Transformer with difference convolutional network for lightweight universal boundary detection.

Although deep-learning methods can achieve human-level performance in boundary detection, their improvements mostly rely on larger models and specific datasets, leading to significant computational power consumption. As a fundamental low-level vision task, a single model with fewer parameters to achieve cross-dataset boundary detection merits further investigation. In this study, a lightweight universal boundary detection method was developed based on convolution and a transformer. The network is called a "transformer with difference convolutional network" (TDCN), which implies the introduction of a difference convolutional network rather than a pure transformer. The TDCN structure consists of three parts: convolution, transformer, and head function. First, a convolution network fused with edge operators is used to extract multiscale difference features. These pixel difference features are then fed to the hierarchical transformer as tokens. Considering the intrinsic characteristics of the boundary detection task, a new boundary-aware self-attention structure was designed in the transformer to provide inductive bias. By incorporating the proposed attention loss function, it introduces the direction of the boundary as strongly supervised information to improve the detection ability of the model. Finally, several head functions with multiscale feature inputs were trained using a bidirectional additive strategy. In the experiments, the proposed method achieved competitive performance on multiple public datasets with fewer model parameters. A single model was obtained to realize universal prediction even for different datasets without retraining, demonstrating the effectiveness of the method. The code is available at https://github.com/neulmc/TDCN.

Impact of an ICU bed capacity optimisation method on the average length of stay and average cost of hospitalisation following implementation of China's open policy with respect to COVID-19: a difference-in-differences analysis based on information management system data from a tertiary hospital in southwest China.

OBJECTIVES: Following the implementation of China's open policy with respect to COVID-19 on 7 December 2022, the influx of patients with infectious diseases has surged rapidly, necessitating hospitals to adopt temporary requisition and modification of ward beds to optimise hospital bed capacity and alleviate the burden of overcrowded patients. This study aims to investigate the effect of an intensive care unit (ICU) bed capacity optimisation method on the average length of stay (ALS) and average cost of hospitalisation (ACH) after the open policy of COVID-19 in China. DESIGN AND SETTING: A difference-in-differences (DID) approach is employed to analyse and compare the ALS and ACH of patients in four modified ICUs and eight non-modified ICUs within a tertiary hospital located in southwest China. The analysis spans 2 months before and after the open policy, specifically from 5 October 2022 to 6 December 2022, and 7 December 2022 to 6 February 2023. PARTICIPANTS: We used the daily data extracted from the hospital's information management system for a total of 5944 patients admitted by the outpatient and emergency access during the 2-month periods before and after the release of the open policy in China. RESULTS: The findings indicate that the ICU bed optimisation method implemented by the tertiary hospital led to a significant reduction in ALS (HR -0.6764, 95% CI -1.0328 to -0.3201, p=0.000) and ACH (HR -0.2336, 95% CI -0.4741 to -0.0068, p=0.057) among ICU patients after implementation of the open policy. These results were robust across various sensitivity analyses. However, the effect of the optimisation method exhibits heterogeneity among patients admitted through the outpatient and emergency channels. CONCLUSIONS: This study corroborates a significant positive impact of ICU bed optimisation in mitigating the shortage of medical resources following an epidemic outbreak. The findings hold theoretical and practical implications for identifying effective emergency coordination strategies in managing hospital bed resources during sudden public health emergency events. These insights contribute to the advancement of resource management practices and the promotion of experiences in dealing with public health emergencies.

Cybersecurity on a budget: Evaluating security and performance of open-source SIEM solutions for SMEs.

The proliferation of cyber threats necessitates robust security measures to safeguard critical assets and data in today's evolving digital landscape. Small and Medium Enterprises (SMEs), which are the backbone of the global economy are particularly vulnerable to these threats due to inadequate protection for critical and sensitive information, budgetary constraints, and lack of cybersecurity expertise and personnel. Security Information and Event Management (SIEM) systems have emerged as pivotal tools for monitoring, detecting, and responding to security incidents. While proprietary SIEM solutions have historically dominated the market, open-source SIEM systems have gained prominence for their accessibility and cost-effectiveness for SMEs. This article presents a comprehensive study focusing on the evaluation of open-source SIEM systems. The research investigates the capabilities of these open-source solutions in addressing modern security challenges and compliance with regulatory requirements. Performance aspects are explored through empirical testing in simulated enterprise-grade SME network environments to assess resource utilization, and real-time data processing capabilities. By providing a rigorous assessment of the security and performance features of open-source SIEM systems, this research offers valuable insights to cybersecurity practitioners, organizations seeking cost-effective security solutions, and the broader academic community. The findings shed light on the strengths and limitations of these systems, aiding decision-makers in selecting the most suitable SIEM solution for their specific requirements while enhancing the cybersecurity posture of SMEs.

Application study of surgical instruments information management system in sports medicine specialty.

The management of surgical instruments is related to the safety and efficiency of surgical operations, and a surgical instruments information management system (SIIMS) has been developed. The aim of the current study is to explore the application value of the SIIMS in sports medicine specialty. A set of self-developed SIIMS for sports medicine surgeries was applied to the study. The application value of the SIIMS was verified by comparing the safety and efficiency of instrument manipulation before and after its application, with instrument accidents, instrument repair rate, instrument scrap rate and instrument use efficiency as indicators. Through the application of the SIIMS, the incidence of surgical instrument accidents decreased from 3.7 times to 1.8 times (P = 0.02), the number of instrument repair decreased from 7.7 times to 2.9 times (P = 0.00), and the number of scrapped instruments decreased from 5.1 to 2.3 (P = 0.03), when referred to per thousand operations. Before and after the application of the SIIMS, the average instrument use efficiency was 74.0% ± 3.3% and 88.2% ± 4.4%, respectively, with statistically significant difference (P = 0.00). The application of the SIIMS in sports medicine specialty is helpful to the fine management of surgical instruments, improve surgical safety and instrument use efficiency.

Impact of the Narcotics Information Management System on Opioid Use Among Outpatients With Musculoskeletal and Connective Tissue Disorders: Quasi-Experimental Study Using Interrupted Time Series.

BACKGROUND: Opioids have traditionally been used to manage acute or terminal pain. However, their prolonged use has the potential for abuse, misuse, and addiction. South Korea introduced a new health care IT system named the Narcotics Information Management System (NIMS) with the objective of managing all aspects of opioid use, including manufacturing, distribution, sales, disposal, etc. OBJECTIVE: This study aimed to assess the impact of NIMS on opioid use. METHODS: We conducted an analysis using national claims data from 45,582 patients diagnosed with musculoskeletal and connective tissue disorders between 2016 and 2020. Our approach included using an interrupted time-series analysis and constructing segmented regression models. Within these models, we considered the primary intervention to be the implementation of NIMS, while we treated the COVID-19 outbreak as the secondary event. To comprehensively assess inappropriate opioid use, we examined 4 key indicators, as established in previous studies: (1) the proportion of patients on high-dose opioid treatment, (2) the proportion of patients receiving opioid prescriptions from multiple providers, (3) the overlap rate of opioid prescriptions per patient, and (4) the naloxone use rate among opioid users. RESULTS: During the study period, there was a general trend of increasing opioid use. After the implementation of NIMS, significant increases were observed in the trend of the proportion of patients on high-dose opioid treatment (coefficient=0.0271; P=.01) and in the level of the proportion of patients receiving opioid prescriptions from multiple providers (coefficient=0.6252; P=.004). An abrupt decline was seen in the level of the naloxone use rate among opioid users (coefficient=-0.2968; P=.04). While these changes were statistically significant, their clinical significance appears to be minor. No significant changes were observed after both the implementation of NIMS and the COVID-19 outbreak. CONCLUSIONS: This study suggests that, in its current form, the NIMS may not have brought significant improvements to the identified indicators of opioid overuse and misuse. Additionally, the COVID-19 outbreak exhibited no significant influence on opioid use patterns. The absence of real-time monitoring feature within the NIMS could be a key contributing factor. Further exploration and enhancements are needed to maximize the NIMS' impact on curbing inappropriate opioid use.

South Africa's oceans and coastal and information management system towards improved ocean access, protection, and governance.

The Oceans and Coastal Information Management System (OCIMS) was launched by the South African Government in 2015 to support the development and governance of the South African ocean economy. The OCIMS has established knowledge tools for marine spatial planning, maritime domain awareness, search and rescue, water quality and harmful algal bloom monitoring. Those tools are used daily by stakeholders across government departments, industry, and civil society. Unlike many other operational oceanographic and coastal systems around the world, the OCIMS was designed from its inception using inputs from stakeholders. Continuous engagements between developers and stakeholders have ensured that the system remains fit for purpose. The OCIMS is both locally relevant and globally cognizant. Developments are undertaken to ensure inter-operability with other systems in the world and promote the exchange and discovery of data. The OCIMS project was able to leverage co-funding and the sharing of data and expertise through partnerships across the public and private sectors. These partnerships have been essential to the success of OCIMS and would not have been possible without continued engagements and the sustained funding provided by the South African national government. The development pathway followed to establish the OCIMS could benefit other countries looking to implement their own operational ocean and coastal system knowledge platform.

Development of the Clinical Specimen Information Management System for Multicenter Clinical Studies.

Some multicenter clinical studies require the acquisition of clinical specimens from patients, and the centralized management and analysis of clinical specimens at a research institution. In such cases, it is necessary to manage clinical specimens with anonymized patient information. In addition, clinical specimens need to be managed in connection with clinical information in clinical studies. In this study, we have developed a clinical specimen information management system that works with electronic data capture system for efficient specimen information management and the system workflow has verified at Osaka University Hospital. In addition, by combining this system with medical image collection system that we have developed previously, the integrated management of clinical information, medical image, and clinical specimen information will become possible. This specimen information management system may be expected to provide the platform for integrated analysis utilizing clinical information, medical image, and data from clinical specimens in multicenter clinical studies.

Learning deep representation and discriminative features for clustering of multi-layer networks.

The multi-layer network consists of the interactions between different layers, where each layer of the network is depicted as a graph, providing a comprehensive way to model the underlying complex systems. The layer-specific modules of multi-layer networks are critical to understanding the structure and function of the system. However, existing methods fail to characterize and balance the connectivity and specificity of layer-specific modules in networks because of the complicated inter- and intra-coupling of various layers. To address the above issues, a joint learning graph clustering algorithm (DRDF) for detecting layer-specific modules in multi-layer networks is proposed, which simultaneously learns the deep representation and discriminative features. Specifically, DRDF learns the deep representation with deep nonnegative matrix factorization, where the high-order topology of the multi-layer network is gradually and precisely characterized. Moreover, it addresses the specificity of modules with discriminative feature learning, where the intra-class compactness and inter-class separation of pseudo-labels of clusters are explored as self-supervised information, thereby providing a more accurate method to explicitly model the specificity of the multi-layer network. Finally, DRDF balances the connectivity and specificity of layer-specific modules with joint learning, where the overall objective of the graph clustering algorithm and optimization rules are derived. The experiments on ten multi-layer networks showed that DRDF not only outperforms eight baselines on graph clustering but also enhances the robustness of algorithms.

Joint estimation of pose, depth, and optical flow with a competition-cooperation transformer network.

Estimating depth, ego-motion, and optical flow from consecutive frames is a critical task in robot navigation and has received significant attention in recent years. In this study, we propose PDF-Former, an unsupervised joint estimation network comprising a full transformer-based framework, as well as a competition and cooperation mechanism. The transformer framework captures global feature dependencies and is customized for different task types, thereby improving the performance of sequential tasks. The competition and cooperation mechanisms enable the network to obtain additional supervisory information at different training stages. Specifically, the competition mechanism is implemented early in training to achieve iterative optimization of 6 DOF poses (rotation and translation information from the target image to the two reference images), the depth of target image, and optical flow (from the target image to the two reference images) estimation in a competitive manner. In contrast, the cooperation mechanism is implemented later in training to facilitate the transmission of results among the three networks and mutually optimize the estimation results. We conducted experiments on the KITTI dataset, and the results indicate that PDF-Former has significant potential to enhance the accuracy and robustness of sequential tasks in robot navigation.

Práticas educacionais colaborativas em saúde mediadas pelas tecnologias da informação e comunicação: uma revisão de literatura / Collaborative educational practices in health mediated by information and communication technologies: a literature review / Prácticas educativas colaborativas en salud mediadas por las tecnologías de la información y comunicación: una revisión de literatura

O objetivo do presente estudo foi identificar elementos estruturantes do processo de trabalho das redes educacionais colaborativas em saúde mediadas por tecnologias de informação e comunicação, assinalando suas características-chave e sua dinâmica de funcionamento. Trata-se de uma revisão de escopo, realiza-da nas bases de dados: Medline, Lilacs e no portal Oasisbr. Foram encontrados 1.499 estudos, dos quais, oito atenderam aos critérios de inclusão. Os resultados da investigação apontam as práticas educacionais colaborativas em saúde mediados por essas tecnologias como processos amplos e complexos, envolvendo a associação de diversos fatores. Destacam-se a dimensão técnico-pedagógica, a gestão estratégica, o gerenciamento do fluxo de informações, os aspectos relacionais, as competências de cada membro e a mediação do processo colaborativo. A integração dos diferentes aspectos da rede traduz um conjunto de desafios para a estruturação dos processos colaborativos que não se limita à pura acumulação cognitiva, mas vincula-se a processos de aprendizagem e desenvolvimento dos sujeitos

The aim of the present study was to identify structural elements of the work process of collaborative educational networks in health, mediated by information and communication technologies, by pointing out its key characteristics and its operating dynamics. This is a scope review, accomplished in the following databases Medline and Lilacs and in the Oasisbr portal. A total of 1.499 studies were found, and eight of them met the inclusion criteria. The search results indicate the collaborative educational practices in health mediated by these technologies as broad and complex processes, involving the association of several factors. The technical-pedagogical dimension, the strategic management, the management of the information flow, the relational aspects, the competencies of each member, and the mediation of the collaborative process are highlighted. The integration of the different aspects of the network translates a set of challenges for the structuring of collaborative processes, which is not limited to pure cognitive accumulation, but is bound to learning processes and to the subjects' development.

El objetivo del presente estudio es identificar elementos estructurantes del proceso de trabajo de las redes educativas colaborativas en salud mediadas por tecnologías de la información y comunicación, señalando sus características claves y su dinámica de funcionamiento. El trabajo presenta una revisión de escopo, realizada en las bases de datos: Medline, Lilacs y en el portal Oasisbr. Fueron encontrados 1.499 estudios, de los cuales ocho cumplieron los criterios de inclusión. Los resultados de la investigación apuntan a las prácticas educativas colaborativas en salud mediadas por estas tecnologías como procesos amplios y com-plejos, que abarcan la asociación de diversos factores. Se destacan la dimensión técnico-pedagógica, la gestión estratégica, el gerenciamiento del flujo de información, los aspectos relacionales, las competencias de cada miembro y la mediación del proceso colaborativo. La integración de los diferentes aspectos de la red traduce un conjunto de desafíos para la estructuración de los procesos colaborativos, que no se limitan a la acumulación cognitiva, sino que se vinculan a los procesos de aprendizaje y desarrollo de los sujetos

Health literacy and the role of social support in different age groups: results of a German cross-sectional survey.

BACKGROUND: Scholars demand more focus on context-related factors of health literacy as the management of health information is seen as a social practice. One prominent factor is social support that is expected to be particularly relevant for persons vulnerable for low health literacy. It was shown that health literacy can differ across the life span and especially older people have been demonstrated to be vulnerable for low health literacy. Therefore, health literacy and the relation of social support on health literacy in different age groups should be investigated. METHODS: In a German nationwide survey 2,151 adults were interviewed face-to-face. General comprehensive health literacy was measured with the HLS19-Q47 which differentiates single steps of health information management - access, understand, appraise, and apply. Social support was measured with the Oslo 3 Social Support Scale. Bivariate and multivariate analyses were performed for all respondents and for five age groups. RESULTS: Health literacy is relatively low in all age groups but particularly low among old-old people (76 + years). Also, the youngest adults (18-29 years) have slightly lower health literacy than middle-aged adults. On average, health literacy is higher among people with higher social support but this association varies between age groups. It tends to be quite strong among younger adults (18-45 years) and young-old persons (65-75 years) but is weak among older middle-aged (46-64 years) and old-old persons. The association also differs between steps of information management. It is stronger for accessing and applying information but there are differences in age groups as well. CONCLUSIONS: Social support is a relevant aspect to improve individuals' health literacy and therefore should be addressed in interventions. However, it is necessary to differentiate between age groups. While both young adults and particularly old-old persons are challenged by health information management, young adults can strongly profit from social support whereas it can barely compensate the low health literacy of old-old persons. In addition, different challenges in information management steps in different age groups need to be considered when designing health literacy interventions. Thus, target group specific services and programs are needed.

Comprehensive information management system for a medical research cohort biobank based on quality by design.

BACKGROUND: With the development of big health and big data, cohort research has become a medical research hotspot. As an important repository of human genetic resources, biobanks must adapt to the requirements of large-scale and efficient operation. Thus, biobanks urgently need to design and build a legal, convenient, and efficient information management system. METHODS: This study applies the concept of "quality by design" to build a comprehensive biobank information management system based on the analysis of user requirements, legal and regulatory risks, and industry-standard requirements. The system integrates the management of scientific research projects, biological specimens, clinical information, quality control, and multi-dimensional information query and development. After 10 months of its operation, the comprehensive management system was evaluated through statistical analysis of the efficiency of the construction of the pregnancy-birth cohort and the quality of genetic resources. RESULTS: Since the system's launch, the statistics on cohort construction efficiency show that the enrollment rate of eligible pregnant women has increased, and the rate of missing volunteers has dropped. The time needed to establish a 1000-person cohort (with complete biological samples and clinical information in early, middle, and late pregnancy) was reduced, and the effective tracking rate of the samples was 77.42%. The error rate of the deep cryogenic refrigerator decreased, with a clinical information integrity rate of 96.47%. CONCLUSIONS: The comprehensive biobank information management system constructed with the "quality by design" concept is well suited to meet the requirements of medical research. This study provides a solution for designing a comprehensive information system for medical institutions' biobanks.

[Analysis and Research on Comprehensive Evaluation Method of Operation Performance of Hospital Valuable Equipment].

OBJECTIVE: To study the effective method of comprehensive evaluation and analysis of hospital valuable medical equipment performance. METHODS: The operation performance of 6 valuable equipment was evaluated by cost-benefit method, comprehensive index method and public evaluation method. RESULTS: Utilize equipment information management methods for data collection and evaluation, and construct an assessment data model based on evaluation indicators from three aspects: equipment operation status, profitability status, and scientific research contribution. CONCLUSIONS: Through the performance analysis of different types of valuable medical equipment, a more real and comprehensive quantitative analysis is carried out, which plays a key role in the reasonable purchase, efficient operation and avoiding idling.

SHOT UK Collaborative Reviewing and Reforming IT Processes in Transfusion (SCRIPT) survey: Laboratory information management systems: Are we ready for digital transformation?

OBJECTIVES: To understand the use, functionality and interoperability of laboratory information management systems (LIMS) in UK transfusion laboratories. BACKGROUND: LIMS are widely used to support safe transfusion practice. LIMS have the potential to reduce the risk of laboratory error using algorithms, flags and alerts that support compliance with best practice guidelines and regulatory standards. Reporting to Serious Hazards of Transfusion (SHOT), the United Kingdom (UK) haemovigilance scheme, has identified cases where the LIMS could have prevented errors but did not. Shared care of patients across different organisations and the development of pathology networks has raised challenges relating to interoperability of IT systems both within, and between, organisations. METHODS AND MATERIALS: A survey was distributed to all SHOT-reporting organisations to understand the current state of LIMS in the UK, prevalence of expertise in transfusion IT, and barriers to progress. Survey questions covered LIMS interoperability with other IT systems used in the healthcare setting. RESULTS: A variety of LIMS and version numbers are in use in transfusion laboratories, LIMS are not always updated due to resource constraints. Respondents identified interoperability and improved functionality as the main requirements for transfusion safety. CONCLUSION: A nationally agreed set of minimum standards for transfusion LIMS is required for safe practice. Adequate resources, training and expertise should be provided to support the effective use and timely updates of LIMS. A single LIMS solution should be in place for transfusion laboratories working within a network and interoperability with other systems should be explored to further improve practice.

History information management strategy for minimising biases and noise for improved medical diagnosis.

Despite measures for physicians' excellence in diagnosis, the need for improvement of medical history techniques has been pointed out as one of the critical elements for improving diagnosis. Specific and proactive frameworks related to methods of effective history acquisition are needed to minimise bias and optimise decision-making. Therefore, this paper uses Linear Sequential Unmasking- Expanded to develop and propose a structured medical history acquisition strategy. The strength of this lies in its reliance on cognitive psychological processes. Breaking information gatherings and decisions into smaller tasks and ordering them correctly reduces cognitive load as well as minimises noise and bias cascade. Additionally, this approach can help physicians develop diagnostic expertise regardless of specialty.

Investigation and Decontamination of an Urban Monkeypox Occurrence.

Before the described monkeypox virus (MPXV) case in this article, limited cases of human MPXV had occurred within the United States. Lessons learned from prior outbreaks contributed to a successful approach to decontamination and containment of an adult case of MPXV in Dallas, Texas. This case report provides an overview of the characteristics of the monkeypox virus, its effects on the human body, and a primary focus on a successful protocol for household decontamination. Additional information is provided on methods related to public relations and information management that were utilized during this incident.

Colorimetric Characterization of Color Imaging System Based on Kernel Partial Least Squares.

Colorimetric characterization is the basis of color information management in color imaging systems. In this paper, we propose a colorimetric characterization method based on kernel partial least squares (KPLS) for color imaging systems. This method takes the kernel function expansion of the three-channel response values (RGB) in the device-dependent space of the imaging system as input feature vectors, and CIE-1931 XYZ as output vectors. We first establish a KPLS color-characterization model for color imaging systems. Then we determine the hyperparameters based on nested cross validation and grid search; a color space transformation model is realized. The proposed model is validated with experiments. The CIELAB, CIELUV and CIEDE2000 color differences are used as evaluation metrics. The results of the nested cross validation test for the ColorChecker SG chart show that the proposed model is superior to the weighted nonlinear regression model and the neural network model. The method proposed in this paper has good prediction accuracy.

LoyalDE: Improving the performance of Graph Neural Networks with loyal node discovery and emphasis.

Recent years have witnessed an increasing focus on graph-based semi-supervised learning with Graph Neural Networks (GNNs). Despite existing GNNs having achieved remarkable accuracy, research on the quality of graph supervision information has inadvertently been ignored. In fact, there are significant differences in the quality of supervision information provided by different labeled nodes, and treating supervision information with different qualities equally may lead to sub-optimal performance of GNNs. We refer to this as the graph supervision loyalty problem, which is a new perspective for improving the performance of GNNs. In this paper, we devise FT-Score to quantify node loyalty by considering both the local feature similarity and the local topology similarity, and nodes with higher loyalty are more likely to provide higher-quality supervision. Based on this, we propose LoyalDE (Loyal Node Discovery and Emphasis), a model-agnostic hot-plugging training strategy, which can discover potential nodes with high loyalty to expand the training set, and then emphasize nodes with high loyalty during model training to improve performance. Experiments demonstrate that the graph supervision loyalty problem will fail most existing GNNs. In contrast, LoyalDE brings about at most 9.1% performance improvement to vanilla GNNs and consistently outperforms several state-of-the-art training strategies for semi-supervised node classification.