Epi-DNNs: Epidemiological priors informed deep neural networks for modeling COVID-19 dynamics

Differential equations-based epidemic compartmental models and deep neural networks-based artificial intelligence (AI) models are powerful tools for analyzing and fighting the transmission of COVID-19. However, the capability of compartmental models is limited by the challenges of parameter estimation, while AI models fail to discover the evolutionary pattern of COVID-19 and lack explainability. This paper aims to provide a novel method (called Epi-DNNs) by integrating compartmental models and deep neural networks (DNNs) to model the complex dynamics of COVID-19. In the proposed Epi-DNNs method, the neural network is designed to express the unknown parameters in the compartmental model and the Runge–Kutta method is implemented to solve the ordinary differential equations (ODEs) so as to give the values of the ODEs at a given time. Specifically, the discrepancy between predictions and observations is incorporated into the loss function, then the defined loss is minimized and applied to identify the best-fitted parameters governing the compartmental model. Furthermore, we verify the performance of Epi-DNNs on the real-world reported COVID-19 data on the Omicron epidemic in Shanghai covering February 25 to May 27, 2022. The experimental findings on the synthesized data have revealed its effectiveness in COVID-19 transmission modeling. Moreover, the inferred parameters from the proposed Epi-DNNs method yield a predictive compartmental model, which can serve to forecast future dynamics.

Epi-DNNs: Epidemiological priors informed deep neural networks for modeling COVID-19 dynamics.

Differential equations-based epidemic compartmental models and deep neural networks-based artificial intelligence (AI) models are powerful tools for analyzing and fighting the transmission of COVID-19. However, the capability of compartmental models is limited by the challenges of parameter estimation, while AI models fail to discover the evolutionary pattern of COVID-19 and lack explainability. This paper aims to provide a novel method (called Epi-DNNs) by integrating compartmental models and deep neural networks (DNNs) to model the complex dynamics of COVID-19. In the proposed Epi-DNNs method, the neural network is designed to express the unknown parameters in the compartmental model and the Runge-Kutta method is implemented to solve the ordinary differential equations (ODEs) so as to give the values of the ODEs at a given time. Specifically, the discrepancy between predictions and observations is incorporated into the loss function, then the defined loss is minimized and applied to identify the best-fitted parameters governing the compartmental model. Furthermore, we verify the performance of Epi-DNNs on the real-world reported COVID-19 data on the Omicron epidemic in Shanghai covering February 25 to May 27, 2022. The experimental findings on the synthesized data have revealed its effectiveness in COVID-19 transmission modeling. Moreover, the inferred parameters from the proposed Epi-DNNs method yield a predictive compartmental model, which can serve to forecast future dynamics.

Impact of the COVID-19 pandemic on cardiac implantable electronic device implantation in China: Insights from 2 years of changing pandemic conditions.

Background: A substantial reduction in the number of cardiac implantable electronic device (CIED) implantation was reported in the early stages of the COVID-19 pandemic. None of the studies have yet explored changes in CIED implantation during the following pandemic. Objective: To explore changes in CIED implantation during the COVID-19 pandemic from 2020 to 2021. Methods: From 2019 to 2021, 177,263 patients undergone CIED implantation from 1,227 hospitals in China were included in the analysis. Generalized linear models measured the differences in CIED implantation in different periods. The relationship between changes in CIED implantation and COVID-19 cases was assessed by simple linear regression models. Results: Compared with the pre-COVID-19 period, the monthly CIED implantation decreased by 17.67% (95% CI: 16.62-18.72%, p < 0.001) in 2020. In 2021, the monthly number of CIED implantation increased by 15.60% (95% CI: 14.34-16.85%, p < 0.001) compared with 2020. For every 10-fold increase in the number of COVID-19 cases, the monthly number of pacemaker implantation decreased by 429 in 2021, while it decreased by 676 in 2020. The proportion of CIED implantation in secondary medical centers increased from 52.84% in 2019 to 56.77% in 2021 (p < 0.001). For every 10-fold increase in regional accumulated COVID-19 cases, the proportion of CIED implantation in secondary centers increased by 6.43% (95% CI: 0.47-12.39%, p = 0.036). Conclusion: The impact of the COVID-19 pandemic on the number of CIED implantation is diminishing in China. Improving the ability of secondary medical centers to undertake more operations may be a critical way to relieve the strain on healthcare resources during the epidemic.

Retrospective Modeling of the Omicron Epidemic in Shanghai, China: Exploring the Timing and Performance of Control Measures.

BACKGROUND: In late February 2022, the Omicron epidemic swept through Shanghai, and the Shanghai government responded to it by adhering to a dynamic zero-COVID strategy. In this study, we conducted a retrospective analysis of the Omicron epidemic in Shanghai to explore the timing and performance of control measures based on the eventual size and duration of the outbreak. METHODS: We constructed an age-structured and vaccination-stratified SEPASHRD model by considering populations that had been detected or controlled before symptom onset. In addition, we retrospectively modeled the epidemic in Shanghai from 26 February 2022 to 31 May 2022 across four periods defined by events and interventions, on the basis of officially reported confirmed (58,084) and asymptomatic (591,346) cases. RESULTS: According to our model fitting, there were about 785,123 positive infections, of which about 57,585 positive infections were symptomatic infections. Our counterfactual assessment found that precise control by grid management was not so effective and that citywide static management was still needed. Universal and enforced control by citywide static management contained 87.65% and 96.29% of transmission opportunities, respectively. The number of daily new and cumulative infections could be significantly reduced if we implemented static management in advance. Moreover, if static management was implemented in the first 14 days of the epidemic, the number of daily new infections would be less than 10. CONCLUSIONS: The above research suggests that dynamic zeroing can only be achieved when strict prevention and control measures are implemented as early as possible. In addition, a lot of preparation is still needed if China wants to change its strategy in the future.

Impact of the COVID-19 pandemic on cardiac implantable electronic device implantation in China: Insights from 2 years of changing pandemic conditions

Background A substantial reduction in the number of cardiac implantable electronic device (CIED) implantation was reported in the early stages of the COVID-19 pandemic. None of the studies have yet explored changes in CIED implantation during the following pandemic. Objective To explore changes in CIED implantation during the COVID-19 pandemic from 2020 to 2021. Methods From 2019 to 2021, 177,263 patients undergone CIED implantation from 1,227 hospitals in China were included in the analysis. Generalized linear models measured the differences in CIED implantation in different periods. The relationship between changes in CIED implantation and COVID-19 cases was assessed by simple linear regression models. Results Compared with the pre-COVID-19 period, the monthly CIED implantation decreased by 17.67% (95% CI: 16.62–18.72%, p < 0.001) in 2020. In 2021, the monthly number of CIED implantation increased by 15.60% (95% CI: 14.34–16.85%, p < 0.001) compared with 2020. For every 10-fold increase in the number of COVID-19 cases, the monthly number of pacemaker implantation decreased by 429 in 2021, while it decreased by 676 in 2020. The proportion of CIED implantation in secondary medical centers increased from 52.84% in 2019 to 56.77% in 2021 (p < 0.001). For every 10-fold increase in regional accumulated COVID-19 cases, the proportion of CIED implantation in secondary centers increased by 6.43% (95% CI: 0.47–12.39%, p = 0.036). Conclusion The impact of the COVID-19 pandemic on the number of CIED implantation is diminishing in China. Improving the ability of secondary medical centers to undertake more operations may be a critical way to relieve the strain on healthcare resources during the epidemic.

Global COVID-19 Pandemic Waves: Limited Lessons Learned Worldwide over the Past Year.

The occurrence of coronavirus disease 2019 (COVID-19) was followed by a small burst of cases around the world; afterward, due to a series of emergency non-pharmaceutical interventions (NPIs), the increasing number of confirmed cases slowed down in many countries. However, the lifting of control measures by the government and the public's loosening of precautionary behaviors led to a sudden increase in cases, arousing deep concern across the globe. arousing deep concern across the globe. This study evaluates the situation of the COVID-19 pandemic in countries and territories worldwide from January 2020 to February 2021. According to the time-varying reproduction number (R(t)) of each country or territory, the results show that almost half of the countries and territories in the world have never controlled the epidemic. Among the countries and territories that had once contained the occurrence, nearly half failed to maintain their prevention and control, causing the COVID-19 pandemic to rebound across the world-resulting in even higher waves in half of the rebounding countries or territories. This work also proposes and uses a time-varying country-level transmission risk score (CTRS), which takes into account both R(t) and daily new cases, to demonstrate country-level or territory-level transmission potential and trends. Time-varying hierarchical clustering of time-varying CTRS values was used to successfully reveal the countries and territories that contributed to the recent aggravation of the global pandemic in the last quarter of 2020 and the beginning of 2021, and to identify countries and territories with an increasing risk of COVID-19 transmission in the near future. Furthermore, a regression analysis indicated that the introduction and relaxation of NPIs, including workplace closure policies and stay-at-home requirements, appear to be associated with recent global transmission changes. In conclusion, a systematic evaluation of the global COVID-19 pandemic over the past year indicates that the world is now in an unexpected situation, with limited lessons learned. Summarizing the lessons learned could help in designing effective public responses for constraining future waves of COVID-19 worldwide.

A Remote Management System for Control and Surveillance of Echinococcosis: Design and Implementation Based on Internet of Things (preprint)

Background: As a neglected cross-species parasitic disease transmitted between canines and livestock, echinococcosis remains a global public health concern with a heavy disease burden. In China, especially in the epidemic pastoral communities on the Qinghai-Tibet Plateau, the harsh climate, low socio-economic status, poor overall hygiene, and remote and insufficient access to all owned dogs exacerbate the difficulty in implementing the ambitious control programme for echinococcosis. New methods and tools are urgently needed to increase the deworming coverage and frequency, promote real-time scientific surveillance, and prevent transmission of echinococcosis. Methods: We propose the remote management system (RMS) based on IoT as a novel tool to control smart deworming devices to deliver efficient PZQ baits to dogs regularly and automatically and also as a smart digital management platform to monitor, analyse, and display the epidemic trends of echinococcosis dynamically, in real time. The RMS is an excellent alternative to existing manual deworming methods and management for surveillance of echinococcosis.Results: The smart collars are fully capable of anti-collision, waterproof, and cold-proof performance, and the battery’s energy is sufficient. The RMS can accurately analyse the monitoring data and parameters including positive rates of canine faeces, and the prevalence of echinococcosis in the general population livestock, and children. The data of dogs deworming and surveillance for echinococcosis is able to be controlled using RMS and has expanded gradually in townships to the whole Hezuo region. A total of 48 administrators (3, 3, 8, 11, 23 at the provincial, municipal, county, township, village levels, respectively) participated in the questionnaire survey, with 93.8% of its overall satisfaction rate.Conclusion: The existing difficulties and challenges in the way of prevention and control for echinococcosis can partially be resolved using the innovative, IoT-based technologies and tools. The proposed RMS to advance the upgrade of existing manual prevention and control models for echinococcosis, especially in the current ongoing COVID-19 pandemic, as social distance and community blockade continue.