Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 25
Filter
1.
researchsquare; 2024.
Preprint in English | PREPRINT-RESEARCHSQUARE | ID: ppzbmed-10.21203.rs.3.rs-4152460.v1

ABSTRACT

Objectives Dominant strains had been replaced by SARS-CoV-2 JN.1 lineages, and spread widely in a short period of time. However, accurate detection method and reason for rapid spread have not been clarified.Methods Ion Torrent, Illumina and Nanopore sequencing platforms were used to detect whole genome sequences of SARS-CoV-2 positive cases in Dalian CDC from December 2023 to January 2024.Results Ion Torrent and Illumina platform had missing sites, but optimized Ion Torrent and Nanopore platform covered all detected sites. Ion Torrent platform had higher sensitivity than others and was more suitable for short-read length sequencing. However, primers need to be optimized in time. Illumina platform was also suitable for short-read length and prone to site drop out. Nanopore platform was more suitable for long read-length sequencing and had high compatibility for more variation site. Furthermore, compared JN.1 lineages with BA.2.86, multiple specific variation sites were detected for the first time in non-S protein region.Conclusion Timely optimized primers and supplement variation sites will provide a more effective mean for monitoring and controlling the prevalence of JN.1 lineages in advance, and the discovery of specific variation sites may reveal the reasons for immune escape and rapid transmission.

2.
biorxiv; 2023.
Preprint in English | bioRxiv | ID: ppzbmed-10.1101.2023.10.03.560426

ABSTRACT

Age is a major risk factor for coronavirus disease (COVID-19)-associated severe pneumonia and mortality; however, the underlying mechanism remains unclear. Herein, we investigated whether age-related deregulation of RNAi components and RNA splicing factors affects COVID-19 severity. Decreased expression of RNAi components (Dicer and XPO5) and splicing factors (SRSF3 and hnRNPA3) correlated with increased severity of COVID-19 and SARS-CoV-2 nucleocapsid (N) protein-induced pneumonia. N protein induced autophagic degradation of Dicer, XPO5, SRSF3, and hnRNPA3, repressing miRNA biogenesis and RNA splicing and inducing DNA damage, proteotoxic stress, and pneumonia. Dicer, XPO5, SRSF3, and hnRNPA3 were downregulated with age in mouse lung tissues. Older mice experienced more severe N protein-induced pneumonia than younger mice. However, treatment with a poly(ADP-ribose) polymerase inhibitor (PJ34) or aromatase inhibitor (anastrozole) relieved N protein-induced pneumonia by restoring Dicer, XPO5, SRSF3, and hnRNPA3 expression. These findings will aid in developing improved treatments for SARS-CoV-2-associated pneumonia.


Subject(s)
Coronavirus Infections , Pneumonia , Fractures, Stress , COVID-19
3.
medrxiv; 2023.
Preprint in English | medRxiv | ID: ppzbmed-10.1101.2023.09.12.23295354

ABSTRACT

Childhood maltreatment has been associated with some infection-related outcomes, yet its potential role in severe COVID-19 outcomes has not been addressed. Therefore, leveraging longitudinal data from the population-based UK Biobank (N=151,427), our study aimed to explore the association between childhood maltreatment and severe COVID-19 outcomes (i.e., hospitalization or death due to COVID-19) and its underlying mechanisms. Our results suggest that childhood maltreatment, particularly physical neglect, is associated with a 54.0% increased risk of severe COVID-19 outcomes (i.e., hospitalization or death due to COVID-19), which was not modified by genetic predisposition to severe COVID-19 outcomes. We found that 50.9% of this association was mediated by suboptimal socioeconomic status, lifestyle and prepandemic somatic diseases or psychiatric disorders. These findings highlight the role of early life adversities in severe health consequences across the lifespan and call for increased clinical surveillance of people exposed to childhood maltreatment in COVID-19 outbreaks and future pandemics.


Subject(s)
COVID-19 , Mental Disorders , Death , Somatoform Disorders
5.
arxiv; 2023.
Preprint in English | PREPRINT-ARXIV | ID: ppzbmed-2306.07652v1

ABSTRACT

Background: The objective of this study is to evaluate the impact of COVID-19 inactivated vaccine administration on the outcomes of in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) cycles in infertile couples in China. Methods: We collected data from the CYART prospective cohort, which included couples undergoing IVF treatment from January 2021 to September 2022 at Sichuan Jinxin Xinan Women & Children's Hospital. Based on whether they received vaccination before ovarian stimulation, the couples were divided into the vaccination group and the non-vaccination group. We compared the laboratory parameters and pregnancy outcomes between the two groups. Findings: After performing propensity score matching (PSM), the analysis demonstrated similar clinical pregnancy rates, biochemical pregnancy and ongoing pregnancy rates between vaccinated and unvaccinated women. No significant disparities were found in terms of embryo development and laboratory parameters among the groups. Moreover, male vaccination had no impact on patient performance or pregnancy outcomes in assisted reproductive technology treatments. Additionally, there were no significant differences observed in the effects of vaccination on embryo development and pregnancy outcomes among couples undergoing ART. Interpretation: The findings suggest that COVID-19 vaccination did not have a significant effect on patients undergoing IVF/ICSI with fresh embryo transfer. Therefore, it is recommended that couples should receive COVID-19 vaccination as scheduled to help mitigate the COVID-19 pandemic.


Subject(s)
COVID-19 , Infertility, Female
6.
researchsquare; 2023.
Preprint in English | PREPRINT-RESEARCHSQUARE | ID: ppzbmed-10.21203.rs.3.rs-2991762.v1

ABSTRACT

Objective:  The infection rate and mortality of COVID-19 in hemodialysis patients are extremely high. In this study, we analyzed the risk prediction of pneumonia in Chinese’s hemodialysis patients with COVID-19.  Method: We conducted a retrospective analysis of maintenance hemodialysis patients with COVID-19 admitted to Peking University Third Hospital from December 1, 2022 to January 31, 2023. We collected demographic data, underlying diseases, dialysis treatment data, and laboratory test results of these patients; logistic regression and ROC curve were used to analyze the risk factors of pneumonia.  Results:  A total of 209 hemodialysis patients with COVID-19 were enrolled in this study, of whom 80(38.3%) had pneumonia and 129(61.7%) normal. Multivariate logistic analysis revealed that older age (OR=1.030, 95%CI 1.002~1.059, p=0.036), lower hemoglobin (OR=0.968, 95%CI 0.942~0.995, p=0.019), lower albumin (OR=0.834, 95%CI 0.738-0.943, p=0.004) were risk factors for pneumonia. Patients with age >65 years old, hemoglobin <115g/L or albumin <36.8g/L had a higher risk of pneumonia, and we combined the three indexes to predict the risk of pneumonia (P= elogit(P)    / 1+  elogit(P) , logit(P)=9.593 +0.031×Age (years old) -0.038×Hemoglobin (g/L) -0.210×Albumin (g/L)), drew the ROC curve with the risk P value (AUC=0.756, 95% CI 0.687~0.825, p<0.001), when P=0.575 was selected as the cut-off value, the sensitivity and specificity of the three indexes combined to predict pneumonia were 44.0% and 94.5% respectively.  Conclusion: Older age, anemia and hypoalbuminemia were risk factors for pneumonia in MHD patients. We could reduce the incidence of pneumonia and improve the prognosis of MHD patients by correcting anemia and hypoalbuminemia.


Subject(s)
COVID-19 , Pneumonia , Hypoalbuminemia , Anemia
7.
Journal of Organizational Change Management ; 35(7):984-999, 2022.
Article in English | ProQuest Central | ID: covidwho-2152404

ABSTRACT

Purpose>Drawing upon the literature on person-leader supplementary fit literature, this study aims to positions dissatisfaction with organizational performance as a difficult condition that moderates the relationship between leader-employee congruence/incongruence in creativity goal and employee innovative performance.Design/methodology/approach>In this paper data were collected from 226 leader-employee dyads from several information technology companies in China. Polynomial regression combined with the response surface methodology was used to test the hypotheses.Findings>Three conclusions were drawn. First, employee innovative performance was maximized when leaders and employees were congruence in creativity goal. Second, in the case of congruence, employee had higher innovative performance when a leader's and an employee's creativity goal matched at high levels. Third, dissatisfaction with organizational performance moderated the effect of leader – employee congruence in creativity goal on employee innovative performance.Originality/value>This study enhanced theoretical developments by considering the importance of leaders' congruence with employees in creativity goal for the first time. Additionally, the research results provided better practical guidance for how to help employees recover from difficult condition and continue to participate in innovation.

8.
Atmospheric Chemistry and Physics ; 22(22):14455-14466, 2022.
Article in English | ProQuest Central | ID: covidwho-2118990

ABSTRACT

Shanghai, one of China's most important economic centres, imposed a citywide lockdown in April and May 2022 to contain a resurgence in cases of the coronavirus disease in 2019. Compared with the 2020 lockdown, the 2022 lockdown occurred in a warm season and lasted much longer, thereby serving as a relevant real-world test of the response of ambient ozone (O3) concentrations to emission reductions in a high-O3 season. In this study, we analysed surface observations of O3 and nitrogen dioxide (NO2) concentrations and satellite-retrieved tropospheric NO2 and formaldehyde (HCHO) column concentrations in the first 5 months of 2022 with comparisons to the year 2021. During the 2-month 2022 lockdown, the maximum daily 8 h average (MDA8) O3 concentrations at 1 or more of the city's 19 sites exceeded China's air quality standard of 160 µgm-3 21 times, with the highest value being 200 µgm-3. The city-average MDA8 O3 concentration increased by 13 % in April–May 2022 year-on-year, despite sharp declines in NO2 surface and column concentrations (both by 49 %) and a 19 % decrease in the HCHO column concentration. These results show that the reductions in O3 precursors and other pollutants during the 2022 lockdown did not prevent ground-level O3 pollution. An analysis of meteorological data indicates that there were only small changes in the meteorological conditions, and there was little transport of O3 from the high-O3 inland regions during the 2022 lockdown, neither of which can account for the increased and high concentrations of O3 that were observed during this period. The mean HCHO/NO2 ratio in April–May increased from 1.11 in 2021 to 1.68 in 2022, and the correlation between surface O3 and NO2 concentrations changed from negative in 2021 to positive in 2022. These results indicate that the high O3 concentrations in 2022 were mainly due to large reductions in the emissions of NOx and that the decrease in the concentrations of volatile organic compounds (VOCs) could not overcome the NO titration effect. During the 2022 lockdown, Shanghai's urban centre remained VOC-sensitive despite drastic reductions in road transportation (73 %–85 %) and industrial activities (∼60 %), whereas its semi-rural areas transitioned from VOC-limited to VOC–NOx-co-limited regimes. Our findings suggest that future emission reductions similar to those that occurred during the lockdown, such as those that will result from electrifying transportation, will not be sufficient to eliminate O3 pollution in urban areas of Shanghai and possibly other VOC-limited metropoles without the imposition of additional VOC controls or more substantial decreases in NOx emissions.

9.
International journal of public health ; 67, 2022.
Article in English | EuropePMC | ID: covidwho-2034421

ABSTRACT

Objectives: To develop and internally validate two clinical risk scores to detect coronavirus disease 2019 (COVID-19) during local outbreaks. Methods: Medical records were extracted for a retrospective cohort of 336 suspected patients admitted to Baodi hospital between 27 January to 20 February 2020. Multivariate logistic regression was applied to develop the risk-scoring models, which were internally validated using a 5-fold cross-validation method and Hosmer-Lemeshow (H-L) tests. Results: Fifty-six cases were diagnosed from the cohort. The first model was developed based on seven significant predictors, including age, close contact with confirmed/suspected cases, same location of exposure, temperature, leukocyte counts, radiological findings of pneumonia and bilateral involvement (the mean area under the receiver operating characteristic curve [AUC]:0.88, 95% CI: 0.84–0.93). The second model had the same predictors except leukocyte and radiological findings (AUC: 0.84, 95% CI: 0.78–0.89, Z = 2.56, p = 0.01). Both were internally validated using H-L tests and showed good calibration (both p > 0.10). Conclusion: Two clinical risk scores to detect COVID-19 in local outbreaks were developed with excellent predictive performances, using commonly measured clinical variables. Further external validations in new outbreaks are warranted.

10.
Computational urban science ; 2(1), 2022.
Article in English | EuropePMC | ID: covidwho-2034048

ABSTRACT

Since the Corona Virus Disease 2019 (COVID-19) swept the world, many countries face a problem that is a shortage of medical resources. The role of emergency medical facilities in response to the epidemic is beginning to arouse public attention, and the construction of the urban resilient emergency response framework has become the critical way to resist the epidemic. Today, China has controlled the domestically transmitted COVID-19 cases through multiple emergency medical facilities and inclusive patient admission criteria. Most of the existing literature focuses on case studies or characterizations of individual facilities. This paper constructs an evaluation system to measure urban hospital resilience from the spatial perspective and deciphered the layout patterns and regularities of emergency medical facilities in Wuhan, the city most affected by the epidemic in China. Findings indicate that the pattern of one center and two circles are a more compelling layout structure for urban emergency medical facilities in terms of accessibility and service coverage for residents. Meanwhile, the Fangcang shelter hospital has an extraordinary performance in terms of emergency response time, and it is a sustainable facility utilization approach in the post-epidemic era. This study bolsters areas of the research on the urban resilient emergency response framework. Moreover, the paper summarizes new medical facilities’ planning and location characteristics and hopes to provide policy-makers and urban planners with valuable empirical evidence.

11.
ACS omega ; 7(16):14211-14221, 2022.
Article in English | EuropePMC | ID: covidwho-1836996

ABSTRACT

The current global pandemic of new coronary pneumonia clearly reveals the importance of developing highly efficient filtration and fast germicidal performance of multifunctional air filters. In this study, a novel air filter with a controllable morphology based on the rod-like to flower-like zinc oxide/graphene-based photocatalytic composite particles loaded on glass microfiber was prepared by one-step microwave rapid synthesis. The multifunctional air filter shows the following special functions: the 10 mg·L–1 organic pollutant solution RhB was completely degraded within 2 h under a 500 W xenon lamp, and also 99% of Escherichia coli and Staphylococcus aureus were inactivated under a 60 W light-emitting diode lamp. Furthermore, after introducing the controllable morphology zinc oxide/graphene-based photocatalytic composite particles, the filtration efficiency of the multifunctional air filter was also kept at the same level (99.8%) as the one without any addition, indicating no loss of high-efficiency filtration while obtaining the rapid bactericidal function. The rapid antibacterial principle of the multifunctional air filter has also been proposed through the UV–vis spectroscopies, photoluminescence, and electron-spin resonance spectrum. The zinc oxide/graphene-based photocatalytic composite particles tightly coated on the glass microfiber surface could increase the active sites by changing the morphology of zinc oxide and, in the meantime, promote the separation of zinc oxide photo-generated electron–hole pairs to improve the rapid sterilization ability of the multifunctional air filters. In addition, an empirical formula to evaluate the relationship between the composition, viscosity, and viscosity modulus of glass microfiber was proposed by testing the viscosity of glass microfiber composed of 14 different compositions at 1300 and 1400 °C, which can be used as a criterion to evaluate the production technology of glass microfiber filters.

12.
biorxiv; 2022.
Preprint in English | bioRxiv | ID: ppzbmed-10.1101.2022.01.20.477147

ABSTRACT

Cardiac manifestations are commonly observed in COVID-19 patients and prominently contributed to overall mortality. Human myocardium could be infected by SARS-CoV-2, and human pluripotent stem cell-derived cardiomyocytes (hPSC-CMs) are susceptible to SARS-CoV-2 infection. However, molecular mechanisms of SARS-CoV-2 gene-induced injury and dysfunction of human CMs remain elusive. Here, we find overexpression of three SARS-CoV-2 coding genes, Nsp6, Nsp8 and M, could globally compromise transcriptome of hPSC-CMs. Integrated transcriptomic analyses of hPSC-CMs infected by SARS-CoV-2 with hPSC-CMs of Nsp6, Nsp8 or M overexpression identified concordantly activated genes enriched into apoptosis and immune/inflammation responses, whereas reduced genes related to heart contraction and functions. Further, Nsp6, Nsp8 or M overexpression induce prominent apoptosis and electrical dysfunctions of hPSC-CMs. Global interactome analysis find Nsp6, Nsp8 and M all interact with ATPase subunits, leading to significantly reduced cellular ATP level of hPSC-CMs. Finally, we find two FDA-approved drugs, ivermectin and meclizine, could enhance the ATP level, and ameliorate cell death and dysfunctions of hPSC-CMs overexpressing Nsp6, Nsp8 or M. Overall, we uncover the global detrimental impacts of SARS-CoV-2 genes Nsp6, Nsp8 and M on the whole transcriptome and interactome of hPSC-CMs, define the crucial role of ATP level reduced by SARS-CoV-2 genes in CM death and functional abnormalities, and explore the potentially pharmaceutical approaches to ameliorate SARS-CoV-2 genes-induced CM injury and abnormalities.


Subject(s)
Chemical and Drug Induced Liver Injury , Carcinoma, Renal Cell , Leukemia-Lymphoma, Adult T-Cell , Death , COVID-19 , Inflammation , Abnormalities, Drug-Induced
14.
Zhongguo Weishengtaxixue Zazhi / Chinese Journal of Microecology ; 32(5):583-585, 2020.
Article in Chinese | GIM | ID: covidwho-1497980

ABSTRACT

Corona Virus Disease 2019(COVID-19) is a contagious disease with respiratory symptoms as the main manifestation that has recently occurred worldwide. This disease poses a major threat to the lives of people in China and the world. The contagiosity of Severe Acute Respiratory Syndrome Coronavirus 2(SARS-CoV-2) is stronger than those of SARS-CoV and MERS-CoV, which is one of the biggest characteristics of the pathogen, and the disease progresses rapidly after infection with severe harmfulness. Scientists in China and around the world have made great efforts to understand the disease. This article aims to sort out the knowledge on the disease and improve the clinicians' initial understanding on the disease.

15.
Zhongguo Bingdubing Zazhi = Chinese Journal of Viral Diseases ; - (3):209, 2021.
Article in English | ProQuest Central | ID: covidwho-1329332

ABSTRACT

Most viruses require their glycoproteins to be hydrolyzed in order to enter host cells.In some cases, the severability of viral glycoproteins is a determinant of their virulence.These viral glycoproteins can be cleaved by one or more proteases in host cells with furin as the common one.Furin further promotes viral infection by identifying specific amino acid sequences in glycoprotein precursors.Morever, furin plays a critical role in the infections of many viruses including human immunodeficiency virus, flavivirus, filamentavirus and coronavirus, and is considered as a promising drug treatment and prevention target.In this review, we summarize the biological background of furin and its hydrolysis function to viral glycoproteins.

16.
medrxiv; 2021.
Preprint in English | medRxiv | ID: ppzbmed-10.1101.2021.05.17.21257134

ABSTRACT

An unequitable vaccine allocation and continuously emerging SARS-CoV-2 variants pose challenges to contain the pandemic, which underscores the need for licensing more vaccine candidates, increasing manufacturing capacity and implementing better immunization strategy. Here, we report data from a proof-of-concept investigation in two healthy individuals who received two doses of inactivated whole-virus COVID-19 vaccines, followed by a single heterologous boost vaccination after 7 months with an mRNA vaccine candidate (LPP-Spike-mRNA) developed by Stemirna Therapeutics. Following the boost, Spike-specific antibody (Ab), memory B cell and T cell responses were significantly increased. These findings indicate that a heterologous immunization strategy combining inactivated and mRNA vaccines can generate robust vaccine responses and therefore provide a rational and effective vaccination regimen.


Subject(s)
COVID-19
17.
researchsquare; 2021.
Preprint in English | PREPRINT-RESEARCHSQUARE | ID: ppzbmed-10.21203.rs.3.rs-258283.v1

ABSTRACT

SARS-CoV-2 has emerged as a major threat to global public health, resulting in global societal and economic disruptions. Here, we investigate the intramolecular and intermolecular RNA interactions of wildtype (WT) and a mutant (Δ382) SARS-CoV-2 virus in cells using high throughput structure probing on Illumina and Nanopore platforms. We identified twelve potentially functional structural elements within the SARS-CoV-2 genome, observed that identical sequences can fold into divergent structures on different subgenomic RNAs, and that WT and Δ382 virus genomes can fold differently. Proximity ligation sequencing experiments identified hundreds of intramolecular and intermolecular pair-wise interactions within the virus genome and between virus and host RNAs. SARS-CoV-2 binds strongly to mitochondrial and small nucleolar RNAs and is extensively 2’-O-methylated. 2’-O-methylation sites in the virus genome are enriched in the untranslated regions and are associated with increased pair-wise interactions. SARS-CoV-2 infection results in a global decrease of 2’-O-methylation sites on host mRNAs, suggesting that binding to snoRNAs could be a pro-viral mechanism to sequester methylation machinery from host RNAs towards the virus genome. Collectively, these studies deepen our understanding of the molecular basis of SARS-CoV-2 pathogenicity, cellular factors important during infection and provide a platform for targeted therapy.


Subject(s)
COVID-19
18.
Science of The Total Environment ; : 145992, 2021.
Article in English | ScienceDirect | ID: covidwho-1091645

ABSTRACT

Coronavirus disease 2019 (COVID-19) has become a worldwide public health threat. Many associated factors including population movement, meteorological parameters, air quality and socioeconomic conditions can affect COVID-19 transmission. However, no study has combined these various factors in a comprehensive analysis. We collected data on COVID-19 cases and the factors of interest in 340 prefectures of mainland China from 1 December 2019 to 30 April 2020. Moran's I statistic, Getis-Ord Gi⁎ statistic and Kulldorff's space-time scan statistics were used to identify spatial clusters of COVID-19, and the geographically weighted regression (GWR) model was applied to investigate the effects of the associated factors on COVID-19 incidence. A total of 67,449 laboratory-confirmed cases were reported during the study period. Wuhan city as well as its surrounding areas were the cluster areas, and January 25 to February 21, 2020, was the clustering time of COVID-19. The population outflow from Wuhan played a significant role in COVID-19 transmission, with the local coefficients varying from 14.87 to 15.02 in the 340 prefectures. Among the meteorological parameters, relative humidity and precipitation were positively associated with COVID-19 incidence, while the average wind speed showed a negative correlation, but the relationship of average temperature with COVID-19 incidence inconsistent between northern and southern China. NO2 was positively associated, and O3 was negatively associated, with COVID-19 incidence. Environment with high levels of inbound migration or travel, poor ventilation, high humidity or heavy rainfall, low temperature, and high air pollution may be favorable for the growth, reproduction and spread of SARS-CoV-2. Therefore, applying appropriate lockdown measures and travel restrictions, strengthening the ventilation of living and working environments, controlling air pollution and making sufficient preparations for a possible second wave in the relatively cold autumn and winter months may be helpful for the control and prevention of COVID-19.

19.
researchsquare; 2020.
Preprint in English | PREPRINT-RESEARCHSQUARE | ID: ppzbmed-10.21203.rs.3.rs-91923.v1

ABSTRACT

Background: A fever outpatient clinic at the south campus of Shanghai East Hospital (SEH) openedin response to the coronavirus disease (COVID-19) outbreak. We analyzed the data of all 11,972patients who visited the fever clinic and the 29 confirmed COVID-19 cases to determine the clinical and epidemiological characteristics of confirmed COVID-19 cases diagnosed at SEH.Methods: Data were collected from all fever outpatient clinic patients between January 23 and September 30, 2020. We compared the characteristics of confirmed patients, including age, occupation, area, symptoms, laboratory results, and computed tomography (CT) findings, according to month.Results: By September 30, 2020, 11,972 patients, including 29 (0.24%) confirmed COVID-19 cases, visited the clinic. Four of five confirmed domestic cases identified during January–February 2020 were from Wuhan (mainly elderly retirees and local employees), Hubei. After the epidemic spread internationally, all 22 confirmed cases identified during March–April 2020 were individuals who returned from abroad. They were predominantly young Chinese international students. The sporadic two confirmed cases during May–September 2020 included an employee returning to work from Hubei and an Indian servant from abroad. Symptoms, laboratory tests, and CT findings were consistent with previous reports of COVID-19-positive cases.Conclusions: The characteristics of confirmed COVID-19 cases at SEH varied among different periods in response to the spread of the pandemic. However, due to the effective early isolation and quarantine measures, no outbreak occurred in SEH, which contributed to the prevention and control of the epidemic in Shanghai. 


Subject(s)
Coronavirus Infections , Fever , COVID-19
20.
arxiv; 2020.
Preprint in English | PREPRINT-ARXIV | ID: ppzbmed-2009.10401v4

ABSTRACT

Medical diagnostic image analysis (e.g., CT scan or X-Ray) using machine learning is an efficient and accurate way to detect COVID-19 infections. However, sharing diagnostic images across medical institutions is usually not allowed due to the concern of patients' privacy. This causes the issue of insufficient datasets for training the image classification model. Federated learning is an emerging privacy-preserving machine learning paradigm that produces an unbiased global model based on the received updates of local models trained by clients without exchanging clients' local data. Nevertheless, the default setting of federated learning introduces huge communication cost of transferring model updates and can hardly ensure model performance when data heterogeneity of clients heavily exists. To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections. First, we design an architecture for dynamic fusion-based federated learning systems to analyse medical diagnostic images. Further, we present a dynamic fusion method to dynamically decide the participating clients according to their local model performance and schedule the model fusion-based on participating clients' training time. In addition, we summarise a category of medical diagnostic image datasets for COVID-19 detection, which can be used by the machine learning community for image analysis. The evaluation results show that the proposed approach is feasible and performs better than the default setting of federated learning in terms of model performance, communication efficiency and fault tolerance.


Subject(s)
COVID-19
SELECTION OF CITATIONS
SEARCH DETAIL