Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 322
Filter
1.
2nd International Conference on Medical Imaging and Additive Manufacturing, ICMIAM 2022 ; 12179, 2022.
Article in English | Scopus | ID: covidwho-2029447

ABSTRACT

Pulmonary medical image processing is an effective diagnostic method for COVID-19, and CapsNet-based methods have achieved good performance. However, as cost-blind methods, these diagnostic methods only consider immediate and deterministic decisions, which easily lead to misdiagnosis and high costs. Therefore, based on a revised CapsNet, we propose a cost-sensitive three-way decision (3WD) method for COVID-19 diagnosis, named as Caps-3WD. To enhance the feature extraction ability for pneumonia areas, we introduce a Restage module to improve convolution layer of the original CapsNet. Further, to lighten the model, we introduce depth wise separable convolution to reconstruct decoder. Additionally, three options are considered in the decision set: infected, normal, and suspected, which are given different costs, respectively. The lowest-cost decision is chosen for each input. In the experimental analysis, we compare Caps-3WD with CNN-based and CapsNet-based methods on COVID-CXR dataset, which proves the effectiveness of 3WD and the superiority of Caps-3WD in COVID-19 diagnosis. © 2022 SPIE. Downloading of the is permitted for personal use only.

2.
Emerging Microbes & Infections ; : 1-25, 2022.
Article in English | MEDLINE | ID: covidwho-2028962

ABSTRACT

To further describe the effect of the "fragile population" and their "higher-risk" comorbidities on prognosis among hospitalized Omicron patients, this observational cohort study enrolled hospitalized patients confirmed with SARS-CoV-2 during the 2022 Omicron wave in Shanghai, China. The primary outcome was progression to severe or critical cases. The secondary outcome was viral shedding time from the first positive SARS-CoV-2 detection. A total of 847 participants were enrolled, most of who featured as advanced age (>70 years old: 30.34%), not fully vaccinated (55.84%), combined with at least 1 comorbidity (65.41%). Multivariate cox regression suggested age > 70 years old (aHR[95%CI] 0.78[0.61-0.99]), chronic kidney disease (CKD) stage 4-5 (aHR[95%CI] 0.61[0.46-0.80]), heart conditions (aHR[95%CI] 0.76[0.60-0.97]) would elongate viral shedding time and fully/booster vaccination (aHR[95%CI] 0.35[0.12-0.87]) would shorten this duration. Multivariate logistic regression suggested CKD stage 4-5 (aHR[95%CI] 3.21[1.45-7.27]), cancer (aHR[95%CI] 9.52[4.19-22.61]), and long-term bedridden status (aHR[95%CI] 4.94[2.36 -10.44]) were the "higher" risk factor compared with the elderly, heart conditions, metabolic disorders, isolated hypertension, etc. for severity while female (aHR[95%CI] 0.34[0.16-0.68]) and fully/booster Vaccination (aHR[95%CI] 0.35[0.12-0.87]) could provide protection from illness progression. CKD stage 4-5, cancer and long-term bedridden history were "higher-risk" factors among hospitalized Omicron patients for severity progression while full vaccination could provide protection from illness progression.

3.
Communications Biology ; 5(1):958, 2022.
Article in English | MEDLINE | ID: covidwho-2028733

ABSTRACT

Hydroxychloroquine (HCQ), a drug used to treat lupus and malaria, was proposed as a treatment for SARS-coronavirus-2 (SARS-CoV-2) infection, albeit with controversy. In vitro, HCQ effectively inhibits viral entry, but its use in the clinic has been hampered by conflicting results. A better understanding of HCQ's mechanism of actions in vitro is needed. Recently, anesthetics were shown to disrupt ordered clusters of monosialotetrahexosylganglioside1 (GM1) lipid. These same lipid clusters recruit the SARS-CoV-2 surface receptor angiotensin converting enzyme 2 (ACE2) to endocytic lipids, away from phosphatidylinositol 4,5 bisphosphate (PIP2) clusters. Here we employed super-resolution imaging of cultured mammalian cells (VeroE6, A549, H1793, and HEK293T) to show HCQ directly perturbs clustering of ACE2 receptor with both endocytic lipids and PIP2 clusters. In elevated (high) cholesterol, HCQ moves ACE2 nanoscopic distances away from endocytic lipids. In cells with resting (low) cholesterol, ACE2 primarily associates with PIP2 clusters, and HCQ moves ACE2 away from PIP2 clusters-erythromycin has a similar effect. We conclude HCQ inhibits viral entry through two distinct mechanisms in high and low tissue cholesterol and does so prior to inhibiting cathepsin-L. HCQ clinical trials and animal studies will need to account for tissue cholesterol levels when evaluating dosing and efficacy.

4.
Clinical and Translational Medicine ; 12(9):e1016, 2022.
Article in English | MEDLINE | ID: covidwho-2027332

ABSTRACT

BACKGROUND: To determine an appropriate dose of, and immunization schedule for, a vaccine SCoK against COVID-19 for an efficacy study;herein, we conducted randomized controlled trials to assess the immunogenicity and safety of this vaccine in adults. METHODS: These randomized, double-blind, placebo-controlled phase 1 and 2 trials of vaccine SCoK were conducted in Binhai District, Yan City, Jiangsu Province, China. Younger and older adult participants in phase 1 and 2 trials were sequentially recruited into different groups to be intramuscularly administered 20 or 40 mug vaccine SCoK or placebo. Participants were enrolled into our phase 1 and 2 studies to receive vaccine or placebo. RESULTS: No serious vaccine-related adverse events were observed in either trial. In both trials, local and systemic adverse reactions were absent or mild in most participants. In our phase 1 and 2 studies, the vaccine induced significantly increased neutralizing antibody responses to pseudovirus and live SARS-CoV-2. The vaccine induced significant neutralizing antibody responses to live SARS-CoV-2 on day 14 after the last immunization, with NT50s of 80.45 and 92.46 in participants receiving 20 and 40 mug doses, respectively;the seroconversion rates were 95.83% and 100%. The vaccine SCoK showed a similar safety and immunogenicity profiles in both younger participants and older participants. The vaccine showed better immunogenicity in phase 2 than in phase 1 clinical trial. Additionally, the incidence of adverse reactions decreased significantly in phase 2 clinical trial. The vaccine SCoK was well tolerated and immunogenic.

5.
American Journal Of Translational Research ; 14(8):5719-5729, 2022.
Article in English | MEDLINE | ID: covidwho-2027183

ABSTRACT

Patients with major psychiatric disorders (MPD) that include schizophrenia (SCH), bipolar disorder (BP), and major depressive disorder (MDD) are at increased risk for coronavirus disease 2019 (COVID-19). However, the safety and efficacy of COVID-19 vaccines in MPD patients have not been fully evaluated. This study aimed to investigate adverse events (AEs)/side effects and efficacy of COVID-19 vaccines in MPD patients. This retrospective study included 2034 patients with SCH, BP, or MDD who voluntarily received either BBIBP-CorV or Sinovac COVID-19 vaccines, and 2034 matched healthy controls. The incidence of AEs/side effects and the efficacy of COIVD-19 vaccinations among the two groups were compared. The risk ratio (RR) of side effects in patients with MPD was 0.60 (95% confidence interval [CI]: 0.53-0.68) after the first dose and 0.80 (95% CI: 0.65-0.99) following the second dose, suggesting a significantly lower risk in the MPD group versus healthy controls. The RRs of AEs did not differ between patients and controls. Notably, fully vaccinated patients exhibited a decreased risk of influenza with or without fever compared with controls (RR=0.38, 95% CI: 0.31-0.46;RR=0.23, 95% CI: 0.17-0.30;respectively). Further subgroup comparisons revealed a significantly lower risk of influenza with fever in MDD (RR=0.13, 95% CI: 0.08-0.21) and SCH (RR=0.24, 95% CI: 0.17-0.34) than BP (RR=0.85, 95% CI: 0.69-1.06) compared to controls. We conclude that the benefit-risk ratio of COVID-19 vaccination was more favorable in SCH or MDD versus BP when compared with controls. These data indicate that COVID-19 vaccines are safe and protective in patients with MPD from COVID-19.

6.
Clinical and Translational Gastroenterology ; 31:31, 2022.
Article in English | MEDLINE | ID: covidwho-2025671

ABSTRACT

BACKGROUND: An estimated 15%-29% of patients report new gastrointestinal symptoms after COVID-19 while 4% -31% report new depressive symptoms. These symptoms may be secondary to gut microbiome tryptophan metabolism and 5-hydroxytryptamine (5-HT)-based signaling. METHODS: This study utilized specimens from 2 patient cohorts: (1) fecal samples from patients with acute COVID-19 who participated in a randomized controlled trial testing prebiotic fiber;and (2) blood samples from patients with acute COVID-19. Six months after recovering from COVID-19, both cohorts answered questions related to gastrointestinal symptoms and anxiety or depression. Microbiome composition and function, focusing on tryptophan metabolism-associated pathways, and plasma 5-HT were assessed. RESULTS: In the first cohort (n=13), gut microbiome L-tryptophan biosynthesis during acute COVID-19 was decreased among those who developed more severe gastrointestinal symptoms (2.0-fold lower log activity comparing those with the most severe gastrointestinal symptoms versus those with no symptoms, P=0.06). All tryptophan pathways showed decreased activity among those with more GI symptoms. The same pathways were also decreased in those with the most severe mental health symptoms after COVID-19. In an untargeted analysis, 5 additional metabolic pathways significantly differed based on subsequent development of gastrointestinal symptoms. In the second cohort (n=39,), plasma 5-HT concentration at the time of COVID-19 was increased 5.1-fold in those with gastrointestinal symptoms alone compared to those with mental health symptoms alone (P=0.02). CONCLUSIONS: Acute gut microbiome-mediated reduction in 5-HT signaling may contribute to long-term gastrointestinal and mental health symptoms after COVID-19. Future studies should explore modification of 5-HT signaling to reduce post-COVID symptoms.

7.
Elife ; 11, 2022.
Article in English | PubMed | ID: covidwho-2025329

ABSTRACT

Large-scale populations in the world have been vaccinated with COVID-19 vaccines, however, breakthrough infections of SARS-CoV-2 are still growing rapidly due to the emergence of immune-evasive variants, especially Omicron. It is urgent to develop effective broad-spectrum vaccines to better control the pandemic of these variants. Here, we present a mosaic-type trimeric form of spike receptor-binding domain (mos-tri-RBD) as a broad-spectrum vaccine candidate, which carries the key mutations from Omicron and other circulating variants. Tests in rats showed that the designed mos-tri-RBD, whether used alone or as a booster shot, elicited potent cross-neutralizing antibodies against not only Omicron but also other immune-evasive variants. Neutralizing antibody ID50 titers induced by mos-tri-RBD were substantially higher than those elicited by homo-tri-RBD (containing homologous RBDs from prototype strain) or the BIBP inactivated COVID-19 vaccine (BBIBP-CorV). Our study indicates that mos-tri-RBD is highly immunogenic, which may serve as a broad-spectrum vaccine candidate in combating SARS-CoV-2 variants including Omicron.

8.
Natural Gas Industry ; 42(7):1-6, 2022.
Article in Chinese | Scopus | ID: covidwho-2024390

ABSTRACT

Natural gas will play more and more important role in the sustainable low-carbon development mode characterized by low energy consumption, low pollution and low emission. It has been and will continue to be the focus of attention. The 28th World Gas Conference (WGC2022) was held on May 23-27, 2022 in Daegu, South Korea. The conference summarized the progress of world natural gas in the past four years, analyzed and judged the future development trend, and reached seven consensuses: (1) Natural gas is not only a transitional fuel, but also a basic fuel for future development. (2) Supply and demand value chain of natural gas has high flexibility and adaptability, and supply diversification has become a development advantage. (3) With the effect of the rapid increase of oil and gas price, the reversal of natural gas to coal has intensified the rapid growth of global carbon emissions. (4) Structural tension is emerging in the global LNG market, and the number of long-term agreement contracts will show an increasing trend. (5) The coordinated development of natural gas and hydrogen will accelerate the arrival of the low-carbon era. (6) Methane monitoring and leakage measurement technology in the natural gas industry will become the next important innovation. (7) Governments of various countries have continuously raised the minimum level of underground gas storage, and successively issued incentive policies to increase gas reserves and production. Based on the experience, the following suggestions are put forward for the development of China's natural gas: (1) Continue to highlight the important position of the natural gas industry, increase exploration and development, and improve supply capacity and voice;(2) To adapt to the new setup of international natural gas supply caused by the COVID-19 and the conflict between Russia and Ukraine, and to formulate overall strategies for natural gas import and export trade;(3) Attach importance to LNG business, scientifically arrange the construction of LNG import supporting facilities, and take the initiative to cooperate with natural gas resource countries;(4) The whole industrial chain of natural gas and hydrogen business should be planned and deployed together, and hydrogen and natural gas infrastructure construction should be linked up effectively;(5) Increase policy support, strengthen infrastructure construction such as underground gas storage and LNG terminal, reserve more energy to develop confidence, and build a strong defense line for energy security. © 2022 Natural Gas Industry Journal Agency. All rights reserved.

9.
Front Public Health ; 10:926395, 2022.
Article in English | PubMed | ID: covidwho-2022953

ABSTRACT

OBJECTIVE: Thousands of healthcare workers on the frontlines who have been battling the COVID-19 pandemic could face emotional and mental health risks even after their critical pandemic work. This study examined the impact of affective rumination on emotional exhaustion and the spillover effect of affective rumination on unhealthy food consumption among healthcare workers during recuperation. METHODS: A total of 418 frontline healthcare workers from 10 Chinese medical institutions were recruited through random cluster sampling. A linear mixed model in SPSS25.0 was performed for hierarchical regression to analyze the effect of affective rumination on unhealthy food consumption via emotional exhaustion. A conditional process analysis was employed to investigate the moderating role of family support in the mediating effect of emotional exhaustion. RESULTS: Front-line healthcare workers scored at a medium level on an emotional exhaustion scale (2.45 ± 0.88). Affective rumination mediated by emotional exhaustion had a significant positive predictive effect on unhealthy food consumption. The indirect effect accounted for ~43.9% of the total effect. Family support amplified the effect of emotional exhaustion on unhealthy food consumption (β = 0.092, p < 0.05). CONCLUSION: Affective rumination could be a cause of emotional exhaustion and unhealthy food consumption. First-line healthcare workers could be screened for possible emotional exhaustion through the evaluation of affective rumination in order to provide them with targeted interventions. Family support did not prove to be beneficial in all cases as it enhanced the positive effect of emotional exhaustion on unhealthy eating in the current study. Therefore, family support should be carefully integrated in future interventions.

10.
Frontiers in Pharmacology ; 13:936925, 2022.
Article in English | MEDLINE | ID: covidwho-2022836

ABSTRACT

Background: Coronavirus disease 2019 (COVID-19) was declared a global pandemic in March 2020 by the World Health Organization (WHO). As of July 2, 2022, COVID-19 has caused more than 545 million infections and 6.3 million deaths worldwide, posing a significant threat to human health. Currently, there is still a lack of effective prevention and control strategies for the variation and transmission of SARS-CoV-2. Traditional Chinese medicine (TCM), which has a unique theoretical system, has treated various conditions for thousands of years. Importantly, recent studies have revealed that TCM contributed significantly to COVID-19. SanHanHuaShi (SHHS) granules, a Chinese herbal medicine, which has been included in Protocol for the Diagnosis and Treatment of Novel Coronavirus Disease 2019 (6th to 9th editions) issued by the National Health Commission of China and used to prevent and treat COVID-19 disease. A previous retrospective cohort study showed that SHHS could significantly reduce the severity of mild and moderate COVID-19. However, there is an absence of high-quality randomized controlled clinical studies to confirm the clinical effectiveness of SHHS. Therefore, a clinical study protocol and a statistical analysis plan were designed to investigate the efficacy and safety of SHHS for the prevention and treatment of COVID-19. This study will increase the integrity and data transparency of the clinical research process, which is of great significance for improving the practical application of SHHS granules in the future. Methods and analysis: The study was designed as a 7-day, randomized, parallel controlled, open-label, noninferiority clinical trial of positive drugs. A total of 240 patients with mild and moderate COVID-19 will be enrolled and randomly assigned to receive SanHanHuaShi granules or LianHuaQingWen granules treatment in a 1:1 ratio. Disease classification, vital signs, SARS-CoV-2 nucleic acid testing, symptoms, medications, adverse events, and safety evaluations will be recorded at each visit. The primary outcome will be the clinical symptom recovery rate. Secondary outcomes will include the recovery time of clinical symptoms, negative conversion time of SARS-CoV-2 nucleic acid test negative conversion rate, hospitalization time, antipyretic time, rate of conversion to severe patients, and time and rate of single symptom recovery. Adverse incidents and safety assessments will be documented. All data will be analyzed using a predetermined statistical analysis plan, including our method for imputation of missing data, primary and secondary outcome analyses, and safety outcomes. Discussion: The results of this study will provide robust evidence to confirm the effectiveness and safety of SHHS in the treatment of COVID-19. Clinical Trial Registration: http://www.chictr.org.cn. Trial number: ChiCTR2200058080. Registered on 29 March 2022.

11.
Frontiers in Molecular Biosciences ; 9, 2022.
Article in English | Web of Science | ID: covidwho-2022800

ABSTRACT

The antimicrobial resistance (AMR) crisis from bacterial pathogens is frequently emerging and rapidly disseminated during the sustained antimicrobial exposure in human-dominated communities, posing a compelling threat as one of the biggest challenges in humans. The frequent incidences of some common but untreatable infections unfold the public health catastrophe that antimicrobial-resistant pathogens have outpaced the available countermeasures, now explicitly amplified during the COVID-19 pandemic. Nowadays, biotechnology and machine learning advancements help create more fundamental knowledge of distinct spatiotemporal dynamics in AMR bacterial adaptation and evolutionary processes. Integrated with reliable diagnostic tools and powerful analytic approaches, a collaborative and systematic surveillance platform with high accuracy and predictability should be established and implemented, which is not just for an effective controlling strategy on AMR but also for protecting the longevity of valuable antimicrobials currently and in the future.

12.
Risk Management & Healthcare Policy ; 15:1593-1605, 2022.
Article in English | MEDLINE | ID: covidwho-2022232

ABSTRACT

Purpose: The coronavirus disease 2019 (COVID-19) pandemic disrupted the supply of blood globally, resulting in numerous studies focusing on the challenges in maintaining blood supply, and the responses to it, in countries with a mixed blood donation model. This study explored blood donation challenges and mobilization mechanisms in North China, which employs a non-remunerative donation model, during the COVID-19 pandemic's first wave. Materials and Methods: A qualitative approach was adopted to investigate blood donation practices in Chengde from April to June 2020. Data were collected from eight blood donors, six potential donors, three blood donation station leaders, and two government officials, through semi-structured interviews. Results: The major challenge for blood supply was decreased blood donations, owing to lockdown restrictions, and individual and familial apprehensions. Mobilization mechanisms included bureaucratic and ideological mobilization. However, although group blood donation alleviates the pressure on supply chains during emergencies, it is detrimental to the cultivation of civic engagement in the long run. Conclusion: This study contributes to the understanding of how countries with uncompensated blood donation models respond to public health emergencies. It suggests that striking a balance between the society's and the state's perception of blood donation would allow the state to incorporate the different "voices" of society, and devise an inclusive blood donation policy.

13.
Bmc Medical Research Methodology ; 22(1), 2022.
Article in English | Web of Science | ID: covidwho-2021242

ABSTRACT

Background One critical variable in the time series analysis is the change point, which is the point where an abrupt change occurs in chronologically ordered observations. Existing parametric models for change point detection, such as the linear regression model and the Bayesian model, require that observations are normally distributed and that the trend line cannot have extreme variability. To overcome the limitations of the parametric model, we apply a nonparametric method, the Mann-Kendall-Sneyers (MKS) test, to change point detection for the state-level COVID-19 case time series data of the United States in the early outbreak of the pandemic. Methods The MKS test is implemented for change point detection. The forward sequence and the backward sequence are calculated based on the new weekly cases between March 22, 2020 and January 31, 2021 for each of the 50 states. Points of intersection between the two sequences falling within the 95% confidence intervals are identified as the change points. The results are compared with two other change point detection methods, the pruned exact linear time (PELT) method and the regression-based method. Also, an open-access tool by Microsoft Excel is developed to facilitate the model implementation. Results By applying the MKS test to COVID-19 cases in the United States, we have identified that 30 states (60.0%) have at least one change point within the 95% confidence intervals. Of these states, 26 states have one change point, 4 states (i.e., LA, OH, VA, and WA) have two change points, and one state (GA) has three change points. Additionally, most downward changes appear in the Northeastern states (e.g., CT, MA, NJ, NY) at the first development stage (March 23 through May 31, 2020);most upward changes appear in the Western states (e.g., AZ, CA, CO, NM, WA, WY) and the Midwestern states (e.g., IL, IN, MI, MN, OH, WI) at the third development stage (November 19, 2020 through January 31, 2021). Conclusions This study is among the first to explore the potential of the MKS test applied for change point detection of COVID-19 cases. The MKS test is characterized by several advantages, including high computational efficiency, easy implementation, the ability to identify the change of direction, and no assumption for data distribution. However, due to its conservative nature in change point detection and moderate agreement with other methods, we recommend using the MKS test primarily for initial pattern identification and data pruning, especially in large data. With modification, the method can be further applied to other health data, such as injuries, disabilities, and mortalities.

14.
Sage Open ; 12(3), 2022.
Article in English | Web of Science | ID: covidwho-2021085

ABSTRACT

Based on online survey data from 2020, the present study employed a logit model to examine the effects of COVID-19 on household financial behaviors in China. Additionally, the KHB (Kohler, Karlson, Holm) model was employed to explore the pathway through which COVID-19 affects household financial behaviors. These analyses revealed that household saving and borrowing behaviors were more sensitive to COVID-19 than insurance and investment behaviors. Moreover, the effects of COVID-19 on household saving and investment behaviors were found to be mediated by attitudes toward COVID-19. These findings suggest that more effective measures to reduce households' panic attitude to public health emergencies can diminish fluctuations in household financial behaviors in the short term.

15.
28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; : 4752-4762, 2022.
Article in English | Scopus | ID: covidwho-2020403

ABSTRACT

Human daily activities, such as working, eating out, and traveling, play an essential role in contact tracing and modeling the diffusion patterns of the COVID-19 pandemic. However, individual-level activity data collected from real scenarios are highly limited due to privacy issues and commercial concerns. In this paper, we present a novel framework based on generative adversarial imitation learning, to generate artificial activity trajectories that retain both the fidelity and utility of the real-world data. To tackle the inherent randomness and sparsity of irregular-sampled activities, we innovatively capture the spatiotemporal dynamics underlying trajectories by leveraging neural differential equations. We incorporate the dynamics of continuous flow between consecutive activities and instantaneous updates at observed activity points in temporal evolution and spatial transformation. Extensive experiments on two real-world datasets show that our proposed framework achieves superior performance over state-of-the-art baselines in terms of improving the data fidelity and data utility in facilitating practical applications. Moreover, we apply the synthetic data to model the COVID-19 spreading, and it achieves better performance by reducing the simulation MAPE over the baseline by more than 50%. The source code is available online: https://github.com/tsinghua-fib-lab/Activity-Trajectory-Generation. © 2022 ACM.

16.
28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; : 4832-4833, 2022.
Article in English | Scopus | ID: covidwho-2020400

ABSTRACT

Exploring the vast amount of rapidly growing scientific text data is highly beneficial for real-world scientific discovery. However, scientific text mining is particularly challenging due to the lack of specialized domain knowledge in natural language context, complex sentence structures in scientific writing, and multi-modal representations of scientific knowledge. This tutorial presents a comprehensive overview of recent research and development on scientific text mining, focusing on the biomedical and chemistry domains. First, we introduce the motivation and unique challenges of scientific text mining. Then we discuss a set of methods that perform effective scientific information extraction, such as named entity recognition, relation extraction, and event extraction. We also introduce real-world applications such as textual evidence retrieval, scientific topic contrasting for drug discovery, and molecule representation learning for reaction prediction. Finally, we conclude our tutorial by demonstrating, on real-world datasets (COVID-19 and organic chemistry literature), how the information can be extracted and retrieved, and how they can assist further scientific discovery. We also discuss the emerging research problems and future directions for scientific text mining. © 2022 Owner/Author.

17.
28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; : 2882-2892, 2022.
Article in English | Scopus | ID: covidwho-2020398

ABSTRACT

To control the outbreak of COVID-19, efficient individual mobility intervention for EPidemic Control (EPC) strategies are of great importance, which cut off the contact among people at epidemic risks and reduce infections by intervening the mobility of individuals. Reinforcement Learning (RL) is powerful for decision making, however, there are two major challenges in developing an RL-based EPC strategy: (1) the unobservable information about asymptomatic infections in the incubation period makes it difficult for RL's decision-making, and (2) the delayed rewards for RL causes the deficiency of RL learning. Since the results of EPC are reflected in both daily infections (including unobservable asymptomatic infections) and long-term cumulative cases of COVID-19, it is quite daunting to design an RL model for precise mobility intervention. In this paper, we propose a Variational hiErarcHICal reinforcement Learning method for Epidemic control via individual-level mobility intervention, namely Vehicle. To tackle the above challenges, Vehicle first exploits an information rebuilding module that consists of a contact-risk bipartite graph neural network and a variational LSTM to restore the unobservable information. The contact-risk bipartite graph neural network estimates the possibility of an individual being an asymptomatic infection and the risk of this individual spreading the epidemic, as the current state of RL. Then, the Variational LSTM further encodes the state sequence to model the latency of epidemic spreading caused by unobservable asymptomatic infections. Finally, a Hierarchical Reinforcement Learning framework is employed to train Vehicle, which contains dual-level agents to solve the delayed reward problem. Extensive experimental results demonstrate that Vehicle can effectively control the spread of the epidemic. Vehicle outperforms the state-of-the-art baseline methods with remarkably high-precision mobility interventions on both symptomatic and asymptomatic infections. © 2022 Owner/Author.

18.
International Wound Journal ; 29:29, 2022.
Article in English | MEDLINE | ID: covidwho-2019376

ABSTRACT

This retrospective study aims to explore whether the COVID-19 pandemic altered patient conditions and surgery outcomes by studying 213 pressure injury (PI) patients who underwent surgery during 2016 to 2019 (pre-COVID) and 2020 to 2021 (COVID) in Taiwan. We extracted patient demographics, surgical and blood test records, preoperative vital signs, and flap surgery outcomes. In total, 464 surgeries were performed, including 308 pre-COVID and 156 COVID. During the COVID period, there were more patients presenting with dementia, and it had significantly more patients with >12 000 white blood cells/muL (24.03% vs 15.59%, P = 0.029), higher C-reactive protein levels (7.13 +/- 6.36 vs 5.58 +/- 5.09 mg/dL, P = 0.014), pulse rates (86.67 +/- 14.76 vs 81.26 +/- 13.66 beats/min, P < 0.001), and respiratory rates (17.87 +/- 1.98 vs 17.31 +/- 2.39 breaths/min, P = 0.009) but lower haemoglobin levels (9.75 +/- 2.02 vs 10.43 +/- 1.67 mg/dL, P < 0.001) preoperatively. There were no between-group differences in flap surgery outcomes but had fewer flap surgeries during COVID-19. Thus, PI patient condition was generally poor during the COVID-19 pandemic because of reduced access to medical treatment;this problem may be resolved through holistic care during a future pandemic or pandemic-like situation.

19.
IEEE Journal of Biomedical & Health Informatics. PP ; 06:06, 2022.
Article in English | MEDLINE | ID: covidwho-2018931

ABSTRACT

The emergence of coronavirus disease 2019 (COVID-19) has had a significant impact on healthcare and the economy. To understand the COVID-19 disease mechanism and the related biological functions in the short term, both clinicians and scientists are making every effort to find an efficient way to collect and explore the vast amount of COVID-19-related knowledge. Representation learning has been highlighted as a promising method to construct a COVID-19 knowledge graph. However, most existing representation learning models do not perform very well when dealing with the COVID-19 knowledge graph because of its low-connected star-like structure and various nonlinear relationships. In this study, we propose a novel representation learning model called translation on hyperplanes with an activation operation and similar semantic sampling (SimH) for COVID-19 knowledge graphs. Specifically, the activation operation is designed to provide additional interaction features for low-in-degree entities by interaction feature permutation and share relation-specific partitions of pairwise interactions by an activation vector. As a result, problems that fewer features are captured from low-in-degree entities are alleviated. Moreover, hyperplane projection is introduced to the distance-based scoring function so that nonlinear relationships can be modeled while the lower complexity is maintained, as compared to other nonlinear models. To consider that negative sampling can improve the embedding quality of fact triples, a negative triplet sampling method that adaptively replaces entities with similar semantics is introduced to generate reliable negative triplets. Extensive experiments are conducted on the COVID-19-Concepts dataset. The experimental results show that our SimH model achieves significant improvements in prediction and classification accuracy over existing knowledge representation learning models.

20.
10th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2022 ; 2022-June:1004-1009, 2022.
Article in English | Scopus | ID: covidwho-2018923

ABSTRACT

Coronavirus pandemics have influenced people's daily life seriously since 2019. Authorized organizations suggested people wear a mask in public areas can significantly reduce the probability of getting infected. Thus, we proposed a method based on a simple convolutional neural network (CNN) to perform mask detection. The whole developing process was divided into two stages and mainly used three datasets (dataset_l, dataset_2 and dataset_3). Dataset_1 has images of people with and without masks. Dataset_2 and dataset_3 have one more category-images of people wearing masks incorrectly. The first stage was to train the model based on dataset_1 and it achieved 100% accuracy on validation set. It could also be applied to another two similar datasets without any training on them with accuracy 73.55% and 66.80% respectively. In the second stage, to detect people wearing masks incorrectly, the same model was trained based on dataset_2. The accuracy of this model reached 99.34%. However, when applying it directly to dataset_3, only 44.50% accuracy was achieved. To improve the accuracy, the distribution of dataset_2 and dataset_3 was rearranged. Finally, the accuracy of the model for dataset_3 was nearly 80%. We concluded that generally deep learning models would have better generalization on mask-detection tasks and our model was good at handling two-label mask dataset. © 2022 IEEE.

SELECTION OF CITATIONS
SEARCH DETAIL