30 times, with an analysis of trading performance from groups of 3, 5, 7, and 9 trading agents exhibiting high consistency and redundancy. Compared with models integrating smart contracts, it possesses a higher convergence efficiency of trading quotes.

The objective of this retrospective study was to predict short-term efficacy of anti-vascular endothelial growth factor (VEGF) treatment in diabetic macular edema (DME) using machine learning regression models. Real-world data from 279 DME patients who received anti-VEGF treatment at Ineye Hospital of Chengdu University of TCM between April 2017 and November 2022 were analyzed. Eight machine learning regression models were established to predict four clinical efficacy indicators. The accuracy of the models was evaluated using mean absolute error ( MAE ), mean square error ( MSE ) and coefficient of determination score ( R 2 ). Multilayer perceptron had the highest R 2 and lowest MAE among all models. Regression tree and lasso regression had similar R 2 , with lasso having lower MAE and MSE . Ridge regression, linear regression, support vector machines and polynomial regression had lower R 2 and higher MAE . Support vector machine had the lowest MSE , while polynomial regression had the highest MSE . Stochastic gradient descent had the lowest R 2 and high MAE and MSE . The results indicate that machine learning regression algorithms are valuable and effective in predicting short-term efficacy in DME patients through anti-VEGF treatment, and the lasso regression is the most effective ML algorithm for developing predictive regression models.

Background Viral myocarditis (VMC) is a type of cardiac inflammation that is generally caused by coxsackievirus B3 (CVB3) infection. Several MicroRNAs (miRNAs) are known to play crucial roles in VMC pathogenesis. MiR-15 is reportedly associated with myocardial injury, inflammatory responses and viral infection. Whether miR-15 affects the occurrence and development of VMC remains largely unknown. The roles of miR-15 and their underlying mechanisms in CVB3-stimulated H9c2 cells were assessed in this study. Methods We infected H9c2 cells with CVB3 to establish a VMC cellular model. We then determined the effects of miR-15 inhibition on three cardiomyocyte injury markers: lactate dehydrogenase (LDH), creatine kinase-MB (CK-MB) and cardiac troponin-I (cTn-I). The impact on CVB3-induced cell apoptosis and pro-inflammatory cytokines was also investigated. The effects of miR-15 inhibition on NLRP3 inflammasome activation were also assessed. The target relationship between miR-15 and NOD-like receptor X1 (NLRX1) was determined using a luciferase reporter assay. Results MiR-15 expression was significantly upregulated in H9c2 cells after CVB3 infection. Inhibition of miR-15 significantly decreased the CVB3-induced levels of LDH, CK-MB and cTn-I. It also elevated cell viability, reduced CVB3-induced cell apoptosis and decreased the generation of the interleukins IL-1β, IL-6 and IL-18. Furthermore, we determined that miR-15 inhibition suppressed NLRP3 inflammasome activation by downregulating NLRP3 and caspase-1 p20 expression. We found a direct target relationship between miR-15 and NLRX1. Additionally, inhibition of NLRX1 reversed the protective effects of miR-15 inhibition against CVB3-induced myocardial cell injury by regulating the NLRP3 inflammasome. Conclusion Our results indicate that miR-15 inhibition alleviates CVB3-induced myocardial inflammation and cell injury. This may be partially due to NLRX1-mediated NLRP3 inflammasome inactivation.

Diabetic macular edema (DME) is a common complication of diabetes that can lead to vision loss, and anti-vascular endothelial growth factor (anti-VEGF) therapy is the standard of care for DME, but the treatment outcomes vary widely among patients. This study collected optical coherence tomography (OCT) images and clinical data from DME patients who received anti-VEGF treatment to develop and validate deep learning (DL) models for predicting the anti-VEGF outcomes in DME patients based on convolutional neural network (CNN) and multilayer perceptron (MLP) combined architecture by using multimodal data. An Xception-MLP architecture was utilized to predict best-corrected visual acuity (BCVA), central subfield thickness (CST), cube volume (CV), and cube average thickness (CAT). Mean absolute error (MAE), mean squared error (MSE) and mean squared logarithmic error (MSLE) were employed to evaluate the model performance. In this study, both the training set and the validation set exhibited a consistent decreasing trend in MAE, MSE, and MSLE. No statistical difference was found between the actual and predicted values in all clinical indicators. This study demonstrated that the improved CNN-MLP regression models using multimodal data can accurately predict outcomes in BCVA, CST, CV, and CAT after anti-VEGF therapy in DME patients, which is valuable for ophthalmic clinical decisions and reduces the economic burden on patients.

ObjectiveTo evaluate the diagnostic accuracy of deep learning algorithms to identify age-related macular degeneration and to explore factors impacting the results for future model training.MethodsDiagnostic accuracy studies published in PubMed, EMBASE, the Cochrane Library, and ClinicalTrails.gov before 11 August 2022 which employed deep learning for age-related macular degeneration detection were identified and extracted by two independent researchers. Sensitivity analysis, subgroup, and meta-regression were performed by Review Manager 5.4.1, Meta-disc 1.4, and Stata 16.0. The risk of bias was assessed using QUADAS-2. The review was registered (PROSPERO CRD42022352753).ResultsThe pooled sensitivity and specificity in this meta-analysis were 94% (P = 0, 95% CI 0.94-0.94, I2 = 99.7%) and 97% (P = 0, 95% CI 0.97-0.97, I2 = 99.6%), respectively. The pooled positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and the area under the curve value were 21.77(95% CI 15.49-30.59), 0.06 (95% CI 0.04-0.09), 342.41 (95% CI 210.31-557.49), and 0.9925, respectively. Meta-regression indicated that types of AMD (P = 0.1882, RDOR = 36.03) and layers of the network (P = 0.4878, RDOR = 0.74) contributed to the heterogeneity.ConclusionsConvolutional neural networks are mostly adopted deep learning algorithms in age-related macular degeneration detection. Convolutional neural networks, especially ResNets, are effective in detecting age-related macular degeneration with high diagnostic accuracy. Types of age-related macular degeneration and layers of the network are the two essential factors that impact the model training process. Proper layers of the network will make the model more reliable. More datasets established by new diagnostic methods will be used to train deep learning models in the future, which will benefit for fundus application screening, long-range medical treatment, and reducing the workload of physicians.

Quinoa is renowned for its high nutritional value, which not only meets the nutritional needs of the human body but also makes it a suitable option for individuals with diabetes and celiac disease due to its low sugar and gluten-free characteristics. In China, the primary cultivation regions of quinoa are the Tibetan Plateau, the Yunnan–Guizhou Plateau, and Northwest China, which are predominantly characterized by hilly and mountainous terrain, resulting in the gradual development of mechanized harvesting processes. The efficacy of the mechanized harvesting process in these regions is suboptimal, exhibiting poor clearance and efficiency. In this paper, the design and MBD-EDEM coupling analysis of the quinoa combine harvester’s cleaning and screening mechanism is carried out to simulate the cleaning process of quinoa threshing materials. The results show that the vibrating screen can complete the forward sliding and dispersed throwing up of the materials and effectively avoid the accumulation of the threshing materials. The coupling results of the permeability of each material in the cleaning and screening mechanism, as well as the vibrating screen movement condition, indicate that when the herringbone screen opening degree is set in the range of 15° to 30°, the cleaning and screening device can achieve a high cleaning efficiency while maintaining a low impurity rate. Field trial data further confirm that within this opening range, the cleaning effect and efficiency both exhibit significant advantages.

Ferroptosis, a recently discovered type of programmed cell death (PCD) distinguished by iron overload and lipid peroxidation, differs fundamentally from necrosis, apoptosis, and autophagy. Emerging evidence indicates that ferroptosis is deeply implicated in the disruption of the ocular microenvironment, wherein both structural and immune cells are significantly compromised. Rather than being an isolated cellular event, ferroptosis actively engages in a complex bidirectional crosstalk with the ocular immune system, driving neuroinflammation and tissue degeneration. In this review, we shift the paradigm from traditional disease-specific descriptions to the underlying microenvironmental interactions that dictate ocular health. Furthermore, we systematically evaluate the therapeutic potential of emerging interventions. Specifically, we highlight the latest breakthroughs in utilizing natural and dietary compounds as potent ferroptosis regulators. Crucially, we address current translational limitations by exploring advanced drug delivery systems, such as nanocarriers and hydrogels, designed to effectively overcome the blood-retinal barrier (BRB) and improve targeted efficacy. Ultimately, this review provides a comprehensive roadmap for advancing ferroptosis-targeted therapies from the laboratory to clinical ophthalmology.