Inclusive Smart Textile Design for Healthy Ageing

Population ageing is a global phenomenon. This trend poses healthcare ser-vices, social care, and political challenges, yet implies a growing demand for ageing-related products and services. Smart textile technology has been increas-ingly applied in healthcare applications to support healthy ageing from many aspects. This research indicated the challenges for older people to stay in their own house in later life from the previous literature and reviewed smart home healthcare products and smart textiles for healthy ageing. We found that the current development of elderly textile products neglects the real needs of older people in healthcare products in the home environment from their perspectives. Thus, this research aims to discover the health and well-being needs of people aged 60+ living independently at home in the UK, especially during COVID-19. This research conducted interviews with 12 individuals and questionnaires with 43 individuals for questionnaires. Results highlighted the current unmet healthcare-related needs at home and participants' experiences and attitudes towards healthcare products. Finally, it indicated the potential opportunity for inclusive smart textile design for healthy ageing in the future. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

Dynamic Safety Assessment and Enhancement of Port Operational Infrastructure Systems during the COVID-19 Era

Seaports function as lifeline systems in maritime transportation, facilitating critical processes like shipping, distribution, and allied cargo handling. These diverse subsystems constitute the Port Infrastructure System (PIS) and have intricate functional interdependencies. The PIS is vulnerable to several external disruptions, and the impact of COVID-19 is severe and unprecedented in this domain. Therefore, this study proposes a novel general port safety framework to cope with recurring hazards and crisis events like COVID-19 and to augment PIS safety through a multi-state failure system. The PIS is divided into three critical subsystems: shipping, terminal, and distribution infrastructure, thereby capturing its functional interdependency and intricacy. A dynamic input-output model is employed, incorporating the spatial variability and average delay of the disruption, to determine the PIS resilience capacity under the stated disruptions. This study simulates three disruption scenarios and determines the functional failure capacity of the system by generating a functional change curve in Simulink. This study offers viable solutions to port managers, terminal operators, and concerned authorities in the efficient running of intricate interdependent processes and in devising efficient risk control measures to enhance overall PIS resilience and reliability. As part of future studies, given the difficulty in obtaining relevant data and the relatively limited validation of the current model, we aim to improve the accuracy and reliability of our model and enhance its practical applicability to real-world situations with data collected from a real-world case study of a PIS system.

ELASTIC: Edge Workload Forecasting based on Collaborative Cloud-Edge Deep Learning

With the rapid development of edge computing in the post-COVID19 pandemic period, precise workload forecasting is considered the basis for making full use of the edge limited resources, and both edge service providers (ESPs) and edge service consumers (ESCs) can benefit significantly from it. Existing paradigms of workload forecasting (i.e., edge-only or cloud-only) are improper, due to failing to consider the inter-site correlations and might suffer from significant data transmission delays. With the increasing adoption of edge platforms by web services, it is critical to balance both accuracy and efficiency in workload forecasting. In this paper, we propose ELASTIC, which is the first study that leverages a cloud-edge collaborative paradigm for edge workload forecasting with multi-view graphs. Specifically, at the global stage, we design a learnable aggregation layer on each edge site to reduce the time consumption while capturing the inter-site correlation. Additionally, at the local stage, we design a disaggregation layer combining both the intra-site correlation and inter-site correlation to improve the prediction accuracy. Extensive experiments on realistic edge workload datasets collected from China's largest edge service provider show that ELASTIC outperforms state-of-the-art methods, decreases time consumption, and reduces communication cost. © 2023 ACM.

[Visceral leishmaniasis in Xinjiang Uygur Autonomous Region during the COVID-19 pandemic: a case report].

OBJECTIVE: To perform an epidemiological investigation on a case of visceral leishmaniasis reported from Shule County, Kashi Prefecture, Xinjiang Uygur Autonomous Region in 2021, so as to provide insights into differential diagnosis of visceral leishmaniasis during the COVID-19 pandemic. METHODS: The epidemiological history of this case was collected, and the case was diagnosed for Leishmania infection with the immunochromatographic (rK39) strip test, bone marrow smear microscopy and PCR assay. RESULTS: The patient had typical clinical symptoms of leishmaniasis, including irregular fever, hepatosplenomeg- aly, low serum albumin and elevated globulin. Bone marrow smear microscopy identified L. donovani amastigotes, and both rK39 strip test and PCR assay were positive, while the case was tested negative for SARS-CoV-2. COVID-19 was therefore excluded and visceral leishmaniasis was diagnosed. Standard full-dose treatment with sodium stibogluconate was given, and no Leishmania was found on blood smears during the reexamination. No recurrence was found during the followup after discharge for hospital. CONCLUSIONS: During the COVID-19 pandemic, it is recommended to increase the perception of differential diagnosis of visceral leishmaniasis among first-contact doctors, and reinforce the capability of differential diagnosis and health education of visceral leishmaniasis among medical and healthcare institutions at all levels, to prevent missed diagnosis and misdiagnosis of visceral leishmaniasis.

Daily tourism demand forecasting before and during COVID-19: data predictivity and an improved decomposition-ensemble framework

The global tourism industry is struggling to recover from the COVID-19 pandemic. During the COVID-19 pandemic, daily tourism forecasting is more critical than ever before in supporting decisions and planning. Considering the changes in tourist psyche and behaviour caused by COVID-19, this study attempts to investigate whether the statistical modelling methods can work reliably under the new normal when travel restrictions are eased or lifted. To this end, we first compare the predictivity of daily tourism demand data before and during COVID-19, and observe heterogeneous impacts across different geographical scales. Then an improved multivariate & multiscale decomposition-ensemble framework is proposed to forecast daily tourism demand. The empirical study indicates the superiority and practicability of the proposed framework before and during COVID-19. Finally, we call for more research on the comparability of tourism demand forecasting.

Measuring College Students' Satisfaction with the Teaching Effectiveness of Online English Courses Based on the IPA Model

The English learning ability and academic performance of pre-service teachers affect the future professional development of preschool and primary education teachers. The English course has been transferred to online due to COVID-19. Whether the practicability of e-learning is consistent with students' expectations primarily affect teaching effectiveness. A paired-sample t-test on the importance and satisfaction of online English learning effectiveness of pre-service teachers from freshmen to juniors at a private university revealed no significant difference in the overall importance and satisfaction. Then the coordinated system is constructed according to the Importance -Performance Analysis (IPA) to identify the critical indicators for improving the teaching effect of online courses. The results imply that network stability and teachers' timely responses to students' questions should be concentrated. In addition, students are pretty satisfied with the e-learning platform, teaching quality and management, which should be further maintained. The suggestions for improving the effectiveness of online English teaching in private universities are proposed accordingly. © 2023 IEEE.

Design of VISUAL SLAM indoor disinfection robot based on STM32 control

In recent years, the novel corona virus pandemic is raging around the world, and the safety of home environment and public environment has become the focus of people's attention [2]. Therefore, the research on disinfection robot has become one of the important directions in the field of machinery and artificial intelligence. This paper proposes a robot with the STM32 MCU as the core of disinfection, and is equipped with a variety of sensors and a camera vision, has the original cloud service management platform, the remote deployment of navigation, based on visual SLAM to realize high precision navigation and positioning, can realize to indoor environment autonomously route planning, automatic obstacle avoidance checking, disinfection, epidemic prevention function, at the same time can pass Bit computer software realizes remote control of robot, which has great development potential. © 2022 ACM.

DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

(Aim) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. (Methods) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. (Results) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). (Conclusion) Our method outperforms 10 state-of-the-art approaches. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Prevention behaviors and influencing factors among Wuhan middle school students during COVID⁃19 epidemic

Objective: To investigate how well do the middle school students in Wuhan know and perform COVID-19 prevention behaviors during the epidemic, and to identify the influencing factors that impact the wellness of students' performance on mask-wearing, hand washing, and other health-related behaviors. Method: We surveyed 21 middle schools in Wuhan using a self-developed questionnaire, evaluated the students' prevention behaviors, and used logistic regression to identify the influencing factors. Results: We investigated 6 858 students with an average age of (14. 5±1. 5) years, including 3 584 male students (accounting for 52. 3%). Grade, parents' education, and submission time are significantly related to the wellness of the three types of health behaviors (P<0. 05). Junior high school students showed a better performance in handwashing and other health-related behaviors than senior high school students (P<0. 05). Parents' education showed a significant impact on students' prevention behaviors in all aspects (P<0. 05). Conclusion: Enhancement is needed for the education of prevention behaviors among middle school students. Schools should pay more attention to students whose parents are of the lower level of education. © 2023 Editorial Board of Medical Journal of Wuhan University. All rights reserved.

Proteomics research of SARS-CoV-2 and COVID-19 disease

Currently, coronavirus disease 2019 (COVID-19) is still spreading in a global scale, exerting a massive health and socioeconomic crisis. Deep insights into the molecular functions of the viral proteins and the pathogenesis of this infectious disease are urgently needed. In this review, we comprehensively describe the proteome of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and summarize their protein interaction map with host cells. In the protein interaction network between the virus and the host, a total of 787 host prey proteins that appeared in at least two studies or were verified by co-immunoprecipitation experiments. Together with 29 viral proteins, a network of 1762 proximal interactions were observed. We also review the proteomics results of COVID-19 patients and proved that SARS-CoV-2 hijacked the host's translation system, post-translation modification system, and energy supply system via viral proteins, resulting in various immune disorders, multiple cardiomyopathies, and cholesterol metabolism diseases. © 2022 the author(s), published by De Gruyter, Berlin/Boston.

Evaluation and treatment of Coronavirus disease 2019 with obesity.

The pandemic of coronavirus disease 2019 (COVID-19) has spread worldwide and the mortality is high in severe COVID-19 patients. Clinical studies suggested that obesity is an independent risk factor for severe and dead cases of COVID-19. For COVID-19 patients with obesity, early evaluation of obesity-related comorbidities and aggressive treatments, including diet control, airway management, anticoagulant thromboprophylaxis, and management of comorbidities, are encouraged to improve their prognosis.Copyright © 2021, Peking Union Medical College Hospital. All rights reserved.

Personalized exercise recommendation method based on causal deep learning: Experiments and implications

The COVID-19 pandemic has accelerated innovations for supporting learning and teaching online. However, online learning also means a reduction of opportunities in direct communication between teachers and students. Given the inevitable diversity in learning progress and achievements for individual online learners, it is difficult for teachers to give personalized guidance to a large number of students. The personalized guidance may cover many aspects, including recommending tailored exercises to a specific student according to the student's knowledge gaps on a subject. In this paper, we propose a personalized exercise recommendation method named causal deep learning (CDL) based on the combination of causal inference and deep learning. Deep learning is used to train and generate initial feature representations for the students and the exercises, and intervention algorithms based on causal inference are then applied to further tune these feature representations. Afterwards, deep learning is again used to predict individual students' score ratings on exercises, from which the Top-N ranked exercises are recommended to similar students who likely need enhancing of skills and understanding of the subject areas indicated by the chosen exercises. Experiments of CDL and four baseline methods on two real-world datasets demonstrate that CDL is superior to the existing methods in terms of capturing students' knowledge gaps in learning and more accurately recommending appropriate exercises to individual students to help bridge their knowledge gaps. © 2022 The Author(s).

An imported case of ovale malaria in Xinjiang during the epidemic period of COVID-19.

On December 13, 2020, Yutian County People's hospital reported one imported malaria case in Hotan, Xinjiang. The patient had worked and lived in Yaounde, Cameroon, from January to September 2020. He was infected with malaria twice in March and May 2020. Antimalarial treatment was administrated by the team doctor for 2-3 days in each treatment. The treatment was stopped after the symptoms improved. The patient returned to China on September 16 and was hospitalized on December 13 due to a high fever of 39! and upper respiratory symptoms. Multiple detections of COVID-19 nucleic acid showed negative results. Peripheral blood from the patient was taken for Plasmodium rapid diagnostic test (RDT), which showed a positive result suggesting non Plasmodium falciparum infection. Ring stage P. ovale was found in the blood smear. Nested PCR showed positive for P. ovale. A diagnosis of imported ovale malaria was made. The patient was administrated with 4 dihydroartemisinin piperaquine tablets and 3 primaquine phosphate tablets daily. The malaria parasite test became negative after 8 days of treatment. The patient was followed up for 3 months after discharge and had no symptoms of chills or fever.Copyright © 2022, National Institute of Parasitic Diseases. All rights reserved.

FEASIBILITY of LINKING UNIVERSAL WELL-CHILD HEALTHCARE and FINANCIAL COUNSELLING: FINDINGS from the AUSTRALIAN HEALTHIER WEALTHIER FAMILIES (HWF) PILOT RANDOMISED CONTROLLED TRIAL

Background: We pilot-tested the feasibility and short-term impacts of "Healthier Wealthier Families" (HWF), which seeks to reduce financial hardship by developing a referral pathway between universal child and family health (CFH) services and financial counselling. Method(s): Setting: CFH services in five sites (Victoria, New South Wales), coinciding with the COVID-19 pandemic. Participant(s): Caregivers of children aged 0-5 years. Eligible clients disclosed financial hardship using a study-designed screening tool. Design(s): Pilot randomised controlled trial (RCT). With mixed progress in Sites 1-3, we conducted an implementation evaluation and adapted the protocol to a simplified RCT (Site 4) and direct referral with pre-post evaluation (Site 5). Intervention(s): Financial counselling. The comparator was usual care. Measures: Feasibility was assessed via proportions of clients screened, enrolled, followed-up, and who accessed financial counselling. Impacts (quantitative surveys, qualitative interviews) included finances to 6 months post-enrolment. Result(s): 72%-100% of clients across sites answered the financial screen. In RCT sites (1-4), less than one-quarter enrolled. In Site 5, n = 44/64 (64%) clients were eligible and engaged with financial counselling. Common challenges facing these clients were utility debts (73%), obtaining government entitlements (43%) and material aid/emergency relief (27%). On average, their household income increased $250 per fortnight ($6504 annually), and families received average single payments of $784. Caregivers identified benefits including reduced stress, practical help, increased knowledge and empowerment. Conclusion(s): Financial hardship screening via CFH, and direct referral, were acceptable to caregivers. Individual randomisation was infeasible. Matching between populations and CFH practice is necessary to incorporate a HWF model of care.

Ground-Based MAX-DOAS Observation of Trace Gases from 2019 to 2021 in Huaibei, China

With the spread of the COVID-19 pandemic and the implementation of closure measures in 2020, population mobility and human activities have decreased, which has seriously impacted atmospheric quality. Huaibei City is an important coal and chemical production base in East China, which faces increasing environmental problems. The impact of anthropogenic activities on air quality in this area was investigated by comparing the COVID-19 lockdown in 2020 with the normal situation in 2021. Tropospheric NO2, HCHO and SO2 column densities were observed by ground-based multiple axis differential optical absorption spectroscopy (MAX-DOAS). In situ measurements for PM2.5, NO2, SO2 and O3 were also taken. The observation period was divided into four phases, the pre-lockdown period, phase 1 lockdown, phase 2 lockdown and the post-lockdown period. Ground-based MAX-DOAS results showed that tropospheric NO2, HCHO and SO2 column densities increased by 41, 14 and 14%, respectively, during phase 1 in 2021 vs. 2020. In situ results showed that NO2 and SO2 increased by 59 and 11%, respectively, during phase 1 in 2021 vs. 2020, but PM2.5 and O3 decreased by 15 and 17%, respectively. In the phase 2 period, due to the partial lifting of control measures, the concentration of pollutants did not significantly change. The weekly MAX-DOAS results showed that there was no obvious weekend effect of pollutants in the Huaibei area, and NO2, HCHO and SO2 had obvious diurnal variation characteristics. In addition, the relationship between the column densities and wind speed and direction in 2020 and 2021 was studied. The results showed that, in the absence of traffic control in 2021, elevated sources in the Eastern part of the city emitted large amounts of NO2. The observed ratios of HCHO to NO2 suggested that tropospheric ozone production involved NOX-limited scenarios. The correlation analysis between HCHO and different gases showed that HCHO mainly originated from primary emission sources related to SO2. © 2023 by the authors.

Oral Microbiota in Children Who Started Antiretroviral Therapy at Young Ages

Background: Infancy is an important developmental period when the human microbiome is shaped. Given links between young age at antiretroviral treatment (ART) initiation and smaller persisting viral reservoirs, we hypothesized that earlier ART initiation may leave distinct microbial signatures in the oral cavity detectable in children living with HIV (CLWH). Method(s): Oral swab samples were collected from 477 CLWH and 123 children without HIV at two sites in Johannesburg, South Africa. CLWH had started ART < 2 years of age with 60% starting < 6 months of age. Most were wellcontrolled on ART at a median of 10 years of age when the swab was collected. Controls were age-matched and recruited from the same communities. Sequencing of the V4 amplicon of the 16S rRNA gene was done using established protocols. DADA2, decontam, and phyloseq were used for sequence inference, contaminant removal, and subsequent analyses. All p-values were adjusted for multiple testing using Benjamini-Hochberg false discovery rate method. Statistical analyses were performed with R. Result(s): CLWH had lower alpha diversity than uninfected children (Shannon index p< 0.0001). Genus-level abundances of Granulicatella, Streptococcus and Gemella were greater and Neisseria and Haemophilus were less abundant among CLWH compared to uninfected children. Associations were strongest among boys. There was no evidence of attenuation of associations with earlier ART initiation. In fact, decreased bacterial diversity and differences in taxa abundances in CLWH versus controls were consistent regardless of whether ART was started before or after 6 months of age. Shifts in genus-level taxa abundances relative to uninfected controls were most marked in children on regimens containing lopinavir/ritonavir;with few shifts seen if on regimens containing efavirenz. Conclusion(s): A distinct profile of less diverse oral bacterial taxa was observed in school-age CLWH on ART versus uninfected age-matched children suggesting persisting interference of HIV and its treatments on microbiota in the mouth. Any effects of earlier ART initiation were not detectable at this age. Studies of treated adults with HIV have observed similar shifts in taxa abundances. Oral microbiota have been linked to salivary cytokine levels with associations between Granulicatella and IL-8 and Neisseria and IL-6. Declines in Neisseria abundances in oral samples have been associated with more severe outcomes in influenza and COVID-19.

Epidemiologic Characteristics of Multisystem Inflammatory Syndrome in Children (Mis-C) with a Focus on Outcomes

Purpose of Study Treatment outcomes of children diagnosed with MIS-C are unclear and warrant investigation. The purpose of this study is to investigate the characteristics of pediatric patients diagnosed with MIS-C and their treatment outcomes with an emphasis on fatalities associated with MISC. Methods Used A literature review using Google Scholar and Pubmed using keywords such as 'Multisystem Inflammatory Syndrome in Children', 'Pediatric Inflammatory Multisystem Syndrome', and 'Coronavirus Disease 2019' was conducted. We included studies of hospitalized MIS-C patients with a sample size of more than 15. Summary of Results Of ten studies published before August 2020, five reported hospitalized MIS-C cases in the United States and five in Europe. A total of 514 hospitalized patients were reported with a sample size of 15 to 186 in various studies. Of 514 patients, 431 (84%) tested positive for SARS-CoV-2 via RT-PCR or serology. In different studies, 50% to 100% of MIS-C patients required PICU admission, 10% to 54% were intubated, and up to 80% required vasopressors. In studies that reported echocardiogram results, coronary artery dilations or aneurysm were noted in up to 93%, and depressed cardiac function was reported in 51- 100% of MIS-C patients. Treatment of MIS-C patients included intravenous immunoglobulins (IVIG) 388/514 (75%) plus steroids 288/514 (56%), along with anticoagulants and Anakinra 26/514 (5%). In total, 23 patients were put on ECMO, and of those, 16 (70%) survived. The larger studies reported fatality rate of 2% to 3% in hospitalized MIS-C patients. A total of 10 deaths were reported. Of the fatality causes that were described, 3 were associated with cerebral infarction after ECMO, 2 had not received IVIG, systemic glucocorticoids, or immunomodulators, and another 2 had co-morbidities. Conclusions Our review suggests that children with MIS-C who are hospitalized typically have a severe disease course. The outcome in vast majority of patients is favorable but death can occur, most likely as a result of cardiac dysfunction or cerebral infarction. Larger studies are needed to identify clinical features as well as laboratory and diagnostic parameters that predict disease severity and outcome.

COVID-19 Impact on the Italian Community-based System of Mental Health Care: Reflections and Lessons Learned for the Future

Surface longwave downward radiation (LWDR) is a key factor affecting the surface energy balance. The daily LWDR and the diurnal variations of LWDR are of great significance for studies of climate change and surface processes. How to obtain LWDR at an averaged temporal scale from instantaneous LWDR is one of the longstanding problems in the field of radiation budget from remote sensing. In this paper, two temporal upscaling methods are introduced, namely, a method based on the diurnal variations of LWDR (diurnal variation based, DVB) and a method based on random forest regression (RFR). The results reveal that: (1) The DVB method has a global hourly and daily LWDR root-mean-square error (RMSE) of less than 21 W/m2 and 15 W/m2, respectively, and the RMSE of the daily LWDR based on RFR is less than 7 W/m2;(2) When compared with four existing statistical interpolation methods, the DVB method can not only ensure the accuracy, but also can overcome the problem of missing samples and/or an abnormal samples during upscaling;(3) Except for directly predict daily LWDR, the DVB methods can also obtain more accurate LWDR diurnal variations such as hourly, half-hourly etc. The RFR method enables high-efficiency and accurate estimation of daily averaged LWDR from instantaneous measurements. Compared with existing methods and products, the proposed methods are not only efficient, but also have a superior applicability and reliable accuracy. The proposed strategies provide new ideas for the community in estimating LWDR at continuous temporal scales from remotely sensed measurements.

Risk of autoimmune diseases in patients with COVID-19 a retrospective cohort study

Background There are a growing number of case reports of various autoimmune diseases occurring after COVID-19, yet there is no large-scale population-based evidence to support this potential association. This study provides a closer insight into the association between COVID-19 and autoimmune diseases and reveals discrepancies across sex, age, and race of participants.Methods This is a retrospective cohort study based on the TriNetX U.S. Collaborative Network. In the test-negative design, cases were participants with positive polymerase chain reaction (PCR) test results for SARS-CoV-2, while controls were participants who tested negative and were not diagnosed with COVID-19 throughout the follow-up period. Patients with COVID-19 and controls were propensity score-matched (1: 1) for age, sex, race, adverse socioeconomic status, lifestyle-related variables, and comorbidities. The primary endpoint is the incidence of newly recorded autoimmune diseases. Adjusted hazard ratios (aHRs) and 95% confident intervals (CIs) of autoimmune diseases were calculated between propensity score-matched groups with the use of Cox proportional-hazards regression models.Findings Between January 1st, 2020 and December 31st, 2021, 3,814,479 participants were included in the study (888,463 cases and 2,926,016 controls). After matching, the COVID-19 cohort exhibited significantly higher risks of rheumatoid arthritis (aHR:2.98, 95% CI:2.78-3.20), ankylosing spondylitis (aHR:3.21, 95% CI:2.50-4.13), systemic lupus erythematosus (aHR:2.99, 95% CI:2.68-3.34), dermatopolymyositis (aHR:1.96, 95% CI:1.47-2.61), systemic sclerosis (aHR:2.58, 95% CI:2.02-3.28), Sjogren's syndrome (aHR:2.62, 95% CI:2.29-3.00), mixed connective tissue disease (aHR:3.14, 95% CI:2.26-4.36), Behcet's disease (aHR:2.32, 95% CI:1.38-3.89), polymyalgia rheumatica (aHR:2.90, 95% CI:2.36-3.57), vasculitis (aHR:1.96, 95% CI:1.74-2.20), psoriasis (aHR:2.91, 95% CI:2.67-3.17), inflammatory bowel disease (aHR:1.78, 95%CI:1.72-1.84), celiac disease (aHR:2.68, 95% CI:2.51-2.85), type 1 diabetes mellitus (aHR:2.68, 95%CI:2.51-2.85) and mortality (aHR:1.20, 95% CI:1.16-1.24).Interpretation COVID-19 is associated with a different degree of risk for various autoimmune diseases. Given the large sample size and relatively modest effects these findings should be replicated in an independent dataset. Further research is needed to better understand the underlying mechanisms.Funding Kaohsiung Veterans General Hospital (KSVGH111-113).

Deep Rank-Based Average Pooling Network for Covid-19 Recognition

(Aim) To make a more accurate and precise COVID-19 diagnosis system, this study proposed a novel deep rank-based average pooling network (DRAPNet) model, i.e., deep rank-based average pooling network, for COVID-19 recognition. (Methods) 521 subjects yield 1164 slice images via the slice level selection method. All the 1164 slice images comprise four categories: COVID-19 positive;community-acquired pneumonia;second pulmonary tuberculosis;and healthy control. Our method firstly introduced an improved multiple-way data augmentation. Secondly, an n-cony rank-based average pooling module (NRAPM) was proposed in which rank-based pooling-particularly, rank-based average pooling (RAP)-was employed to avoid overfitting. Third, a novel DRAPNet was proposed based on NRAPM and inspired by the VGG network. Grad-CAM was used to generate heatmaps and gave our AI model an explainable analysis. (Results) Our DRAPNet achieved a micro-averaged F1 score of 95.49% by 10 runs over the test set. The sensitivities of the four classes were 95.44%, 96.07%, 94.41%, and 96.07%, respectively. The precisions of four classes were 96.45%, 95.22%, 95.05%, and 95.28%, respectively. The F1 scores of the four classes were 95.94%, 95.64%, 94.73%, and 95.67%, respectively. Besides, the confusion matrix was given. (Conclusions) The DRAPNet is effective in diagnosing COVID-19 and other chest infectious diseases. The RAP gives better results than four other methods: strided convolution, l(2)-norm pooling, average pooling, and max pooling.