COVID-19 Case Data Research Articles

Intrinsic and effective severity of COVID-19 cases infected with the ancestral strain and Omicron BA.2 variant in Hong Kong.

Understanding severity of infections with SARS-CoV-2 and its variants is crucial to inform public health measures. Here we used COVID-19 patient data from Hong Kong to characterise the severity profile of COVID-19. Time-varying and age-specific effective severity measured by case-hospitalization risk and hospitalization-fatality risk was estimated with all individual COVID-19 case data collected in Hong Kong from 23 January 2020 through to 26 October 2022 over six epidemic waves. The intrinsic severity of Omicron BA.2 was compared with the estimate for the ancestral strain with the data from unvaccinated patients without previous infections. With 32,222 COVID-19 hospitalizations and 9,669 deaths confirmed over 6 epidemic waves, the time-varying hospitalization fatality risk dramatically increased from below 10% before the largest fifth wave of Omicron BA.2, to 41% during the peak of the fifth wave when hospital resources were severely constrained. The age-specific fatality risk in unvaccinated hospitalized Omicron cases was comparable to the estimates for unvaccinated cases with the ancestral strain. During epidemics predominated by Omicron BA.2, fatality risk was highest amongst older unvaccinated patients. Omicron has comparable intrinsic severity to the ancestral Wuhan strain although the effective severity is substantially lower in Omicron cases due to vaccination.

Changes in traffic crash patterns: Before and after the outbreak of COVID-19 in Florida

In the twentieth year of the twenty-first century, humanity is facing an unprecedented global crisis owing to the COVID-19 pandemic. It has brought about drastic changes in the way we live and work, as well as the way we move from one place to another, namely transportation. Previous studies have preliminarily found that mobility, travel behavior, and road traffic safety status experienced great changes after the outbreak of the COVID-19. The objective of this study is to explore how crash patterns have changed, as well as the contributing factors of such changes and the heterogeneity between counties in Florida. Thus, data of COVID-19 cases, crash, socioeconomic factors, and traffic volume of 2019 and 2020 are collected. Preliminary analyses show a considerable reduction from March to June. Substantial changes are shown in the proportions of crashes by time of occurrence and injury severity. Two types of statistical models are developed to identify factors of (1) changes in the percentages of crashes by type and (2) the numbers of crashes by type. The developed models reveal various demographic, socioeconomic, and travel factors. After controlling other factors, the total numbers of crashes are 14% lower after the outbreak. The most significant reductions are observed in peak-hour (22%), while no significant change is found in fatal crashes. The results show that the number of crashes has significantly decreased even after controlling the traffic volume, but some crash types (e.g., fatal) did not show a significant reduction. The findings are expected to provide some insights into better transportation planning and management to ensure traffic safety in a possible future epidemic.

Zero-Inflated Time Series Clustering Via Ensemble Thick-Pen Transform

This study develops a new clustering method for high-dimensional zero-inflated time series data. The proposed method is based on thick-pen transform (TPT), in which the basic idea is to draw along the data with a pen of a given thickness. Since TPT is a multi-scale visualization technique, it provides some information on the temporal tendency of neighborhood values. We introduce a modified TPT, termed ‘ensemble TPT (e-TPT)’, to enhance the temporal resolution of zero-inflated time series data that is crucial for clustering them efficiently. Furthermore, this study defines a modified similarity measure for zero-inflated time series data considering e-TPT and proposes an efficient iterative clustering algorithm suitable for the proposed measure. Finally, the effectiveness of the proposed method is demonstrated by simulation experiments and two real datasets: step count data and newly confirmed COVID-19 case data.

Polynomial Regression Model to Predict Future Covid Cases

Accurate case predictions are essential for efficient public health management and resource allocation since the COVID-19 pandemic has had a substantial impact on economies and global health. Using polynomial regression, a machine learning technique that fits a polynomial function to the data, this research seeks to create a predictive model for future COVID-19 cases. The model takes into consideration the elements such as population density, healthcare facilities, and governmental initiatives using historical COVID-19 case data from India. In order to forecast the number of upcoming COVID-19 instances, the polynomial regression model is employed. The model's effectiveness is assessed using a number of measures, including mean squared error and R-squared. The outcomes demonstrate that the polynomial regression model can precisely forecast the trend of COVID-19 instances over time. This approach can be useful for forecasting the spread of the virus and informing public health policies. The limitations and future directions of the model are also discussed. Furthermore, the model's adaptability to changing trends and its ability to capture non-linear relationships between variables, make it a promising tool for forecasting future pandemics and other public health crises.

Waning vaccine response to severe COVID-19 outcomes during omicron predominance in Thailand.

The COVID-19 pandemic has evolved quickly, with different variants of concern resulting in the need to offer continued protection through booster vaccinations. The duration of enhanced protection with booster doses against severe COVID-19 is still unclear. Understanding this is critical to recommendations on the frequency of future booster doses. Utilising a Hospital Information System for COVID-19 established in Chiang Mai, Thailand, we conducted a cohort study by linking patient-level data of laboratory-confirmed COVID-19 cases to the national immunization records, during the omicron predominant period (1 February- 31 July 2022). Out of 261,103 adults with COVID-19 included in the study, there were 333 (0.13%) severe COVID-19 cases and 190 (0.07%) deaths. Protection against severe COVID-19 was highest with boosters received >14-60 days prior to positive test (93%) and persisted at >60-120 days (91%) but started to wane at >120-180 days (77%) and further at >180 days (68%). The rate of waning differed with age. Those ≥70 years showed faster waning of booster vaccine responses as compared to those aged 18-49 years, who retained good responses up to 180 days. Equivalent risk reduction against severe COVID-19 was seen with all the vaccine types used as boosters in Thailand. Booster doses provided high levels of protection against severe COVID-19 with omicron, up to 4 months. Repeat boosters will be required to continue protection beyond 4 months, particularly in the elderly. mRNA and viral vector vaccines can be used flexibly to improve booster coverage.

Exploration of the COVID-19 pandemic at the neighborhood level in an intra-urban setting.

The COVID-19 pandemic represents a worldwide threat to health. Since its onset in 2019, the pandemic has proceeded in different phases, which have been shaped by a complex set of influencing factors, including public health and social measures, the emergence of new virus variants, and seasonality. Understanding the development of COVID-19 incidence and its spatiotemporal patterns at a neighborhood level is crucial for local health authorities to identify high-risk areas and develop tailored mitigation strategies. However, analyses at the neighborhood level are scarce and mostly limited to specific phases of the pandemic. The aim of this study was to explore the development of COVID-19 incidence and spatiotemporal patterns of incidence at a neighborhood scale in an intra-urban setting over several pandemic phases (March 2020-December 2021). We used reported COVID-19 case data from the health department of the district Berlin-Neukölln, Germany, additional socio-demographic data, and text documents and materials on implemented public health and social measures. We examined incidence over time in the context of the measures and other influencing factors, with a particular focus on age groups. We used incidence maps and spatial scan statistics to reveal changing spatiotemporal patterns. Our results show that several factors may have influenced the development of COVID-19 incidence. In particular, the far-reaching measures for contact reduction showed a substantial impact on incidence in Neukölln. We observed several age group-specific effects: school closures had an effect on incidence in the younger population (< 18 years), whereas the start of the vaccination campaign had an impact primarily on incidence among the elderly (> 65 years). The spatial analysis revealed that high-risk areas were heterogeneously distributed across the district. The location of high-risk areas also changed across the pandemic phases. In this study, existing intra-urban studies were supplemented by our investigation of the course of the pandemic and the underlying processes at a small scale over a long period of time. Our findings provide new insights for public health authorities, community planners, and policymakers about the spatiotemporal development of the COVID-19 pandemic at the neighborhood level. These insights are crucial for guiding decision-makers in implementing mitigation strategies.

Perbandingan Algoritma K-Means dan Algoritma K-Medoids Pada Kasus Covid-19 di Indonesia

Analyzing Covid-19 data has been conducted in many types of research, but research on classifying each case from Covid-19 data in all provinces in Indonesia has yet to be available. This study uses two clustering algorithms, namely K-Means and K-Medoids, to classify positive cases recovered and died in the Covid-19 data into three clusters, namely low, medium and high. The research data is Covid-19 case data in all provinces in Indonesia from 2020 to 2021. In the clustering calculations, the three distance methods used in this study are the Chebyshev Distance, Manhattan Distance, and Euclidean Distance. Based on the Silhouette Coefficient test results for the three distance calculation methods, it was found that Manhattan Distance is the best distance calculation method for K-Means and K-Medoids. Furthermore, the results of testing the Sum Squared Error (SSE), Silhouette Coefficient (SC) and Davies Index Bouldin (DBI) methods for the resulting clusters show that the value generated by the K-Means algorithm is higher in the SC and DBI methods. This result is evidenced by the SC value of 0.838; 0.838; and 0.925 in positive cases, recovered and died. While the DBI value is 0.305 for positive cases, 0.295 for recovered cases and 1.569 for dead cases. Based on these values, it proves that K-Means is superior in grouping and placing clusters compared to K-Medoids.

Wastewater Surveillance Can Function as an Early Warning System for COVID-19 in Low-Incidence Settings.

During the first two years of the COVID-19 pandemic, Australia implemented a series of international and interstate border restrictions. The state of Queensland experienced limited COVID-19 transmission and relied on lockdowns to stem any emerging COVID-19 outbreaks. However, early detection of new outbreaks was difficult. In this paper, we describe the wastewater surveillance program for SARS-CoV-2 in Queensland, Australia, and report two case studies in which we aimed to assess the potential for this program to provide early warning of new community transmission of COVID-19. Both case studies involved clusters of localised transmission, one originating in a Brisbane suburb (Brisbane Inner West) in July-August 2021, and the other originating in Cairns, North Queensland in February-March 2021. Publicly available COVID-19 case data derived from the notifiable conditions (NoCs) registry from the Queensland Health data portal were cleaned and merged spatially with the wastewater surveillance data using statistical area 2 (SA2) codes. The positive predictive value and negative predictive value of wastewater detection for predicting the presence of COVID-19 reported cases were calculated for the two case study sites. Early warnings for local transmission of SARS-CoV-2 through wastewater surveillance were noted in both the Brisbane Inner West cluster and the Cairns cluster. The positive predictive value of wastewater detection for the presence of notified cases of COVID-19 in Brisbane Inner West and Cairns were 71.4% and 50%, respectively. The negative predictive value for Brisbane Inner West and Cairns were 94.7% and 100%, respectively. Our findings highlight the utility of wastewater surveillance as an early warning tool in low COVID-19 transmission settings.

Tracking COVID-19 in the United States With Surveillance of Aggregate Cases and Deaths.

Early during the COVID-19 pandemic, the Centers for Disease Control and Prevention (CDC) leveraged an existing surveillance system infrastructure to monitor COVID-19 cases and deaths in the United States. Given the time needed to report individual-level (also called line-level) COVID-19 case and death data containing detailed information from individual case reports, CDC designed and implemented a new aggregate case surveillance system to inform emergency response decisions more efficiently, with timelier indicators of emerging areas of concern. We describe the processes implemented by CDC to operationalize this novel, multifaceted aggregate surveillance system for collecting COVID-19 case and death data to track the spread and impact of the SARS-CoV-2 virus at national, state, and county levels. We also review the processes established to acquire, process, and validate the aggregate number of cases and deaths due to COVID-19 in the United States at the county and jurisdiction levels during the pandemic. These processes include time-saving tools and strategies implemented to collect and validate authoritative COVID-19 case and death data from jurisdictions, such as web scraping to automate data collection and algorithms to identify and correct data anomalies. This topical review highlights the need to prepare for future emergencies, such as novel disease outbreaks, by having an event-agnostic aggregate surveillance system infrastructure in place to supplement line-level case reporting for near-real-time situational awareness and timely data.

Fitting and validation of an agent-based model for COVID-19 case forecasting in workplaces and universities.

COVID-19 forecasting models have been critical in guiding decision-making on surveillance testing, social distancing, and vaccination requirements. Beyond influencing public health policies, an accurate COVID-19 forecasting model can impact community spread by enabling employers and university leaders to adapt worksite policies and practices to contain or mitigate outbreaks. While many such models have been developed for COVID-19 forecasting at the national, state, county, or city level, only a few models have been developed for workplaces and universities. Furthermore, COVID-19 forecasting models have rarely been validated against real COVID-19 case data. Here we present the systematic parameter fitting and validation of an agent-based compartment model for the forecasting of daily COVID-19 cases in single-site workplaces and universities with real-world data. Our approaches include manual fitting, where initial model parameters are chosen based on historical data, and automated fitting, where parameters are chosen based on candidate case trajectory simulations that result in best fit to prevalence estimation data. We use a 14-day fitting window and validate our approaches on 7- and 14-day testing windows with real COVID-19 case data from one employer. Our manual and automated fitting approaches accurately predicted COVID-19 case trends and outperformed the baseline model (no parameter fitting) across multiple scenarios, including a rising case trajectory (RMSLE values: 2.627 for baseline, 0.562 for manual fitting, 0.399 for automated fitting) and a decreasing case trajectory (RMSLE values: 1.155 for baseline, 0.537 for manual fitting, 0.778 for automated fitting). Our COVID-19 case forecasting model allows decision-makers at workplaces and universities to proactively respond to case trend forecasts, mitigate outbreaks, and promote safety.

A multi-strain model with asymptomatic transmission: Application to COVID-19 in the US

COVID-19, induced by the SARS-CoV-2 infection, has caused an unprecedented pandemic in the world. New variants of the virus have emerged and dominated the virus population. In this paper, we develop a multi-strain model with asymptomatic transmission to study how the asymptomatic or pre-symptomatic infection influences the transmission between different strains and control strategies that aim to mitigate the pandemic. Both analytical and numerical results reveal that the competitive exclusion principle still holds for the model with the asymptomatic transmission. By fitting the model to the COVID-19 case and viral variant data in the US, we show that the omicron variants are more transmissible but less fatal than the previously circulating variants. The basic reproduction number for the omicron variants is estimated to be 11.15, larger than that for the previous variants. Using mask mandate as an example of non-pharmaceutical interventions, we show that implementing it before the prevalence peak can significantly lower and postpone the peak. The time of lifting the mask mandate can affect the emergence and frequency of subsequent waves. Lifting before the peak will result in an earlier and much higher subsequent wave. Caution should also be taken to lift the restriction when a large portion of the population remains susceptible. The methods and results obtained her e may be applied to the study of the dynamics of other infectious diseases with asymptomatic transmission using other control measures.

Epidemic highs and lows: a stochastic diffusion model for active cases

We derive a stochastic epidemic model for the evolving density of infective individuals in a large population. Data shows main features of a typical epidemic consist of low periods interspersed with outbreaks of various intensities and duration. In our stochastic differential model, a novel reproductive term combines a factor expressing the recent notion of ‘attenuated Allee effect’ and a capacity factor is controlling the size of the process. Simulation of this model produces sample paths of the stochastic density of infectives, which behave much like long-time Covid-19 case data of recent years. Writing the process as a stochastic diffusion allows us to derive its stationary distribution, showing the relative time spent in low levels and in outbursts. Much of the behaviour of the density of infectives can be understood in terms of the interacting drift and diffusion coefficient processes, or, alternatively, in terms of the balance between noise level and the attenuation parameter of the Allee effect. Unexpected results involve the effect of increasing overall noise variance on the density of infectives, in particular on its level-crossing function.

Superspreading potentials of SARS-CoV-2 Delta variants across different contact settings in Eastern China: A retrospective observational study

ObjectivesAs the genetic variants of SARS-CoV-2 continuously pose threats to global health, evaluating superspreading potentials of emerging genetic variants is of importance for region-wide control of COVID-19 outbreaks. MethodsBy using detailed epidemiological contact tracing data of test-positive COVID-19 cases collected between July and August 2021 in Nanjing and Yangzhou, China, we assessed the superspreading potential of outbreaks seeded by SARS-CoV-2 Delta variants. The transmission chains and case-clusters were constructed according to the individual-based surveillance data. We modelled the disease transmission as a classic branching process with transmission heterogeneity governed by negative binomial models. Subgroup analysis was conducted by different contact settings and age groups. ResultsWe reported a considerable heterogeneity in the contact patterns and transmissibility of Delta variants in eastern China. We estimated an expected 14% (95% CI: 11–16%) of the most infectious cases generated 80% of the total transmission. ConclusionsDelta variants demonstrated a significant potential of superspreading under strict control measures and active COVID-19 detecting efforts. Enhancing the surveillance on disease transmissibility especially in high-risk settings, along with rapid contact tracing and case isolations would be one of the key factors to mitigate the epidemic caused by the emerging genetic variants of SARS-CoV-2.

The effect of changing COVID-19 restrictions on the transmission rate in a veterinary clinic

With the declaration of the COVID-19 pandemic by the World Health Organization on March 11, 2020, the University of Tennessee College of Veterinary Medicine (UTCVM), like other institutions, restructured their services to reduce the potential spread of the COVID-19 virus while simultaneously providing critical and essential veterinary services. A mathematical model was developed to predict the change in the level of possible COVID-19 infections due to the increased number of potential contacts within the UTCVM hospital. A system of ordinary differential equations with different compartments for UTCVM individuals and the Knox county population was formulated to show the dynamics of transmission and the number of confirmed cases. Key transmission rates in the model were estimated using COVID-19 case data from the surrounding county and UTCVM personnel. Simulations from this model show the increasing number of COVID-19 cases among UTCVM personnel as the number of daily clients and the number of veterinary staff in the clinic are increased. We also investigate how changes within the Knox county community impact the UTCVM hospital. These scenarios show the importance of understanding the effects of re-opening scenarios in veterinary teaching hospitals.

Global antibiotic use during the COVID-19 pandemic: analysis of pharmaceutical sales data from 71 countries, 2020-2022.

Despite bacterial coinfection rates of less than 10%, antibiotics are prescribed to an estimated 75% of patients with COVID-19, potentially exacerbating antimicrobial resistance. We estimated the associations of COVID-19 cases and vaccinations with global antibiotic sales during the first two years of the COVID-19 pandemic. We obtained monthly data on broad-spectrum antibiotic sales volumes (cephalosporins, penicillins, macrolides, and tetracyclines) in 71 countries during March 2020-May 2022 from the IQVIA MIDAS® database. These data were combined with country-month-level COVID-19 case and vaccination data from Our World in Data. We used least squares (pooled) and fixed-effects panel data regression models, accounting for country characteristics, to estimate the associations between antibiotic sales volumes and COVID-19 cases and vaccinations per 1000 people. Sales of all four antibiotics fell sharply during April and May 2020, followed by a gradual rise to near pre-pandemic levels through May 2022. In fixed-effects regression models, a 10% increase in monthly COVID-19 cases was associated with 0.2%-0.3% higher sales of cephalosporins, 0.2%-0.3% higher sales of penicillins, 0.4%-0.6% higher sales of macrolides, and 0.3% higher sales of all four antibiotics combined per 1000 people. Across continents, a 10% increase in monthly COVID-19 cases was associated with 0.8%, 1.3%, and 1.5% higher macrolides sales in Europe, North America, and Africa respectively. Sales of other antibiotics across continent were also positively associated with COVID-19 cases, although the estimated associations were smaller in magnitude. No consistent associations were observed between antibiotic sales and COVID-19 vaccinations. Results from pooled regression analysis were similar to those from the fixed-effects models. Antibiotic sales were positively associated with COVID-19 cases globally during 2020-2022. Our findings underline that antibiotic stewardship in the context of COVID-19 remains essential. Bill & Melinda Gates Foundation.

Revisiting classical SIR modelling in light of the COVID-19 pandemic.

Classical infectious disease models during epidemics have widespread usage, from predicting the probability of new infections to developing vaccination plans for informing policy decisions and public health responses. However, it is important to correctly classify reported data and understand how this impacts estimation of model parameters. The COVID-19 pandemic has provided an abundant amount of data that allow for thorough testing of disease modelling assumptions, as well as how we think about classical infectious disease modelling paradigms. We aim to assess the appropriateness of model parameter estimates and prediction results in classical infectious disease compartmental modelling frameworks given available data types (infected, active, quarantined, and recovered cases) for situations where just one data type is available to fit the model. Our main focus is on how model prediction results are dependent on data being assigned to the right model compartment. We first use simulated data to explore parameter reliability and prediction capability with three formulations of the classical Susceptible-Infected-Removed (SIR) modelling framework. We then explore two applications with reported data to assess which data and models are sufficient for reliable model parameter estimation and prediction accuracy: a classical influenza outbreak in a boarding school in England and COVID-19 data from the fall of 2020 in Missoula County, Montana, USA. We demonstrated the magnitude of parameter estimation errors and subsequent prediction errors resulting from data misclassification to model compartments with simulated data. We showed that prediction accuracy in each formulation of the classical disease modelling framework was largely determined by correct data classification versus misclassification. Using a classical example of influenza epidemics in an England boarding school, we argue that the Susceptible-Infected-Quarantined-Recovered (SIQR) model is more appropriate than the commonly employed SIR model given the data collected (number of active cases). Similarly, we show in the COVID-19 disease model example that reported active cases could be used inappropriately in the SIR modelling framework if treated as infected. We demonstrate the role of misclassification of disease data and thus the importance of correctly classifying reported data to the proper compartment using both simulated and real data. For both a classical influenza data set and a COVID-19 case data set, we demonstrate the implications of using the "right" data in the "wrong" model. The importance of correctly classifying reported data will have downstream impacts on predictions of number of infections, as well as minimal vaccination requirements.

A novel prediction model based on decomposition-integration and error correction for COVID-19 daily confirmed and death cases

Coronavirus disease (COVID-19) has infected billion people around the world and affected the economy, but most countries are considering reopening, so the COVID-19 daily confirmed and death cases have increased greatly. It is very necessary to predict the COVID-19 daily confirmed and death cases in order to help every country formulate prevention policies. To enhance the prediction performance, this paper proposes a prediction model based on improved variational mode decomposition by sparrow search algorithm (SVMD), improved kernel extreme learning machine by Aquila optimizer algorithm (AO-KELM) and error correction idea, named SVMD-AO-KELM-error for short-term prediction of COVID-19 cases. Firstly, to solve mode number and penalty factor selection of variational mode decomposition (VMD), an improved VMD based on sparrow search algorithm (SSA), named SVMD, is proposed. SVMD decomposes the COVID-19 case data into some intrinsic mode function (IMF) components and residual is considered. Secondly, to properly selected regularization coefficients and kernel parameters of kernel extreme learning machine (KELM) and improve the prediction performance of KELM, an improved KELM by Aquila optimizer (AO) algorithm, named AO-KELM, is proposed. Each component is predicted by AO-KELM. Then, the prediction error of IMF and residual are predicted by AO-KELM to correct prediction results, which is error correction idea. Finally, prediction results of each component and error prediction results are reconstructed to get final prediction results. Through the simulation experiment of the COVID-19 daily confirmed and death cases in Brazil, Mexico, and Russia and comparison with twelve comparative models, simulation experiment gives that SVMD-AO-KELM-error has best prediction accuracy. It also proves that the proposed model can be used to predict the pandemic COVID-19 cases and offers a novel approach for COVID-19 cases prediction.

Non-pharmaceutical Interventions and COVID-19: Do County- and State-Level Policies Predict the Spread of COVID-19?

This study examines the impact of county- and state-level policies on the spread and severity of COVID-19 in communities in the USA during the first wave of the COVID-19 pandemic. We use county-level COVID-19 death and case data to examine the impact of county- and state-level mandates and non-pharmaceutical interventions (NPIs) on the spread and severity of COVID-19. Following previous work by Amuendo-Dorantes et al. (2020), we utilize a strategy that incorporates the duration of NPI implementation within a county. Specifically, we examine aggregated measures of mask mandates, daycare closures, stay-at-home orders, and restaurant and bar closures. In addition to the implementation and duration of NPI policy, we examine the role of pre-existing factors that contribute to social determinants of health in a locality. We incorporate information on the incidence of prior health conditions, socio-economic factors, and demographics including racial and ethnic composition, share of immigrant population of counties, and state governance in our estimations. To alleviate the possible endogeneity of COVID-19 outcomes and NPIs, we use instrumental variable estimation and our results show that collectively NPIs decreased the intensity of the pandemic by decreasing the total deaths and cases. Furthermore, we find the magnitude of the impact of NPIs increases the longer they are implemented. We also estimate a specification that allows for heterogeneity of NPI impact based on the racial and ethnic composition of counties. Our results suggest that NPIs have a non-uniform impact in counties with different racial and ethnic compositions.

Forecast covid-19 cases and fatalities to help understand what drives transmission rate in Tamil Nadu – India

A newly emerged human Covid-19 virus from Wuhan, China caused by SARS-Cov2 having 96.1% similar genomic sequence as that of a bat has resulted in global pandemic and adversely affected the healthcare sector in terms of management, manpower, planning. The findings can be used to help the healthcare sector with better pandemic management and identify the root causes and the factors affecting the transmission rate of covid-19 cases. The study focuses on: i) Forecasting covid-19 cases, ii) to study relationship of temperature, density, lockdown, and seasonal factor on the covid-19 transmission rate, iii) how forecasting will help in terms of managerial aspects. The method used to forecast covid-19 cases was data visualization of secondary data accessed and gathered from Kaggle by using Tableau as a tool. It was done by establishing multiple connections; comparing temperature, density, lockdown and seasonal factor individually with covid-19 cases and its effect on the viral transmission rate. Density is found to be independent of transmission rate, which is affected by temperature, seasonal factor &amp; lockdown. The rate was less at higher temperatures and under a complete lockdown imposed on the State. Healthcare workers will have a better hold in the management henceforth with creative patient consideration approaches like customized medical coverage, clinical choice supportive networks and better resource planning with the forecasted data of Covid-19 cases.

Multi-Source Data and Machine Learning-Based Refined Governance for Responding to Public Health Emergencies in Beijing: A Case Study of COVID-19

The outbreak of COVID-19 in Beijing has been sporadic since the beginning of 2022 and has become increasingly severe since October. In China’s policy of insisting on dynamic clearance, fine-grained management has become the focus of current epidemic prevention and control. In this paper, we conduct a refined COVID-19 risk prediction and identification of its influencing factors in Beijing based on neighborhood-scale spatial statistical units. We obtained geographic coordinate data of COVID-19 cases in Beijing and quantified them into risk indices of each statistical unit. Additionally, spatial autocorrelation was used to analyze the epidemic risk clustering characteristics. With the multi-source data, 20 influencing elements were constructed, and their spatial heterogeneity was explored by screening 8 for Multiscale Geographically weighted regression (MGWR) model analysis. Finally, a neural network classification model was used to predict the risk of COVID-19 within the sixth ring of Beijing. The MGWR model and the neural network classification model showed good performance: the R2 of the MGWR model was 0.770, and the accuracy of the neural network classification model was 0.852. The results of this study show that: (1) COVID-19 risk is uneven, with the highest clustering within the Fifth Ring Road of Beijing; (2) The results of the MGWR model show that population structure, population density, road density, residential area density, and living service facility density have significant spatial heterogeneity on COVID-19 risk; and (3) The prediction results show a high COVID-19 risk, with the most severe risk being in the eastern, southeastern and southern regions. It should be noted that the prediction results are highly consistent with the current epidemic situation in Shijingshan District, Beijing, and can provide a strong reference for fine-grained epidemic prevention and control in Beijing.