BackgroundTraumatic spinal cord injury (TSCI) is a highly fatal and disabling event, and its incidence rate is increasing in China. Therefore, we collated the epidemiological factors of TSCI in different regions of China to update the earlier systematic review published in 2018.MethodWe searched four English and three Chinese electronic databases from 1978 to October 1, 2022. From the included reports, information on sample characteristics, incidence, injury characteristics, prognostic factors, and economic burden was extracted. The selection of data was based on the PRISMA statement. The quality of the included studies was assessed by the Agency for Healthcare Research and Quality (AHRQ) tool. The results of the meta-analysis were presented in the form of pooled frequency and forest plots.ResultsA total of 59 reports (60 studies) from 23 provinces were included, of which 41 were in the Chinese language. The random pooled incidence of TSCI in China was estimated to be 65.15 per million (95% CI: 47.20–83.10 per million), with a range of 6.7 to 569.7 per million. The pooled male-to-female ratio was 1.95:1. The pooled mean age of the cases at the time of injury was 45.4 years. Motor vehicle accidents (MVAs) and high falls were found to be the leading causes of TSCI. Incomplete quadriplegia and AISA/Frankel grade D were the most common types of TSCI. Cervical level injury was the most prevalent. The pooled in-hospital mortality and complication rates for TSCI in China were 3% (95% CI: 2–4%) and 35% (95% CI: 23–47%). Respiratory problems were the most common complication and the leading cause of death.ConclusionCompared with previous studies, the epidemiological data on TSCI in China has changed significantly. A need to update the data over time is essential to implement appropriate preventive measures and formulate interventions according to the characteristics of the Chinese population.
Graph clustering is a fundamental task in data analysis and has attracted considerable attention in recommendation systems, mapping knowledge domain, and biological science. Because graph convolution is very effective in combining the feature information and topology information of graph data, some graph clustering methods based on graph convolution have achieved superior performance. However, current methods lack the consideration of structured information and the process of graph convolution. Specifically, most of existing methods ignore the implicit interaction between topology information and feature information, and the stacking of a small number of graph convolutional layers leads to insufficient learning of complex information. Inspired by graph convolutional network and auto-encoder, we propose a deep graph structured clustering network that applies a deep clustering method to graph structured data processing. Deep graph convolution is employed in the backbone network, and evaluates the result of each iteration with node feature and topology information. In order to optimize the network without supervision, a triple self-supervised module is designed to help update parameters for overall network. In our model, we exploit all information of the graph structured data and perform self-supervised learning. Furthermore, improved graph convolution layers significantly alleviate the problem of clustering performance degradation caused by over-smoothing. Our model is designed to perform on representative and indirect graph datasets, and experimental results demonstrate that our model achieves superior performance over state-of-the-art models. INDEX TERMS Autoencoder, deep graph convolutional network, deep graph clustering, unsupervised learning.
Recently, recommender systems based on Graph Convolution Network (GCN) have become a research hotspot, especially in collaborative filtering. However, most GCN-based models have inferior embedding propagation mechanism, leading to low information extraction efficiency. Besides, the existing methods suffer from high computational complexity for large user-item interaction graphs. In order to solve the above problems, we propose LII-GCCF that integrates Linear transformation, Initial residual and Identity mapping into the Graph Convolutional Collaborative Filtering model. First, initial residual and identity mapping are applied to optimize the information propagation of graph convolution, which privide abundant interaction and alleviate information loss problem. Second, LII-GCCF removes the unnecessary nonlinear transformation based on the characteristics of collaborative filtering to simplify the graph convolution process. Comprehensive experiments are conducted on two public datasets, and the results demonstrate that LII-GCCF has a significant improvement over other state-of-the-art methods.INDEX TERMS Collaborative filtering, graph convolutional network, recommender systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.