Secure and Efficient Smart Healthcare System Based on Federated Learning

The rapid development of smart healthcare system in the Internet of Things (IoT) has made the early detection of many chronic diseases more convenient, quick, and economical. However, when healthcare organizations collect users' health data through deployed IoT devices, there are issues of compromising users' privacy. In view of this situation, this paper introduces federated learning technology to solve the problem of data security. In this paper, we consider the two main problems of federated learning applications in IoT smart healthcare system: (1) how to reduce the time overhead of system running and (2) how to authenticate that the user device uploading data is deployed by the system itself. To solve the above problems, we propose the first federated learning scheme based on full dynamic secret sharing. First, we use a two-mask protocol to keep the user's local model parameters confidential during federated learning. Then, based on homogeneous linear recursive equation, homomorphic hash function, and elliptic curve cryptosystem, the full dynamic secret sharing and user identity authentication are realized. In addition, our scheme allows users to join or quit during training. Finally, we have carried out simulation test on this scheme. The experimental results show that the efficiency of our scheme is improved by about 60% on average in the case of no user dropping and by about 30% in the case of some users dropping.

Comparison of acute respiratory distress syndrome in patients with COVID-19 and influenza A (H7N9) virus infection.

OBJECTIVES: We aimed to compared the clinical features of acute respiratory distress syndrome (ARDS) induced by COVID-19 and H7N9 virus infections. METHODS: Clinical data of 100 patients with COVID-19 and 46 patients with H7N9 were retrospectively analyzed. RESULTS: Elevated inflammatory indices and coagulation disorders were more common in COVID-19-ARDS group than in the H7N9-ARDS group. The median interval from illness onset to ARDS development was shorter in H7N9-ARDS. The PaO2/FiO2 level was lower in H7N9-ARDS, whereas the Sepsis-related Organ Failure Assessment score was higher in COVID-19-ARDS. The proportion of patients with disseminated intravascular coagulation and liver injury in COVID-19-ARDS and H7N9-ARDS was 45.5% versus 3.1% and 28.8% versus 50%, respectively (P <0.05). The mean interval from illness onset to death was shorter in H7N9-ARDS. A total of 59.1% patients with H7N9-ARDS died of refractory hypoxemia compared with 28.9% with COVID-19-ARDS (P = 0.014). Patients with COVID-19-ARDS were more likely to die of septic shock and multiple organ dysfunction compared with H7N9-ARDS (71.2% vs 36.4%, P = 0.005). CONCLUSION: Patients with H7N9 were more susceptible to develop severe ARDS and showed a more acute disease course. COVID-19-ARDS was associated with severe inflammatory response and coagulation dysfunction, whereas liver injury was more common in H7N9-ARDS. The main causes of death between patients with the two diseases were different.

Patterns and influencing factors of COVID-19 vaccination willingness among college students in China.

BACKGROUND: Vaccination is an important preventive measure against the coronavirus disease 19 (COVID-19) pandemic. We aimed to examine the willingness to vaccination and influencing factors among college students in China. METHODS: From March 18 to April 26, 2021, we conducted a cross-sectional online survey among college students from 30 universities in Wuhan, Hubei Province, China. The survey was composed of the sociodemographic information, psychological status, experience during pandemic, the willingness of vaccination and related information. Students' attitudes towards vaccination were classified as 'vaccine acceptance', 'vaccine hesitancy', and 'vaccine resistance'. Multinomial logistic regression analyses were performed to identify the influencing factors associated with vaccine hesitancy and resistance. RESULTS: Among 23,143 students who completed the survey, a total of 22,660 participants were included in the final analysis with an effective rate of 97.9% after excluding invalid questionnaires. A total of 60.6% of participants would be willing to receive COVID-19 vaccine, 33.4% were hesitant to vaccination, and 6.0% were resistant to vaccination. Social media platforms and government agencies were the main sources of information vaccination. Worry about the efficacy and adverse effects of vaccine were the top two common reason of vaccine hesitancy and resistance. Multiple multinomial logistic regression analysis identified that participants who worried about the adverse effects of vaccination were more likely to be vaccine hesitancy (aOR = 2.44, 95% CI = 2.30, 2.58) and resistance (aOR = 2.71, 95% CI = 2.40, 3.05). CONCLUSION: More than half of college students are willing to receive the COVID-19 vaccine, whereas nearly one-third college students are still hesitant or resistant. It is crucial to provide sufficient and scientific information on the efficacy and safety of vaccine through social media and government agencies platforms to promote vaccine progress against COVID-19 and control the pandemic in China.

Using bioinformatics and systems biology to discover common pathogenetic processes between sarcoidosis and COVID-19.

The coronavirus disease (COVID-19) pandemic caused by SARS-CoV-2 is ongoing. Individuals with sarcoidosis tend to develop severe COVID-19; however, the underlying pathological mechanisms remain elusive. To determine common transcriptional signatures and pathways between sarcoidosis and COVID-19, we investigated the whole-genome transcriptome of peripheral blood mononuclear cells (PBMCs) from patients with COVID-19 and sarcoidosis and conducted bioinformatic analysis, including gene ontology and pathway enrichment, protein-protein interaction (PPI) network, and gene regulatory network (GRN) construction. We identified 33 abnormally expressed genes that were common between COVID-19 and sarcoidosis. Functional enrichment analysis showed that these differentially expressed genes were associated with cytokine production involved in the immune response and T cell cytokine production. We identified several hub genes from the PPI network encoded by the common genes. These hub genes have high diagnostic potential for COVID-19 and sarcoidosis and can be potential biomarkers. Moreover, GRN analysis identified important microRNAs and transcription factors that regulate the common genes. This study provides a novel characterization of the transcriptional signatures and biological processes commonly dysregulated in sarcoidosis and COVID-19 and identified several critical regulators and biomarkers. This study highlights a potential pathological association between COVID-19 and sarcoidosis, establishing a theoretical basis for future clinical trials.

Practice and experience of regional medical center entrance linkage and closed-loop management under the wartime situation of the COVID-19 in China

On 28 July 2021, the first indigenous case of novel coronavirus pneumonia (COVID-19) emerged in Yangzhou, marking the beginning of a public health crisis caused by the new coronavirus pneumonia. It is a significant challenge for hospitals to carry out prevention and control measures to ensure the safety of medical professionals and patients when facing the changes in an epidemic situation. Subei People’s Hospital, as one of the first group of “Grade III-class A” hospitals in Jiangsu Province and the Yangzhou Regional Medical Centre, responded quickly and scientifically to prevent and control the disease. A closed-loop management system was implemented at the hospital entrance (consisting of the outpatient clinic, emergency clinic, fever clinic, and buffer ward) and an epidemic prevention and control group was established with the assistance of multiple departments. This group optimized the pre-screening and triage system, standardized the fever clinic consultation process, and improved the construction of an information-based prevention and control network so that patients were detected, diagnosed, isolated, and treated early. The emergency management capability was improved to achieve zero missed consultations of patients attending for COVID-19 and to effectively maintain medical order during this critical period. This current report systematically summarizes the operational practices and the effectiveness achieved by implementation of the entrance closed-loop management in the hospital and analyzed the key operational issues for future reference by medical institutions and management departments.

Predictors of SARS-CoV-2 infection following high-risk exposure (preprint)

ABSTRACT Background Non-pharmaceutical interventions (NPIs) are recommended for COVID-19 mitigation. However, the effectiveness of NPIs in preventing SARS-CoV-2 transmission remains poorly quantified. Methods We conducted a test-negative design case-control study enrolling cases (testing positive for SARS-CoV-2) and controls (testing negative) with molecular SARS-CoV-2 diagnostic test results reported to California Department of Public Health between 24 February-26 September, 2021. We used conditional logistic regression to assess predictors of case status among participants who reported contact with an individual known or suspected to have been infected with SARS-CoV-2 (“high-risk exposure”) within ≤14 days of testing. Results 643 of 1280 cases (50.2%) and 204 of 1263 controls (16.2%) reported high-risk exposures ≤14 days before testing. Adjusted odds of case status were 2.94-fold (95% confidence interval: 1.66-5.25) higher when high-risk exposures occurred with household members (vs. other contacts), 2.06-fold (1.03-4.21) higher when exposures occurred indoors (vs. not indoors), and 2.58-fold (1.50-4.49) higher when exposures lasted ≥3 hours (vs. shorter durations) among unvaccinated and partially-vaccinated individuals; excess risk associated with such exposures was mitigated among fully-vaccinated individuals. Mask usage by participants or their contacts during high-risk exposures reduced adjusted odds of case status by 48% (8-72%). Adjusted odds of case status were 68% (32-84%) and 77% (59-87%) lower for partially- and fully-vaccinated participants, respectively, than for unvaccinated participants. Benefits of mask usage were greatest when exposures lasted ≥3 hours, occurred indoors, or involved non-household contacts. Conclusions NPIs reduced the likelihood of SARS-CoV-2 infection following high-risk exposure. Vaccine effectiveness was substantial for partially and fully vaccinated persons. KEY POINTS SARS-CoV-2 infection risk was greatest for unvaccinated participants when exposures to known or suspected cases occurred indoors or lasted ≥3 hours. Face mask usage when participants were exposed to a known or suspect case reduced odds of infection by 48%.

Non-stationary spatio-temporal point process modeling for high-resolution COVID-19 data (preprint)

Most COVID-19 studies commonly report figures of the overall infection at a state- or county-level. This aggregation tends to miss out on fine details of virus propagation. In this paper, we analyze a high-resolution COVID-19 dataset in Cali, Colombia, that records the precise time and location of every confirmed case. We develop a non-stationary spatio-temporal point process equipped with a neural network-based kernel to capture the heterogeneous correlations among COVID-19 cases. The kernel is carefully crafted to enhance expressiveness while maintaining model interpretability. We also incorporate some exogenous influences imposed by city landmarks. Our approach outperforms the state-of-the-art in forecasting new COVID-19 cases with the capability to offer vital insights into the spatio-temporal interaction between individuals concerning the disease spread in a metropolis.

Mental and neurological disorders and risk of COVID-19 susceptibility, illness severity and mortality: A systematic review, meta-analysis and call for action.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has evolved into a worldwide pandemic, and has been found to be closely associated with mental and neurological disorders. We aimed to comprehensively quantify the association between mental and neurological disorders, both pre-existing and subsequent, and the risk of susceptibility, severity and mortality of COVID-19. METHODS: In this systematic review and meta-analysis, we searched PubMed, Web of Science, Embase, PsycINFO, and Cochrane library databases for studies published from the inception up to January 16, 2021 and updated at July 7, 2021. Observational studies including cohort and case-control, cross-sectional studies and case series that reported risk estimates of the association between mental or neurological disorders and COVID-19 susceptibility, illness severity and mortality were included. Two researchers independently extracted data and conducted the quality assessment. Based on I2 heterogeneity, we used a random effects model to calculate pooled odds ratios (OR) and 95% confidence intervals (95% CI). Subgroup analyses and meta-regression analysis were also performed. This study was registered on PROSPERO (registration number: CRD 42021230832). FINDING: A total of 149 studies (227,351,954 participants, 89,235,737 COVID-19 patients) were included in this analysis, in which 27 reported morbidity (132,727,798), 56 reported illness severity (83,097,968) and 115 reported mortality (88,878,662). Overall, mental and neurological disorders were associated with a significant high risk of infection (pre-existing mental: OR 1·67, 95% CI 1·12-2·49; and pre-existing neurological: 2·05, 1·58-2·67), illness severity (mental: pre-existing, 1·40, 1·25-1·57; sequelae, 4·85, 2·53-9·32; neurological: pre-existing, 1·43, 1·09-1·88; sequelae, 2·17, 1·45-3·24), and mortality (mental: pre-existing, 1·47, 1·26-1·72; neurological: pre-existing, 2·08, 1·61-2·69; sequelae, 2·03, 1·66-2·49) from COVID-19. Subgroup analysis revealed that association with illness severity was stronger among younger COVID-19 patients, and those with subsequent mental disorders, living in low- and middle-income regions. Younger patients with mental and neurological disorders were associated with higher mortality than elders. For type-specific mental disorders, susceptibility to contracting COVID-19 was associated with pre-existing mood disorders, anxiety, and attention-deficit hyperactivity disorder (ADHD); illness severity was associated with both pre-existing and subsequent mood disorders as well as sleep disturbance; and mortality was associated with pre-existing schizophrenia. For neurological disorders, susceptibility was associated with pre-existing dementia; both severity and mortality were associated with subsequent delirium and altered mental status; besides, mortality was associated with pre-existing and subsequent dementia and multiple specific neurological diseases. Heterogeneities were substantial across studies in most analysis. INTERPRETATION: The findings show an important role of mental and neurological disorders in the context of COVID-19 and provide clues and directions for identifying and protecting vulnerable populations in the pandemic. Early detection and intervention for neurological and mental disorders are urgently needed to control morbidity and mortality induced by the COVID-19 pandemic. However, there was substantial heterogeneity among the included studies, and the results should be interpreted with caution. More studies are needed to explore long-term mental and neurological sequela, as well as the underlying brain mechanisms for the sake of elucidating the causal pathways for these associations. FUNDING: This study is supported by grants from the National Key Research and Development Program of China, the National Natural Science Foundation of China, Special Research Fund of PKUHSC for Prevention and Control of COVID-19, and the Fundamental Research Funds for the Central Universities.