ABSTRACT
The COVID-19 outbreak devastated business operations and the world economy, especially for small and medium-sized enterprises (SMEs). With limited capital, poorer risk tolerance, and difficulty in withstanding prolonged crises, SMEs are more vulnerable to pandemics and face a higher risk of shutdown. This research sought to establish a model response to shutdown risk by investigating two questions: How do you measure SMEs' shutdown risk due to pandemics? How do SMEs reduce shutdown risk? To the best of our knowledge, existing studies only analyzed the impact of the pandemic on SMEs through statistical surveys and trivial recommendations. Particularly, there is no case study focusing on an elaboration of SMEs' shutdown risk. We developed a model to reduce cognitive uncertainty and differences in opinion among experts on COVID-19. The model was built by integrating the improved Dempster's rule of combination and a Bayesian network, where the former is based on the method of weight assignment and matrix analysis. The model was first applied to a representative SME with basic characteristics for survival analysis during the pandemic. The results show that this SME has a probability of 79% on a lower risk of shutdown, 15% on a medium risk of shutdown, and 6% of high risk of shutdown. SMEs solving the capital chain problem and changing external conditions such as market demand are more difficult during a pandemic. Based on the counterfactual elaboration of the inferred results, the probability of occurrence of each risk factor was obtained by simulating the interventions. The most likely causal chain analysis based on counterfactual elaboration revealed that it is simpler to solve employee health problems. For the SMEs in the study, this approach can reduce the probability of being at high risk of shutdown by 16%. The results of the model are consistent with those identified by the SME respondents, which validates the model.
ABSTRACT
It has been witnessed that digital technology has the potential to improve the efficiency of emergent healthcare management in COVID-19, which however has not been widely adopted due to unclear definition and configuration. This research aims to propose a proof of concept of digital twins for emergent healthcare management through configuring the cyber and functional interdependencies of healthcare systems at local and city levels. Critical interdependencies of healthcare systems have been firstly identified at both levels, then the information and associated cyber and functional interdependencies embedded in seven critical hospital information systems (HISs) have been identified and mapped. The proposed conceptual digital twin-based approach has been then developed for information coordination amongst these critical HISs at both local and city levels based on permissioned blockchain to (1) integrate and manage the information from seven critical HISs, and further (2) predict the demands of medical resources according to patient trajectory. A case study has been finally conducted at three hospitals in London during the COVID-19 period, and the results showed that the developed framework of blockchain-integrated digital twins is a promising way to provide more accurate and timely procurement information to decision-makers and can effectively support evidence-based decisions on medical resource allocation in the pandemic. © 2023 ICE Publishing: All rights reserved.
ABSTRACT
The sudden admission of many patients with similar needs caused by the COVID-19 (SARS-CoV-2) pandemic forced health care centers to temporarily transform units to respond to the crisis. This process greatly impacted the daily activities of the hospitals. In this paper, we propose a two-step approach based on process mining and discrete-event simulation for sizing a recovery unit dedicated to COVID-19 patients inside a hospital. A decision aid framework is proposed to help hospital managers make crucial decisions, such as hospitalization cancellation and resource sizing, taking into account all units of the hospital. Three sources of patients are considered: (i) planned admissions, (ii) emergent admissions representing day-to-day activities, and (iii) COVID-19 admissions. Hospitalization pathways have been modeled using process mining based on synthetic medico-administrative data, and a generic model of bed transfers between units is proposed as a basis to evaluate the impact of those moves using discrete-event simulation. A practical case study in collaboration with a local hospital is presented to assess the robustness of the approach. Note to Practitioners—In this paper we develop and test a new decision-aid tool dedicated to bed management, taking into account exceptional hospitalization pathways such as COVID-19 patients. The tool enables the creation of a dedicated COVID-19 intensive care unit with specific management rules that are fine-tuned by considering the characteristics of the pandemic. Health practitioners can automatically use medico-administrative data extracted from the information system of the hospital to feed the model. Two execution modes are proposed: (i) fine-tuning of the staffed beds assignment policies through a design of experiment and (ii) simulation of user-defined scenarios. A practical case study in collaboration with a local hospital is presented. The results show that our model was able to find the strategy to minimize the number of transfers and the number of cancellations while maximizing the number of COVID-19 patients taken into care was to transfer beds to the COVID-19 ICU in batches of 12 and to cancel appointed patients using ICU when the department hit a 90% occupation rate. IEEE
ABSTRACT
Objective: To compare the efficacy of the combination of abidol, lopinavir/ritonavir plus recombinant interferon alpha-2b (rIFNalpha-2b) and the combination of lopinavir/ritonavir plus rIFNalpha-2b for patients with COVID-19 in Zhejiang province. Method(s): A multicenter prospective study was carried out to compare the efficacy of triple combination antiviral therapy and dual combination antiviral therapy in 15 medical institutions of Zhejiang province during January 22 to February 16, 2020. All patients were treated with rIFNalpha-2b (5 million U, 2 times/d) aerosol inhalation, in addition 196 patients were treated with abidol (200 mg, 3 times/d) + lopinavir/ritonavir (2 tablets, 1 time/12 h) (triple combination group) and 41 patients were treated with lopinavir/ritonavir (2 tablets, 1 time/12 h) (dual combination group). The patients who received triple combination antiviral therapy were further divided into three subgroups: <48 h, 3-5 d and >5 d according the time from the symptom onset to medication starting. The therapeutic efficacy was compared between triple combination group and dual combination group, and compared among 3 subgroups of patients receiving triple combination antiviral therapy. SPSS 17.0 software was used to analyze the data. Result(s): The virus nucleic acid-negative conversion time in respiratory tract specimens was (12.2+/-4.7) d in the triple combination group, which was shorter than that in the dual combination group [(15.0+/-5.0) d] (t=6.159, P<0.01). The length of hospital stay in the triple combination group [12.0 (9.0, 17.0) d] was also shorter than that in the dual combination group [15.0 (10.0, 18.0) d] (H=2.073, P<0.05). Compared with the antiviral treatment which was started within after the symptom onset of in the triple combination group, the time from the symptom onset to the viral negative conversion was 13.0 (10.0, 17.0), 17.0 (13.0, 22.0) and 21.0 (18.0, 24.0) d in subgroups of 48 h, 3-5 d and >5 d, respectively (Z=32.983, P<0.01), while the time from antiviral therapy to viral negative conversion was (11.8+/-3.9), (13.5+/-5.1) and (11.2+/-4.3) d, respectively(Z=6.722, P<0.05). Conclusion(s): The triple combination antiviral therapy of abidol, lopinavir/litonavir and rIFNalpha-2b shows shorter viral shedding time and shorter hospitalization time, compared with the dual combination antiviral therapy;and the earlier starting triple combination antiviral therapy will result in better antiviral efficacy.Copyright © 2020 by the Chinese Medical Association.
ABSTRACT
Objective To explore the genomic changes of human olfactory neuroepithelial cells after the novel coronavirus (SARS-COV-2) infecting the human body, and establish a protein-protein interaction (PPI) network of differentially expressed genes (DEGs), in order to understand the impact of SARS-COV-2 infection on human olfactory neuroepithelial cells, and provide reference for the prevention and treatment of new coronavirus pneumonia. Methods The public dataset GSE151973 was analyzed by NetworkAnalyst. DEGs were selected by conducting Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway analysis. PPI network, DEGs-microRNA regulatory network, transcription factor-DEGs regulatory network, environmental chemicals-DEGs regulatory network, and drug-DEGs regulatory network were created and visualized by using Cytoscape 3.7.2. Results After SAR-COV-2 invading human olfactory neuroepithelial cells, part of the gene expression profile was significantly up-regulated or down-regulated. A total of 568 DEGs were found, including 550 up-regulated genes (96.8%) and 18 down-regulated genes (3.2%). DEGs were mainly involved in biological processes such as endothelial development and angiogenesis of the olfactory epithelium, and the expression of molecular functions such as the binding of the N-terminal myristylation domain. PPI network suggested that RTP1 and RTP2 were core proteins. MAZ was the most influential transcription factor. Hsa-mir-26b-5p had the most obvious interaction with DEGs regulation. Environmental chemical valproic acid and drug ethanol had the most influence on the regulation of DEG. Conclusion The gene expression of olfactory neuroepithelial cells is significantly up-regulated or down-regulated after infection with SAR-COV-2. SARS-CoV-2 may inhibit the proliferation and differentiation of muscle satellite cells by inhibiting the function of PAX7. RTP1 and RTP2 may resist SARS-CoV-2 by promoting the ability of olfactory receptors to coat the membrane and enhancing the ability of olfactory receptors to respond to odorant ligands. MAZ may regulate DEGs by affecting cell growth and proliferation. Micro RNA, environmental chemicals and drugs also play an important role in the anti-SAR-COV-2 infection process of human olfactory neuroepithelial cells.Copyright © 2022 Editorial Department of Journal of Shanghai Second Medical University. All rights reserved.
ABSTRACT
Objective: To compare the efficacy of the combination of abidol, lopinavir/ritonavir plus recombinant interferon alpha-2b (rIFNalpha-2b) and the combination of lopinavir/ritonavir plus rIFNalpha-2b for patients with COVID-19 in Zhejiang province. Method(s): A multicenter prospective study was carried out to compare the efficacy of triple combination antiviral therapy and dual combination antiviral therapy in 15 medical institutions of Zhejiang province during January 22 to February 16, 2020. All patients were treated with rIFNalpha-2b (5 million U, 2 times/d) aerosol inhalation, in addition 196 patients were treated with abidol (200 mg, 3 times/d) + lopinavir/ritonavir (2 tablets, 1 time/12 h) (triple combination group) and 41 patients were treated with lopinavir/ritonavir (2 tablets, 1 time/12 h) (dual combination group). The patients who received triple combination antiviral therapy were further divided into three subgroups: <48 h, 3-5 d and >5 d according the time from the symptom onset to medication starting. The therapeutic efficacy was compared between triple combination group and dual combination group, and compared among 3 subgroups of patients receiving triple combination antiviral therapy. SPSS 17.0 software was used to analyze the data. Result(s): The virus nucleic acid-negative conversion time in respiratory tract specimens was (12.2+/-4.7) d in the triple combination group, which was shorter than that in the dual combination group [(15.0+/-5.0) d] (t=6.159, P<0.01). The length of hospital stay in the triple combination group [12.0 (9.0, 17.0) d] was also shorter than that in the dual combination group [15.0 (10.0, 18.0) d] (H=2.073, P<0.05). Compared with the antiviral treatment which was started within after the symptom onset of in the triple combination group, the time from the symptom onset to the viral negative conversion was 13.0 (10.0, 17.0), 17.0 (13.0, 22.0) and 21.0 (18.0, 24.0) d in subgroups of 48 h, 3-5 d and >5 d, respectively (Z=32.983, P<0.01), while the time from antiviral therapy to viral negative conversion was (11.8+/-3.9), (13.5+/-5.1) and (11.2+/-4.3) d, respectively(Z=6.722, P<0.05). Conclusion(s): The triple combination antiviral therapy of abidol, lopinavir/litonavir and rIFNalpha-2b shows shorter viral shedding time and shorter hospitalization time, compared with the dual combination antiviral therapy;and the earlier starting triple combination antiviral therapy will result in better antiviral efficacy.Copyright © 2020 by the Chinese Medical Association.
ABSTRACT
Objective To explore the genomic changes of human olfactory neuroepithelial cells after the novel coronavirus (SARS-COV-2) infecting the human body, and establish a protein-protein interaction (PPI) network of differentially expressed genes (DEGs), in order to understand the impact of SARS-COV-2 infection on human olfactory neuroepithelial cells, and provide reference for the prevention and treatment of new coronavirus pneumonia. Methods The public dataset GSE151973 was analyzed by NetworkAnalyst. DEGs were selected by conducting Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway analysis. PPI network, DEGs-microRNA regulatory network, transcription factor-DEGs regulatory network, environmental chemicals-DEGs regulatory network, and drug-DEGs regulatory network were created and visualized by using Cytoscape 3.7.2. Results After SAR-COV-2 invading human olfactory neuroepithelial cells, part of the gene expression profile was significantly up-regulated or down-regulated. A total of 568 DEGs were found, including 550 up-regulated genes (96.8%) and 18 down-regulated genes (3.2%). DEGs were mainly involved in biological processes such as endothelial development and angiogenesis of the olfactory epithelium, and the expression of molecular functions such as the binding of the N-terminal myristylation domain. PPI network suggested that RTP1 and RTP2 were core proteins. MAZ was the most influential transcription factor. Hsa-mir-26b-5p had the most obvious interaction with DEGs regulation. Environmental chemical valproic acid and drug ethanol had the most influence on the regulation of DEG. Conclusion The gene expression of olfactory neuroepithelial cells is significantly up-regulated or down-regulated after infection with SAR-COV-2. SARS-CoV-2 may inhibit the proliferation and differentiation of muscle satellite cells by inhibiting the function of PAX7. RTP1 and RTP2 may resist SARS-CoV-2 by promoting the ability of olfactory receptors to coat the membrane and enhancing the ability of olfactory receptors to respond to odorant ligands. MAZ may regulate DEGs by affecting cell growth and proliferation. Micro RNA, environmental chemicals and drugs also play an important role in the anti-SAR-COV-2 infection process of human olfactory neuroepithelial cells.
ABSTRACT
In this study, Delphi method was used to conduct a questionnaire survey on 12 experts to determine the indicators system and the corresponding weight for early warning features of SARS-CoV-2 Omicron in Tianjin.The positive indexes of experts in three rounds of consultations were both 100%. The experts' authority coefficient was 0.79. The Kendall's W coordination coefficients were 0.375, 0.356 and 0.385 respectively (all P<0.05). The indicators system for early warning features of 2019-nCoV Omicron variant had 5 first-level indicators, 10 second-level indicators and 52 third-level indicators. The weight of each indicator was also determined.
Subject(s)
COVID-19 , SARS-CoV-2 , Humans , Delphi Technique , Surveys and QuestionnairesABSTRACT
This paper assesses the potential risks of epidemic situation and public opinion during the Beijing Winter Olympic Games by analyzing the epidemic situation and public opinion of the Tokyo Olympic Games. The results show that there is a strong time-lag correlation between the COVID-19 epidemic and the public opinion of the Tokyo Olympics. For the epidemic situation, the multi-agent modeling method is used at the city level to simulate the possible spread of diseases in the city where the event was held. At the Olympic village level, the modified the SEIR transmission model is modified to simulate the virus transmission in the Olympic Village during the Beijing Winter Olympic Games. At the end, the risk analysis of the Beijing Winter Olympic Games is carried out based on the time series prediction model. © 2022, Editorial Board of Journal of the University of Electronic Science and Technology of China. All right reserved.
ABSTRACT
Objective To explore the genomic changes of human olfactory neuroepithelial cells after the novel coronavirus (SARS-COV-2) infecting the human body, and establish a protein-protein interaction (PPI) network of differentially expressed genes (DEGs), in order to understand the impact of SARS-COV-2 infection on human olfactory neuroepithelial cells, and provide reference for the prevention and treatment of new coronavirus pneumonia. Methods The public dataset GSE151973 was analyzed by NetworkAnalyst. DEGs were selected by conducting Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway analysis. PPI network, DEGs-microRNA regulatory network, transcription factor-DEGs regulatory network, environmental chemicals-DEGs regulatory network, and drug-DEGs regulatory network were created and visualized by using Cytoscape 3.7.2. Results After SAR-COV-2 invading human olfactory neuroepithelial cells, part of the gene expression profile was significantly up-regulated or down-regulated. A total of 568 DEGs were found, including 550 up-regulated genes (96.8%) and 18 down-regulated genes (3.2%). DEGs were mainly involved in biological processes such as endothelial development and angiogenesis of the olfactory epithelium, and the expression of molecular functions such as the binding of the N-terminal myristylation domain. PPI network suggested that RTP1 and RTP2 were core proteins. MAZ was the most influential transcription factor. Hsa-mir-26b-5p had the most obvious interaction with DEGs regulation. Environmental chemical valproic acid and drug ethanol had the most influence on the regulation of DEG. Conclusion The gene expression of olfactory neuroepithelial cells is significantly up-regulated or down-regulated after infection with SAR-COV-2. SARS-CoV-2 may inhibit the proliferation and differentiation of muscle satellite cells by inhibiting the function of PAX7. RTP1 and RTP2 may resist SARS-CoV-2 by promoting the ability of olfactory receptors to coat the membrane and enhancing the ability of olfactory receptors to respond to odorant ligands. MAZ may regulate DEGs by affecting cell growth and proliferation. Micro RNA, environmental chemicals and drugs also play an important role in the anti-SAR-COV-2 infection process of human olfactory neuroepithelial cells. Copyright © 2022 Editorial Department of Journal of Shanghai Second Medical University. All rights reserved.
ABSTRACT
A passenger flow time series forecasting method based on empirical mode decomposition (EMD) and K-nearest neighbor nonparametric regression (KNN) was proposed. Based on the principle of EMD and KNN algorithm, the EMD-KNN combined algorithm flow was constructed on the basis of improving KNN prediction method. According to the characteristics that the time series trend of passenger flow has changed obviously due to the influence of COVID-19 epidemic situation in the example stations. BP structural breakpoint detection method was used to identify three structural breakpoints, and the time series segment with the closest passenger flow change trend to the forecast day was selected for empirical mode decomposition. The decomposed sequences were reorganized into high-frequency, low-frequency and trend sequences, and then the K-nearest neighbor algorithm considering weight was used to predict, and the final prediction results were obtained by superposition, and compared with the prediction results of single KNN algorithm and ARIMA model. The results show that the prediction accuracy of EMD-KNN combination algorithm is higher than that of single KNN algorithm and ARIMA model, and it can effectively capture the changing trend of passenger flow. © 2022, Editorial Department of Journal of Wuhan University of Technology. All right reserved.
ABSTRACT
Being an efficient image reconstruction and recognition algorithm, two-dimensional PCA (2DPCA) has an obvious disadvantage in that it treats the rows and columns of images unequally. To exploit the other lateral information of images, alternative 2DPCA (A2DPCA) and a series of bilateral 2DPCA algorithms have been proposed. This paper proposes a new algorithm named direct bilateral 2DPCA (DB2DPCA) by fusing bilateral information from images directly-that is, we concatenate the projection results of 2DPCA and A2DPCA together as the projection result of DB2DPCA and we average between the reconstruction results of 2DPCA and A2DPCA as the reconstruction result of DB2DPCA. The relationships between DB2DPCA and related algorithms are discussed under some extreme conditions when images are reshaped. To test the proposed algorithm, we conduct experiments of image reconstruction and recognition on two face databases, a handwritten character database and a palmprint database. The performances of different algorithms are evaluated by reconstruction errors and classification accuracies. Experimental results show that DB2DPCA generally outperforms competing algorithms both in image reconstruction and recognition. Additional experiments on reordered and reshaped databases further demonstrate the superiority of the proposed algorithm. In conclusion, DB2DPCA is a rather simple but highly effective algorithm for image reconstruction and recognition.
ABSTRACT
COVID-19 has brought huge losses to the economy all over the world. To solve this problem, we delivered an epidemic situation evaluation and prediction system based on dynamic data clustering, which was established to cluster the epidemic data in different regions and make evaluations and predictions through the Markov chain. Using the method of streaming data to cluster, we set the data at the same cluster as the sampling results from the same distribution to classify the epidemic situation. We used the Markov chain model to estimate the future development of the epidemic situation. According to the characteristics of stream data, the system can avoid the impact of epidemic data not meeting the assumption of independent homodistribution and only assess the epidemic situation based on local areas. © 2022 IEEE.
ABSTRACT
Background. In 2020/21, deaths due to active tuberculosis (TB) increased globally for the first time in decades with concomitant global decline in TB detection rates, suggesting that delay in TB diagnosis during the COVID-19 pandemic is associated with increased mortality. In the US and New York City, 20% decline in TB cases was reported in 2020/21. We aimed to compare symptom duration, sputum microscopy and radiographic findings in patients with newly diagnosed TB at Montefiore Medical Center (MMC) in the Bronx, New York, before and during the COVID-19 pandemic. We hypothesized that patients during the COVID-19 pandemic present with signs of more advanced TB than before. Methods. Using a cross-sectional study design, we retrospectively reviewed medical records of TB patients identified through microbiology lab records from 11/1/ 2018 to 3/11/2022 and stratified by admission before (11/1/2018-2/29/2020) and during (3/1/2020-3/11/2022) the COVID-19 pandemic. Inclusion criteria were age >=18 years, admission to an MMC hospital, and new diagnosis of culture-confirmed TB. Results. We identified 24 TB patients who presented before and 24 during the pandemic. About 1.7 new TB cases were diagnosed monthly before vs 1.0 during the pandemic, an >40% decline. Patients had both pulmonary and/or extrapulmonary manifestations without differences between groups. There were no significant differences in demographics and comorbidities between the two groups aside from diabetes, which was higher in the pre-COVID group (p = 0.03). Two TB patients had a prior history of COVID and one developed nosocomial COVID during the admission. There was no difference in mortality between groups. Patients with pulmonary manifestations had higher sputum AFB smear positivity (p=0.14) and significantly higher occurrence of multilobar or miliary infiltrates on chest X-ray during compared to before COVID (p = 0.01;Table 1). Table 1. Symptoms and diagnostics on initial presentation of patients with pulmonary TB before and during the COVID-19 pandemic Depending on distribution, t-tests or Mann Whitney U tests were used for continuous and Chi-square tests or Fisher's exact tests for categorical variables. Sputum AFB smears results are reported for the initial 3 smears. Conclusion. Our findings show >40% decline in patients presenting with TB in the Bronx during vs before the COVID-19 pandemic and suggests patients presented with more advanced disease than before the pandemic. Whether COVID-19 could have contributed to this remains to be investigated. Our results have implications for public health and emphasizes the need for earlier identification of TB.
ABSTRACT
Background. Despite multiple studies indicating a low prevalence of bacterial coinfection in coronavirus disease 2019 (COVID-19) patients, the majority of hospitalized COVID-19 patients receive one or more antibiotics. Patients with coinfection usually have multiple risk factors and poor clinical outcomes. Methods. A retrospective case control study was conducted comparing clinical characteristics and antimicrobial use in hospitalized adult COVID-19 patients with bacterial co-infections vs. randomly selected patients without co-infections (matched on month of admission). The study was conducted at three hospitals within the Montefiore Medical Center, Bronx, NY between March 1, 2020 and October 31, 2020. A multivariable logistic regression model was developed to assess the relationship of each predictor variable with coinfection status. Secondary outcomes included hospital mortality, antibiotic days of therapy (DOT), and C. difficile infection. Results. A total of 150 patients with coinfection and 150 patients without coinfection were included in the analysis. Table 1 summarized baseline characteristics and risk factors. The multivariable logistic regression model indicated that presence of a central line (OR=5.4, 95% CI: 2.7-11.1), prior antibiotic exposure within 30 days (OR=5.3, 95% CI: 2.8-10.0), prior ICU admission (OR=3.6, 95% CI: 1.7-7.6), steroid use (OR=2.7, 95% CI: 1.4-4.9), and any comorbid condition (OR=2.7, 95% CI: 1.4-5.2) were significantly associated with the development of coinfection (table 2). Mortality was higher in patients with coinfection (56% vs. 11%, p < 0.0001) (table 3). Average antibiotic DOT was 10.5 in coinfected patients compared to 4 in noncoinfected patients, (p < 0.0001). Forty-one percent of coinfected patients had a multidrug resistant organism isolated. C. difficile rate was higher in coinfected patients (4% vs. 0%, p=0.03). Conclusion. As the healthcare community contends with a 3rd year of COVID-19 pandemic, understanding risk factors most predictive of bacterial coinfection can guide empiric antimicrobial therapy and targeted stewardship interventions. Ideally, co-infection risk scores are developed which may be useful for future inpatient surges.
ABSTRACT
A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques. © 2022 IEEE.
ABSTRACT
The COVID-19 has spread throughout the world.The number of COVID-19 patients still increase rapidly worldwide.The treatment of the COVID-19 patients attracts attention of the researchers.Diagnosis and Treatment Protocol for COVID-19 indicates that atomization inhalation of Alpha-interferon could be used for the antiviral therapy.To explore the possible method for enhancing the effectiveness of the inhalation treatment,numerical simulation was applied to analyze the treatment of a patient with moderate COVID-19 symptoms.Based on the spiral CT scan images on admission,we analyzed the severity of the lung segments.The geometry of the lung was reconstructed according to the lung segmentations.Drug delivery simulations for droplets with different diameters were carried out at low inhalation flow rate (15 L/min).The numbers of the droplets deposited in the airway those delivered into the deeper lung regions were recorded.The relationship between the initial locations of the droplets and their final destinations were obtained.The results indicate that the overall deep lung delivery efficiency of the droplets decreases with the increase of the Stokes number.The delivery efficiency could be significantly increased,if the droplets could be released from two circular areas at the inlet.This investigation proves that the targeted delivery of the inhalable drug is possible. © 2022 Editorial Office of Chinese Journal of Computational Mechanics. All rights reserved.
ABSTRACT
Since 2019, the COVID-19 has been hanging over the whole world, causing uncountable financial loss. In this regard, wearing masks becomes a precaution for the public. However, some people are wearing masks in a wrong way, which may cause virus infection. To detect the wrong wearing of masks, we use 3 classic Convolutional Neural Networks, namely LeNet-5, AlexNet, and VGGNet-16, based on a unique dataset, to train the model and analyze the results. On the unique dataset, LeNet-5 achieved an accuracy of 80.3%, which was the lowest among the three networks, AlexNet attained an accuracy of 90.6%, which is near the precision of VGGNet-16, 92.83%. This work may help the advance of a digital city, making COVID-19 precaution under control. © 2022 SPIE.
ABSTRACT
Interprovincial counterpart support is a cooperative system used by local governments to achieve horizontal flow of resources based on cross-regional cooperation. Existing research has mainly focused on governance efficiency, institutional advantages, and ranking incentives while ignoring the scrambling behavior and operational mechanisms of local governments formed by ranking incentives and territorial responsibilities. This study selected the Wenchuan earthquake, Yushu earthquake, and COVID-19 as three typical cases. We constructed a theoretical framework for competition among provincial local governments and found that competition in interprovincial disaster counterpart support followed a dual behavioral logic of “striving to be first” and “fear of being last”. Specifically, local governments will choose striving to be first under the logic of time coercion, content games, and territorial responsibility;they will choose fear of being last under the logic of responsibility avoidance and moral pressure. This type of scrambling-based horizontal competition reflects the logic of local government competition tournaments. This study further revealed the specific processes, mechanisms, and results of horizontal local government competition, which can provide inspiration for cross-regional and provincial cooperation. © 2022 Shandong Normal University