Covid-19 Dynamic Monitoring and Real-Time Spatio-Temporal Forecasting

Modeling epidemic dynamics using Graph Attention based Spatial Temporal networks

The COVID-19 pandemic and influenza outbreaks have underscored the critical need for predictive models that can effectively integrate spatial and temporal dynamics to enable accurate epidemic forecasting. Traditional time-series analysis approaches have fallen short in capturing the intricate interplay between these factors. Recent advancements have witnessed the incorporation of graph neural networks and machine learning techniques to bridge this gap, enhancing predictive accuracy and providing novel insights into disease spread mechanisms. Notable endeavors include leveraging human mobility data, employing transfer learning, and integrating advanced models such as Transformers and Graph Convolutional Networks (GCNs) to improve forecasting performance across diverse geographies for both influenza and COVID-19. However, these models often face challenges related to data quality, model transferability, and potential overfitting, highlighting the necessity for more adaptable and robust approaches. This paper introduces the Graph Attention-based Spatial Temporal (GAST) model, which employs graph attention networks (GATs) to overcome these limitations by providing a nuanced understanding of epidemic dynamics through a sophisticated spatio-temporal analysis framework. Our contributions include the development and validation of the GAST model, demonstrating its superior forecasting capabilities for influenza and COVID-19 spread, with a particular focus on short-term, daily predictions. The model's application to both influenza and COVID-19 datasets showcases its versatility and potential to inform public health interventions across a range of infectious diseases.

Geoepidemiological perspective on COVID-19 pandemic review, an insight into the global impact

The COVID-19 pandemic showed major impacts, on societies worldwide, challenging healthcare systems, economies, and daily life of people. Geoepidemiology, an emerging field that combines geography and epidemiology, has played a vital role in understanding and combatting the spread of the virus. This interdisciplinary approach has provided insights into the spatial patterns, risk factors, and transmission dynamics of the COVID-19 pandemic at different scales, from local communities to global populations. Spatial patterns have revealed variations in incidence rates, with urban-rural divides and regional hotspots playing significant roles. Cross-border transmission has highlighted the importance of travel restrictions and coordinated public health responses. Risk factors such as age, underlying health conditions, socioeconomic factors, occupation, demographics, and behavior have influenced vulnerability and outcomes. Geoepidemiology has also provided insights into the transmissibility and spread of COVID-19, emphasizing the importance of asymptomatic and pre-symptomatic transmission, super-spreading events, and the impact of variants. Geoepidemiology should be vital in understanding and responding to evolving new viral challenges of this and future pandemics.

Lag-time effects of vaccination on SARS-CoV-2 dynamics in German hospitals and intensive-care units

Background

The Efficacy and effectiveness of vaccination against SARS-CoV-2 have clearly been shown by randomized trials and observational studies. Despite these successes on the individual level, vaccination of the population is essential to relieving hospitals and intensive care units. In this context, understanding the effects of vaccination and its lag-time on the population-level dynamics becomes necessary to adapt the vaccination campaigns and prepare for future pandemics.

Methods

This work applied a quasi-Poisson regression with a distributed lag linear model on German data from a scientific data platform to quantify the effects of vaccination and its lag times on the number of hospital and intensive care patients, adjusting for the influences of non-pharmaceutical interventions and their time trends. We separately evaluated the effects of the first, second and third doses administered in Germany.

Results

The results revealed a decrease in the number of hospital and intensive care patients for high vaccine coverage. The vaccination provides a significant protective effect when at least approximately 40% of people are vaccinated, whatever the dose considered. We also found a time-delayed effect of the vaccination. Indeed, the effect on the number of hospital patients is immediate for the first and second doses while for the third dose about 15 days are necessary to have a strong protective effect. Concerning the effect on the number of intensive care patients, a significant protective response was obtained after a lag time of about 15-20 days for the three doses. However, complex time trends, e.g. due to new variants, which are independent of vaccination make the detection of these findings challenging.

Conclusion

Our results provide additional information about the protective effects of vaccines against SARS-CoV-2; they are in line with previous findings and complement the individual-level evidence of clinical trials. Findings from this work could help public health authorities efficiently direct their actions against SARS-CoV-2 and be well-prepared for future pandemics.

Application of big data and artificial intelligence in epidemic surveillance and containment

Faced with the current time-sensitive COVID-19 pandemic, the overburdened healthcare systems have resulted in a strong demand to develop newer methods to control the spread of the pandemic. Big data and artificial intelligence (AI) have been leveraged amid the COVID-19 pandemic; however, little is known about their use for supporting public health efforts. In epidemic surveillance and containment, efforts are needed to treat critical patients, track and manage the health status of residents, isolate suspected cases, and develop vaccines and antiviral drugs. The applications of emerging practices of artificial intelligence and big data have become powerful "weapons" to fight against the pandemic and provide strong support in pandemic prevention and control, such as early warning, analysis and judgment, interruption and intervention of epidemic, to achieve goals of early detection, early report, early diagnosis, early isolation and early treatment. These are the decisive factors to control the spread of the epidemic and reduce the mortality. This paper systematically summarized the application of big data and AI in epidemic, and describes practical cases and challenges with emphasis on epidemic prevention and control. The included studies showed that big data and AI have the potential strength to fight against COVID-19. However, many of the proposed methods are not yet widely accepted. Thus, the most rewarding research would be on methods that promise value beyond COVID-19. More efforts are needed for developing standardized reporting protocols or guidelines for practice.

Predicting infectious disease for biopreparedness and response: A systematic review of machine learning and deep learning approaches

The complex, unpredictable nature of pathogen occurrence has required substantial efforts to accurately predict infectious diseases (IDs). With rising popularity of Machine Learning (ML) and Deep Learning (DL) techniques combined with their unique ability to uncover connections between large amounts of diverse data, we conducted a PRISMA systematic review to investigate advances in ID prediction for human and animal diseases using ML and DL. This review included the type of IDs modeled, ML and DL techniques utilized, geographical distribution, prediction tasks performed, input features utilized, spatial and temporal scales, error metrics used, computational efficiency, uncertainty quantification, and missing data handling methods. Among 237 relevant articles published between January 2001 and May 2021, highly contagious diseases in humans were most often represented, including COVID-19 (37.1%), influenza/influenza-like illnesses (9.3%), dengue (8.9%), and malaria (5.1%). Out of 37 diseases identified, 51.4% were zoonotic, 37.8% were human-only, and 8.1% were animal-only, with only 1.6% economically significant, non-zoonotic livestock diseases. Despite the number of zoonoses, 86.5% of articles modeled humans whereas only a few articles (5.1%) contained more than one host species. Eastern Asia (32.5%), North America (17.7%), and Southern Asia (13.1%) were the most represented locations. Frequent approaches included tree-based ML (38.4%) and feed-forward neural networks (26.6%). Articles predicted temporal incidence (66.7%), disease risk (38.0%), and/or spatial movement (31.2%). Less than 10% of studies addressed uncertainty quantification, computational efficiency, and missing data, which are essential to operational use and deployment. This study highlights trends and gaps in ML and DL for ID prediction, providing guidelines for future works to better support biopreparedness and response. To fully utilize ML and DL for improved ID forecasting, models should include the full disease ecology in a One-Health context, important food and agricultural diseases, underrepresented hotspots, and important metrics required for operational deployment.

•

An exponential increase in use of ML and DL models over the past decade.

•

ML/DL can model highly complex systems with a wide variety of input features.

•

ML/DL disease models should include the full disease ecology in a One-Health context.

•

Important food & agricultural diseases and key disease hotspots are underrepresented.

•

Studies must focus on operational deployment needs to better support biopreparedness.

COVID-19 outbreaks analysis in the Valencian Region of Spain in the prelude of the third wave

Introduction

The COVID-19 pandemic has led to unprecedented social and mobility restrictions on a global scale. Since its start in the spring of 2020, numerous scientific papers have been published on the characteristics of the virus, and the healthcare, economic and social consequences of the pandemic. However, in-depth analyses of the evolution of single coronavirus outbreaks have been rarely reported.

Methods

In this paper, we analyze the main properties of all the tracked COVID-19 outbreaks in the Valencian Region between September and December of 2020. Our analysis includes the evaluation of the origin, dynamic evolution, duration, and spatial distribution of the outbreaks.

Results

We find that the duration of the outbreaks follows a power-law distribution: most outbreaks are controlled within 2 weeks of their onset, and only a few last more than 2 months. We do not identify any significant differences in the outbreak properties with respect to the geographical location across the entire region. Finally, we also determine the cluster size distribution of each infection origin through a Bayesian statistical model.

Discussion

We hope that our work will assist in optimizing and planning the resource assignment for future pandemic tracking efforts.

Study of the Deep Processes of COVID-19 in Russia: Finding Ways to Identify Preventive Measures

The novel coronavirus disease 2019 (COVID-19) pandemic has had a huge impact on all areas of human life. Since the risk of biological threats will persist in the future, it is very important to ensure mobilization readiness for a prompt response to the possible emergence of epidemics of infectious diseases. Therefore, from both a theoretical and practical standpoint, it is currently necessary to conduct a thorough examination of the COVID-19 epidemic. The goal of this research is to investigate the underlying processes that led to the COVID-19 pandemic in Russia and to identify ways to improve preventive measures and ensure mobilization readiness for a quick response to potential COVID-19-like pandemics. This research will analyze the daily dynamics of the number of infection cases and the number of new lethal cases of COVID-19. We analyzed the daily number of new cases of COVID-19 infection N(d), the daily number of new lethal cases L(d), their percentage ratio L(d)/N(d) 100% in Russia for 2 years of the pandemic (from the beginning of the pandemic to 23 March 2022), the rate of increase and decrease of these indicators (dN(d)/dd and dL(d)/dd), as well as their spectra created on the basis of wavelet analysis. Wavelet analysis of the deep structure of the N(d) and L(d) wavelet spectra made it possible to identify the presence of internal cycles, the study of which makes it possible to predict the presence of days with the maximum number of infections and new deaths in a pandemic similar to COVID-19 and outline ways and methods for improving preventive measures and measures to ensure mobilization readiness for a rapid response to the potential emergence of pandemics similar to COVID-19.

Spatio-temporal variation of Covid-19 health outcomes in India using deep learning based models

Deep learning methods have become the state of the art for spatio-temporal predictive analysis in a wide range of fields, including environmental management, public health, urban planning, pollution monitoring, and so on. Despite the fact that a variety of powerful deep learning-based models can address various problem-specific issues in different research domain, it has been found that no single optimal model can outperform everywhere. Now, in the last two years, various deep learning-based studies have provided a variety of best-performing techniques for predicting COVID-19 health outcomes. In this context, this study attempts to perform a case study that investigates the spatio-temporal variation in the performance of deep-learning-based methods for predicting COVID-19 health outcomes in India. Various widely applied deep learning models namely CNN (convolutional neural network), RNN (recurrent neural network), Vanilla LSTM (long short-term memory), LSTM Autoencoder, and Bidirectional LSTM are considered to investigate their spatio-temporal performance variation. The effectiveness of the models is assessed using various metrics based on COVID-19 mortality time-series from 36 states and union territories of India.

Spatio-temporal predictions of COVID-19 test positivity in Uppsala County, Sweden: a comparative approach

Previous spatio-temporal COVID-19 prediction models have focused on the prediction of subsequent number of cases, and have shown varying accuracy and lack of high geographical resolution. We aimed to predict trends in COVID-19 test positivity, an important marker for planning local testing capacity and accessibility. We included a full year of information (June 29, 2020-July 4, 2021) with both direct and indirect indicators of transmission, e.g. mobility data, number of calls to the national healthcare advice line and vaccination coverage from Uppsala County, Sweden, as potential predictors. We developed four models for a 1-week-window, based on gradient boosting (GB), random forest (RF), autoregressive integrated moving average (ARIMA) and integrated nested laplace approximations (INLA). Three of the models (GB, RF and INLA) outperformed the naïve baseline model after data from a full pandemic wave became available and demonstrated moderate accuracy. An ensemble model of these three models slightly improved the average root mean square error to 0.039 compared to 0.040 for GB, RF and INLA, 0.055 for ARIMA and 0.046 for the naïve model. Our findings indicate that the collection of a wide variety of data can contribute to spatio-temporal predictions of COVID-19 test positivity.

COVID-19 and the Mental Health of Nursing Professionals in Brazil: Associations between Social and Clinical Contexts and Psychopathological Symptoms

The COVID-19 pandemic has had an important negative psychological impact on people worldwide, especially nursing professionals who seem to be more vulnerable to the development of psychopathological symptoms. Objective: To analyze relationships between variables from the social and clinical contexts with psychopathological symptoms in nursing professionals from different geographic regions of Brazil during the COVID-19 pandemic. Methods: Cross-sectional study carried out with 1737 nursing professionals from the five regions of Brazil. Data collection was carried out online with a questionnaire made available via Google Forms containing sociodemographic, occupational, and clinical questions, and the Symptom Assessment Scale-40-R, for the assessment of psychopathological symptoms. Differences between mean scores for the severity of psychopathological symptoms were assessed using the Mann-Whitney and Kruskall-Wallis tests. Results: There was a significant difference in the psychoticism domain scores according to Brazilian geographic region, with greater severity among professionals from the North and Northeast regions when compared with those from the South region. Social context variables (gender, age group, and marital status) and clinical variables (psychological and psychiatric follow-up; psychological or emotional support by the institution; family member, friend, neighbor, or co-worker with COVID-19, and death among them; use of psychiatric medication without a medical prescription; and taking steps to take care of their mental health) were significantly related to psychopathological symptoms. Conclusions: The results point to the importance of mental health promotion strategies for professionals through psychological or emotional support, as evidence indicates that this support can be a predictor of reduced psychological distress.

Differential diagnosis of COVID-19 and influenza

This study uses two existing data sources to examine how patients' symptoms can be used to differentiate COVID-19 from other respiratory diseases. One dataset consisted of 839,288 laboratory-confirmed, symptomatic, COVID-19 positive cases reported to the Centers for Disease Control and Prevention (CDC) from March 1, 2019, to September 30, 2020. The second dataset provided the controls and included 1,814 laboratory-confirmed influenza positive, symptomatic cases, and 812 cases with symptomatic influenza-like-illnesses. The controls were reported to the Influenza Research Database of the National Institute of Allergy and Infectious Diseases (NIAID) between January 1, 2000, and December 30, 2018. Data were analyzed using case-control study design. The comparisons were done using 45 scenarios, with each scenario making different assumptions regarding prevalence of COVID-19 (2%, 4%, and 6%), influenza (0.01%, 3%, 6%, 9%, 12%) and influenza-like-illnesses (1%, 3.5% and 7%). For each scenario, a logistic regression model was used to predict COVID-19 from 2 demographic variables (age, gender) and 10 symptoms (cough, fever, chills, diarrhea, nausea and vomiting, shortness of breath, runny nose, sore throat, myalgia, and headache). The 5-fold cross-validated Area under the Receiver Operating Curves (AROC) was used to report the accuracy of these regression models. The value of various symptoms in differentiating COVID-19 from influenza depended on a variety of factors, including (1) prevalence of pathogens that cause COVID-19, influenza, and influenza-like-illness; (2) age of the patient, and (3) presence of other symptoms. The model that relied on 5-way combination of symptoms and demographic variables, age and gender, had a cross-validated AROC of 90%, suggesting that it could accurately differentiate influenza from COVID-19. This model, however, is too complex to be used in clinical practice without relying on computer-based decision aid. Study results encourage development of web-based, stand-alone, artificial Intelligence model that can interview patients and help clinicians make quarantine and triage decisions.

Ethical Issues in AI-Enabled Disease Surveillance: Perspectives from Global Health

Infectious diseases, as COVID-19 is proving, pose a global health threat in an interconnected world. In the last 20 years, resistant infectious diseases such as severe acute respiratory syndrome (SARS), Middle East respiratory syndrome (MERS), H1N1 influenza (swine flu), Ebola virus, Zika virus, and now COVID-19 have been impacting global health defences, and aggressively flourishing with the rise of global travel, urbanization, climate change, and ecological degradation. In parallel, this extraordinary episode in global human health highlights the potential for artificial intelligence (AI)-enabled disease surveillance to collect and analyse vast amounts of unstructured and real-time data to inform epidemiological and public health emergency responses. The uses of AI in these dynamic environments are increasingly complex, challenging the potential for human autonomous decisions. In this context, our study of qualitative perspectives will consider a responsible AI framework to explore its potential application to disease surveillance in a global health context. Thus far, there is a gap in the literature in considering these multiple and interconnected levels of disease surveillance and emergency health management through the lens of a responsible AI framework.

Application of machine learning in the prediction of COVID-19 daily new cases: A scoping review

COVID-19 has produced a global pandemic affecting all over of the world. Prediction of the rate of COVID-19 spread and modeling of its course have critical impact on both health system and policy makers. Indeed, policy making depends on judgments formed by the prediction models to propose new strategies and to measure the efficiency of the imposed policies. Based on the nonlinear and complex nature of this disorder and difficulties in estimation of virus transmission features using traditional epidemic models, artificial intelligence methods have been applied for prediction of its spread. Based on the importance of machine and deep learning approaches in the estimation of COVID-19 spreading trend, in the present study, we review studies which used these strategies to predict the number of new cases of COVID-19. Adaptive neuro-fuzzy inference system, long short-term memory, recurrent neural network and multilayer perceptron are among the mostly used strategies in this regard. We compared the performance of several machine learning methods in prediction of COVID-19 spread. Root means squared error (RMSE), mean absolute error (MAE), R2 coefficient of determination (R2), and mean absolute percentage error (MAPE) parameters were selected as performance measures for comparison of the accuracy of models. R2 values have ranged from 0.64 to 1 for artificial neural network (ANN) and Bidirectional long short-term memory (LSTM), respectively. Adaptive neuro-fuzzy inference system (ANFIS), Autoregressive Integrated Moving Average (ARIMA) and Multilayer perceptron (MLP) have also have R2 values near 1. ARIMA and LSTM had the highest MAPE values. Collectively, these models are capable of identification of learning parameters that affect dissimilarities in COVID-19 spread across various regions or populations, combining numerous intervention methods and implementing what-if scenarios by integrating data from diseases having analogous trends with COVID-19. Therefore, application of these methods would help in precise policy making to design the most appropriate interventions and avoid non-efficient restrictions.