Global trends and frontiers of research on Kümmell's disease: A bibliometric analysis.

The prevalence of Kümmell's disease (KD) has been increasing due to the aging population and the rise of osteoporotic vertebral compressibility fractures. As a result, there has been a growing concern about this condition. Despite the rapid advancements in its related research fields, the current research status and hotspot analysis of KD remain unclear. Therefore, our goal was to identify and analyze the global research trends on KD using bibliometric tools. All KD data were obtained from the Web of Science Core Collection. The information of research field was collected, including title, author, institutions, journals, countries, references, total citations, and years of publication for further analysis. From 1900 to 2022, a total of 195 articles and 1973 references have been published in this field, originating from 27 countries/regions and 90 journals, with China leading the contributions. The most significant institutional and author contributions come from Soochow University and Kim, HS, respectively. The journal with the highest number of published research and total citation frequency is Spine. The latest research focuses in this field include "risk factor," "osteoporotic vertebral compression fracture," "pedicle screw fixation," "percutaneous vertebroplasty," and "bone cement," and should be closely monitored. Additionally, we have conducted a comprehensive analysis of the 50 most-cited articles in KD, providing a valuable list of articles to guide clinical decision-making and future research for clinicians and researchers. In recent years, there has been a significant increase in scientific research on KD. Future research in KD is likely to focus on surgical treatment, risk factors, and complications.

Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach.

Universal approximation capability, also referred to as universality, is an important property of deep neural networks, endowing them with the potency to accurately represent the underlying target function in learning tasks. In practice, the architecture of deep neural networks largely influences the performance of the models. However, most existing methodologies for designing neural architectures, such as the heuristic manual design or neural architecture search, ignore the universal approximation property, thus losing a potential safeguard about the performance. In this paper, we propose a unified framework to design the architectures of deep neural networks with a universality guarantee based on first-order optimization algorithms, where the forward pass is interpreted as the updates of an optimization algorithm. The (explicit or implicit) network is designed by replacing each gradient term in the algorithm with a learnable module similar to a two-layer network or its derivatives Specifically, we explore the realm of width-bounded neural networks, a common practical scenario, showcasing their universality. Moreover, adding operations of normalization, downsampling, and upsampling does not hurt the universality. To the best of our knowledge, this is the first work that width-bounded networks with universal approximation guarantee can be designed in a principled way. Our framework can inspire a variety of neural architectures including some renowned structures such as ResNet and DenseNet, as well as novel innovations. The experimental results on image classification problems demonstrate that the newly inspired networks are competitive and surpass the baselines of ResNet, DenseNet, as well as the advanced ConvNeXt and ViT, testifying to the effectiveness of our framework.