A New Pneumonia Detection Model Based on Transformer with Improved Self-Attention Mechanism

Clinical diagnosis based on computed tomography (CT) could be used, as part of diagnosis standard of COVID-19 pneumonia. Addressing the problem that accuracy of CT-based traditional pneumonia classification diagnosis models is relatively low when employed for classification of community-acquired pneumonia (CP), COVID-19 pneumonia (NCP) and normal cases, a new network model is proposed which combines application of Swin Transformer and multi-head axial self-attention (MASA) mechanism, to analyze CT images and make intelligence-assisted diagnosis. The method in detail is to partially replace traditional multi-head self-attention (MSA) mechanism in encoders of Swin Transformer by MASA. The improved model is applied to train and test on commonly used pneumonia CT dataset CC-CCII. The results show that the proposed network outperforms traditional networks ResNet50 and Vision Transformer in indicators of accuracy, sensitivity and F1-measure. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Spatiotemporal characteristics of ozone and the formation sensitivity over the Fenwei Plain.

High surface ozone (O3) levels affect human and environmental health. The Fenwei Plain (FWP), one of the critical regions for China's "Blue Sky Protection Campaign", has reported severe O3 pollution. This study investigates the spatiotemporal properties and the causes of O3 pollution over the FWP using high-resolution data from the TROPOspheric Monitoring Instrument (TROPOMI) from 2019 to 2021. This study characterizes spatial and temporal variations in O3 concentration by linking O3 columns and surface monitoring using a trained deep forest machine learning model. O3 concentrations in summer were 2-3 times higher than those found in winter due to higher temperatures and greater solar irradiation. The spatial distributions of O3 correlate with the solar radiation showing decreased trends from the northeastern to the southwestern FWP, with the highest O3 values in Shanxi Province and the lowest in Shaanxi Province. For urban areas, croplands and grasslands, the O3 photochemistry in summer is NOx-limited or in the transitional regime, while it is VOC-limited in winter and other seasons. Reducing NOx emissions would be effective for decreasing O3 levels in summer, while VOC reductions are necessary for winter. The annual cycle in vegetated areas included both NOx-limited and transitional regimes, indicating the importance of NOx controls to protect ecosystems. The O3 response to limiting precursors shown here is of importance for optimizing control strategies and is illustrated by emission changes during the 2020 COVID-19 outbreak.

A 0.63-mm2/Ch 1.3-mΩ/√ Hz-Sensitivity 1-MHz Bandwidth Active Electrode Electrical Impedance Tomography System

Due to the coronavirus pandemic, portable electrical impedance tomography (EIT) systems [1]-[3] have been considered as the only variable wearable medical lung imaging solution for monitoring the treatment of pneumonia patients and their recovery. Generally, the EIT system is classified into passive EIT (P-EIT) [3]-[6] or active electrode EIT (AE-EIT) [2]. The AE-EIT system is preferred as it amplifies and digitalizes the small signals while minimizing the noises incurred by motion artifacts, complex long wire connection, large variation in electrode contact, and stray capacitance problems, which is important for high-performance imaging applications. © 2022 IEEE.

OPENTFV: An Open Domain Table-Based Fact Verification System

The prevalence of misinformation, both online and offline, has prompted a great demand of fact verification. Table-based fact verification aims to check whether a textual claim is supported or refuted based on relational tables. However, most of the existing approaches are in a closed-domain setting, which may not be realistic in practice. To address this problem, in this paper, we introduce OPENTFV, a user-friendly system that supports open domain table-based fact verification. Given a claim input by an end-user, OPENTFV retrieves the relevant tables, and provides a verification result for each table with an intuitive interpretation in natural language. We have implemented OPENTFV and demonstrated OPENTFV in two representative scenarios, COVID-19 claims fact verification based on academic tables and general fact verification on Wiki-tables.

Impact of COVID-19 on acute ischemic stroke presentation and prognosis in a county-level stroke center.

OBJECTIVE: The COVID-19 pandemic has influenced regular medical procedures and health-seeking behaviors. In this study, we aimed to investigate the influence of the COVID-19 pandemic on the presentation and prognosis of acute ischemic stroke (AIS) patients in county-level stroke centers. PATIENTS AND METHODS: We retrospectively collected AIS patients during the strict lockdown period (January 24, 2020, to March 27, 2020) and the corresponding "new normal" period (2021) of the COVID-19 pandemic. Patients seen during the same timeframe in 2019 were enrolled as controls. Statistical analysis was conducted to compare the clinical characteristics of AIS patients who presented during the lockdown and new normal periods and those who presented during the pre-COVID-19 pandemic period. RESULTS: A total of 134 AIS patients presented during the lockdown period (the 2020 group), 207 patients in the pre-COVID-19 period (the 2019 group) and 201 patients in the "new normal" period (the 2021 group). Compared to the 2019 group, there was approximately 1/3 reduction in the number of patients who presented during the lockdown period, while the number of patients who received IVT or EVT was similar between the two groups. The number of patients, baseline characteristics, workflow intervals and clinical outcomes presented during the "new normal" period were similar between the 2019 and 2021 groups. Logistic regression showed that lockdown or new normal status were not risk factors associated with a poor outcome at 90 days. CONCLUSIONS: In county-level city stroke centers, the COVID-19 lockdown resulted in a reduction in the number of patients with AIS admitted to the hospital but had no effect on patients treated with IVT or EVT. Lockdown or new normal status did not influence the prognosis of AIS patients.

Estimating Spatiotemporal Contacts Between Individuals in Underground Shopping Streets Based on Multi-Agent Simulation

Coronavirus disease 2019 (COVID-19) has exposed the public safety issues. Obtaining inter-individual contact and transmission in the underground spaces is an important issue for simulating and mitigating the spread of the pandemic. Taking the underground shopping streets as an example, this study aimed to verify commercial facilities' influence on the spatiotemporal distribution of inter-individual contact in the underground space. Based on actual surveillance data, machine learning techniques are adopted to obtain utilizers' dynamics in underground pedestrian system and shops. Firstly, an entropy maximization approach is adopted to estimate pedestrians' origin-destination (OD) information. Commercial utilization behaviors at different shops are modeled based on utilizers' entering frequency and staying duration, which are obtained by re-identifying individuals' disappearances and appearances at storefronts. Based on observed results, a simulation method is proposed to estimate utilizers' spatiotemporal contact by recreating their space-time paths in the underground system. Inter-individual contact events and exposure duration are obtained in view of their space-time vectors in passages and shops. A social contact network is established to describe the contact relations between all individuals in the whole system. The exposure duration and weighted clustering coefficients were defined as indicators to measure the contact degree of individual and the social contact network. The simulation results show that the individual and contact graph indicators are similar across time, while the spatial distribution of inter-individual contact within shops and passages are time-varying. Through simulation experiments, the study verified the effects of self-protection and commercial type adjustment measures.

Annual report of thoracic surgery services at the Shanghai Chest Hospital in 2020

Background: The thoracic surgery team of the Shanghai Chest Hospital has been publishing its annual report since 2018, summarizing the services and major progress over the last year. Methods: All patients receiving thoracic surgery services at the Department of Thoracic Surgery and the Department of Oncological Surgery at the Shanghai Chest Hospital in 2020 were enrolled. The number of surgical resections, types of surgical procedures, disease histological types, and perioperative outcomes were collected and compared with the results from previous years. Results: In the year 2020, the thoracic team of the Shanghai Chest Hospital faced the unprecedented challenge of the coronavirus disease 2019 (COVID-19) epidemic. A total of 15,664 patients received thoracic surgeries at the Shanghai Chest Hospital, only an 8.0% decrease compared with the previous year of 2019. These included 13,493 pulmonary procedures, 1,075 esophageal procedures, 969 mediastinal procedures, 66 tracheal procedures, 2 lung transplantations, and 59 other procedures. The rate of minimally invasive surgeries among all procedures was 91.1%, including 721 robotic-assisted thoracic surgeries, both of which increased from the year before. In addition, the average length of hospital stay continuously decreased, being only 3.82 days after pulmonary surgery and 10.96 days after esophageal surgery. Meanwhile, the quality of thoracic surgery has improved, with continuously lower rates of perioperative complications and an in-hospital mortality rate of only 0.14%. Conclusions: The services provided and progress made in 2020 by the thoracic surgery team of the Shanghai Chest Hospital were reviewed in this annual report, reflecting a consistent effort to help our patients with high-standard services and state-of-the-art surgical techniques. © 2022 Shanghai Chest. All rights reserved.

Assessing air quality changes in heavily polluted cities during the COVID-19 pandemic: A case study in Xi & rsquo;an, China

Chinese government has instated strict restrictions to halt the spread of COVID-19. Given the complete shutdown of emission-resources, like traffic, factories, restaurants, and construction sites, responses to this pandemic have wrought unintended consequences in air quality. We assessed air pollution during the COVID-19 pandemic in terms of PM2.5, PM10, and O3 in Xi & rsquo;an, China, and revealed the relations between air quality and potential emission resources. We gleaned pollutant concentration data of O3, PM2.5, and PM10 from five monitoring sites and identified their trending during the observed periods. We also deployed ArcGIS to interpolate points among data detected by 130 monitoring sites and obtained spatial distribution of pollution during the observed periods. Correlation analysis helped us reveal the relations between pollutants and seven sources. The results showed that during the lockdown section, the concentration of O3 rose by 100.61 %, and those of PM2.5 and PM10 dropped by 22.4 % and 20.7 %, respectively;and during the recovering section, the concentration of PM10 increased by 12.8 %. The spatial distributions also helped us identify two high-polluted areas and two risky areas where PM10 increased sharply. The correlation analysis also implied that decreasing emission sources is the key to improve air quality. Our study also suggests that coordinated control on ozone and particles should be the focus in the future, and the two high-polluted and the two risky areas require immediate administrative interference. Our study can be a valuable reference for public propaganda on green life and governments & rsquo;sustainable development strategies. The research method for Xi & rsquo;an might also inspire similar studies on other cities.

Optimization strategies for online courses in Chinese universities during COVID-19 pandemic

During the COVID-19 pandemic, Chinese colleges and universities have online courses all over the country, but there is no definitive model for evaluating the effect of online course education. In addition, most domestic universities analyze the factors that affect online courses from a qualitative perspective, and there are fewer reasonable mathematical models. This paper uses the Logistic model to establish a multiple model between college students' online course learning conditions and various influencing factors, and uses a questionnaire survey to analyze the learning status of Chengdu University of Technology students who have taken online courses during the epidemic. Comparison of forecasts. It provides a reference for improving the online learning management system and improving students' online learning level in the future. © Published under licence by IOP Publishing Ltd.

Proof of No-Work: How to Incentivize Individuals to Stay at Home

The recent pandemic of novel coronavirus introduces a new challenge to balancing social welfare, the economy, and privacy while reducing contact among individuals. To reduce the reproduction rate without spoiling our economy, we need good incentive mechanisms to reduce the possibility of spreading the virus as well as good privacy enhancing techniques. Unfortunately, some of the recent approaches in contact tracing are not successful due to privacy concerns and a lack of sufficient incentive mechanisms to guide behavior instead of simply tracking infections. In this paper, we provide a design using smart contracts as an incentive mechanism with enhanced privacy of user location information. We utilize encrypted data calculated from a set of network routing information, and a plaintext equality test of a public key cryptosystem to estimate the duration one is present at the same location. By staying at the same location longer, a user can obtain greater rewards. We have implemented a proof concept of this scheme to evaluate its efficiency. We also discuss financial regulation and economic viewpoints. © 2020, Springer Nature Switzerland AG.

Measures to prevent goggles from fogging during the treatment of Coronavirus Disease 2019.

During these challenging and unprecedented times for the global communities as they battle the COVID-19 pandemic, we found a simple and effective way to prevent the goggles fogging. We hope that it will help the healthcare professionals who are still troubled by the problem of fogging goggles.