Forecasting Of COVID-19 Research Articles

COVID-19 forecasts using Internet search information in the United States

As the COVID-19 ravaging through the globe, accurate forecasts of the disease spread are crucial for situational awareness, resource allocation, and public health decision-making. Alternative to the traditional disease surveillance data collected by the United States (US) Centers for Disease Control and Prevention (CDC), big data from Internet such as online search volumes also contain valuable information for tracking infectious disease dynamics such as influenza epidemic. In this study, we develop a statistical model using Internet search volume of relevant queries to track and predict COVID-19 pandemic in the United States. Inspired by the strong association between COVID-19 death trend and symptom-related search queries such as “loss of taste”, we combine search volume information with COVID-19 time series information for US national level forecasts, while leveraging the cross-state cross-resolution spatial temporal framework, pooling information from search volume and COVID-19 reports across regions for state level predictions. Lastly, we aggregate the state-level frameworks in an ensemble fashion to produce the final state-level 4-week forecasts. Our method outperforms the baseline time-series model, while performing reasonably against other publicly available benchmark models for both national and state level forecast.

Uncertainty quantification for epidemiological forecasts of COVID-19 through combinations of model predictions

Scientific advice to the UK government throughout the COVID-19 pandemic has been informed by ensembles of epidemiological models provided by members of the Scientific Pandemic Influenza group on Modelling. Among other applications, the model ensembles have been used to forecast daily incidence, deaths and hospitalizations. The models differ in approach (e.g. deterministic or agent-based) and in assumptions made about the disease and population. These differences capture genuine uncertainty in the understanding of disease dynamics and in the choice of simplifying assumptions underpinning the model. Although analyses of multi-model ensembles can be logistically challenging when time-frames are short, accounting for structural uncertainty can improve accuracy and reduce the risk of over-confidence in predictions. In this study, we compare the performance of various ensemble methods to combine short-term (14-day) COVID-19 forecasts within the context of the pandemic response. We address practical issues around the availability of model predictions and make some initial proposals to address the shortcomings of standard methods in this challenging situation.

Early human judgment forecasts of human monkeypox, May 2022

Early human judgment forecasts of human monkeypox, May 2022

Comparing trained and untrained probabilistic ensemble forecasts of COVID-19 cases and deaths in the United States

The U.S. COVID-19 Forecast Hub aggregates forecasts of the short-term burden of COVID-19 in the United States from many contributing teams. We study methods for building an ensemble that combines forecasts from these teams. These experiments have informed the ensemble methods used by the Hub. To be most useful to policymakers, ensemble forecasts must have stable performance in the presence of two key characteristics of the component forecasts: (1) occasional misalignment with the reported data, and (2) instability in the relative performance of component forecasters over time. Our results indicate that in the presence of these challenges, an untrained and robust approach to ensembling using an equally weighted median of all component forecasts is a good choice to support public health decision-makers. In settings where some contributing forecasters have a stable record of good performance, trained ensembles that give those forecasters higher weight can also be helpful.

Jakarta COVID-19 Forecast with Bayesian PIRD Multiwave Model

Governments have to consider both socioeconomic and health conditions in handling the COVID-19 pandemic. To help them in understanding possible scenarios behind the numbers and deciding optimum policy, this study proposed a Bayesian protected-infected-recovered-dead (PIRD) multi-wave model. Compounds of the Richards curve are used to understand how many pandemic waves possibly occur, how significant is the occurrence of every single wave, and dynamic in every single wave. The model also estimated the mortality rate due to the COVID-19 pandemic and the duration between infection to death, also infection to recovery. We fitted Jakarta’s COVID-19 data from 3 March 2020 to 25 November 2021 with help of OpenBUGS. We learned that their pandemic should consist of at least two waves, expected to have three waves already. By letting social restriction be looser together with decreasing number of new infection cases, Jakarta could have its fourth and even fifth pandemic wave that starts around mid-May to mid-July 2022 and reach its peak around January to February 2023. Vice versa, they could enter the endemic phase around the end of August 2022 until the beginning of February 2023 and finally have zero COVID-19 new infection around mid-January until mid-June 2023 by having stricter social restrictions.

COVID-19 hospitalizations forecasts using internet search data

As the COVID-19 spread over the globe and new variants of COVID-19 keep occurring, reliable real-time forecasts of COVID-19 hospitalizations are critical for public health decisions on medical resources allocations. This paper aims to forecast future 2 weeks national and state-level COVID-19 new hospital admissions in the United States. Our method is inspired by the strong association between public search behavior and hospitalization admissions and is extended from a previously-proposed influenza tracking model, AutoRegression with GOogle search data (ARGO). Our LASSO-penalized linear regression method efficiently combines Google search information and COVID-19 related time series information with dynamic training and rolling window prediction. Compared to other publicly available models collected from COVID-19 forecast hub, our method achieves substantial error reduction in a retrospective out-of-sample evaluation from Jan 4, 2021, to Dec 27, 2021. Overall, we showed that our method is flexible, self-correcting, robust, accurate, and interpretable, making it a potentially powerful tool to assist healthcare officials and decision making for the current and future infectious disease outbreaks.

COVID-Forecast-Graph: An Open Knowledge Graph for Consolidating COVID-19 Forecasts and Economic Indicators via Place and Time

Abstract. The longer the COVID-19 pandemic lasts, the more apparent it becomes that understanding its social drivers may be as important as understanding the virus itself. One such social driver is misinformation and distrust in institutions. This is particularly interesting as the scientific process is more transparent than ever before. Numerous scientific teams have published datasets that cover almost any imaginable aspects of COVID-19 during the last two years. However, consistently and efficiently integrating and making sense of these separate data “silos” to scientists, decision makers, journalists, and more importantly the general public remain a key challenge with important implications for transparency. Several types of knowledge graphs have been published to tackle this issue and to enable data crosswalks by providing rich contextual information. Interestingly, none of these graphs has focused on COVID-19 forecasts despite them acting as the underpinning for decision making. In this work we motivate the need for exposing forecasts as a knowledge graph, showcase queries that run against the graph, and geographically interlink forecasts with indicators of economic impacts.

COVID-19 forecasting and intervention planning using gated recurrent unit and evolutionary algorithm.

The rapid spread of COVID-19, caused by the SARS-CoV-2 virus, has had and continues to pose a significant threat to global health. We propose a predictive model based on the gated recurrent unit (GRU) that investigates the influence of non-pharmaceutical interventions (NPIs) on the progression of COVID-19. The proposed model is validated by case studies for multiple states in the United States. It should be noted that the proposed model can be generalized to other regions of interest. The results show that the predictive model can achieve accurate forecasts across the US. The forecast is then utilized to identify the optimal mitigation policies. The goal is to identify the best stringency level for each policy that can minimize the total number of new COVID-19 cases while minimizing the mitigation costs. A meta-heuristics method, named multi-population evolutionary algorithm with differential evolution (MPEA-DE), has been developed to identify optimal mitigation strategies that minimize COVID-19 infection cases while reducing economic and other negative implications. We compared the optimal mitigation strategies identified by the MPEA-DE model with three baseline search strategies. The results show that MPEA-DE performs better than other baseline models based on prescription dominance.

BeCaked: An Explainable Artificial Intelligence Model for COVID-19 Forecasting

From the end of 2019, one of the most serious and largest spread pandemics occurred in Wuhan (China) named Coronavirus (COVID-19). As reported by the World Health Organization, there are currently more than 100 million infectious cases with an average mortality rate of about five percent all over the world. To avoid serious consequences on people’s lives and the economy, policies and actions need to be suitably made in time. To do that, the authorities need to know the future trend in the development process of this pandemic. This is the reason why forecasting models play an important role in controlling the pandemic situation. However, the behavior of this pandemic is extremely complicated and difficult to be analyzed, so that an effective model is not only considered on accurate forecasting results but also the explainable capability for human experts to take action pro-actively. With the recent advancement of Artificial Intelligence (AI) techniques, the emerging Deep Learning (DL) models have been proving highly effective when forecasting this pandemic future from the huge historical data. However, the main weakness of DL models is lacking the explanation capabilities. To overcome this limitation, we introduce a novel combination of the Susceptible-Infectious-Recovered-Deceased (SIRD) compartmental model and Variational Autoencoder (VAE) neural network known as BeCaked. With pandemic data provided by the Johns Hopkins University Center for Systems Science and Engineering, our model achieves 0.98 R^2 and 0.012 MAPE at world level with 31-step forecast and up to 0.99 R^2 and 0.0026 MAPE at country level with 15-step forecast on predicting daily infectious cases. Not only enjoying high accuracy, but BeCaked also offers useful justifications for its results based on the parameters of the SIRD model. Therefore, BeCaked can be used as a reference for authorities or medical experts to make on time right decisions.

Seven Principles for Rapid-Response Data Science: Lessons Learned from Covid-19 Forecasting

In this article, we take a step back to distill seven principles out of our experience in the spring of 2020, when our 12-person rapid-response team used skills of data science and beyond to help distribute 340,000+ units of Covid PPE. This process included tapping into domain knowledge of epidemiology and medical logistics chains, curating a relevant data repository, developing models for short-term county-level death forecasting in the US, and building a website for sharing visualization (an automated AI machine). The principles are described in the context of working with Response4Life, a then-new nonprofit organization, to illustrate their necessity. Many of these principles overlap with those in standard data-science teams, but an emphasis is put on dealing with problems that require rapid response, often resembling agile software development. The technical work from this rapid response project resulted in a paper (Altieri et al. (2021)); see also this interview for more background (Yu and Meng (2021)).

Analyzing the Impact of Lockdown in Controlling COVID-19 Spread and Future Prediction

COVID-19 outbreaks are the critical challenge to the administrative units of all worldwide nations. India is also more concerned about monitoring the virus’s spread to control its growth rate by stringent behaviour. The present COVID-19 situation has huge impact in India, and the results of various preventive measures are discussed in this paper. This research presents different trends and patterns of data sources of States that suffered from the second wave of COVID-19 in India until 3rd July 2021. The data sources were collected from the Indian Ministry of Health and Family Welfare. This work reacts particularly to many research activities to discover the lockdown effects to control the virus through traditional methods to recover and safeguard the pandemic. The second wave caused more losses in the economy than the first wave and increased the death rate. To avoid this, various methods were developed to find infected cases during the regulated national lockdown, but the infected cases still harmed unregulated incidents. The COVID-19 forecasts were made on 3rd July 2021, using exponential simulation. This paper deals with the methods to control the second wave giving various analyses reports showing the impact of lockdown effects. This highly helps to safeguard from the spread of the future pandemic.

Spatio-temporal forecasting using wavelet transform-based decision trees with application to air quality and covid-19 forecasting

We develop a new method that combines a decision tree with a wavelet transform to forecast time series data with spatial spillover effects. The method can not only improve prediction but also give good interpretability of the time series mechanism. As a feature exploration method, the wavelet transform represents information at different resolution levels, which may improve the performance of decision trees. The method is applied to simulated data, air pollution and COVID time series data sets. In the simulation, Haar, LA8, D4 and D6 wavelets are compared, with the Haar wavelet having the best performance. In the air pollution application, by using wavelet transform-based decision trees, the temporal effect of air quality index including autoregressive and seasonal effects can be described as well as the spatial correlation effect. To describe the spillover spatial effect in contiguous regions, a spatial weight is constructed to improve the modeling performance. The results show that air quality index has autoregressive, seasonal and spatial spillover effects. The wavelet transformed variables have a better forecasting performance and enhanced interpretability than the original variables. For the COVID time series of cumulative cases, spatial weighted variables are not selected which shows the lock-down policies are truly effective.

Machine Learning, Deep Learning, and Mathematical Models to Analyze Forecasting and Epidemiology of COVID-19: A Systematic Literature Review.

COVID-19 is a disease caused by SARS-CoV-2 and has been declared a worldwide pandemic by the World Health Organization due to its rapid spread. Since the first case was identified in Wuhan, China, the battle against this deadly disease started and has disrupted almost every field of life. Medical staff and laboratories are leading from the front, but researchers from various fields and governmental agencies have also proposed healthy ideas to protect each other. In this article, a Systematic Literature Review (SLR) is presented to highlight the latest developments in analyzing the COVID-19 data using machine learning and deep learning algorithms. The number of studies related to Machine Learning (ML), Deep Learning (DL), and mathematical models discussed in this research has shown a significant impact on forecasting and the spread of COVID-19. The results and discussion presented in this study are based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Out of 218 articles selected at the first stage, 57 met the criteria and were included in the review process. The findings are therefore associated with those 57 studies, which recorded that CNN (DL) and SVM (ML) are the most used algorithms for forecasting, classification, and automatic detection. The importance of the compartmental models discussed is that the models are useful for measuring the epidemiological features of COVID-19. Current findings suggest that it will take around 1.7 to 140 days for the epidemic to double in size based on the selected studies. The 12 estimates for the basic reproduction range from 0 to 7.1. The main purpose of this research is to illustrate the use of ML, DL, and mathematical models that can be helpful for the researchers to generate valuable solutions for higher authorities and the healthcare industry to reduce the impact of this epidemic.

A Review on Machine Learning Approaches in COVID-19 Pandemic Prediction and Forecasting

Novel COVID-19 Coronavirus disease, namely SARS-CoV-2, is a global pandemic and has spread to more than 200 countries. The sudden rise in the number of cases is causing a tremendous effect on healthcare services worldwide. To assist strategies in containing its spread, machine learning (ML) has been employed to effectively track the daily infected and mortality cases as well as to predict the peak growth among the states or/and country-wise. The evidence of ML in tackling previous epidemics has encouraged researchers to reciprocate with this outbreak. In this paper, recent studies that apply various ML models in predicting and forecasting COVID-19 trends have been reviewed. The development in ML has significantly supported health experts with improved prediction and forecasting. By developing prediction models, the world can prepare and mitigate the spread and impact against COVID-19.

Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.

Short-term probabilistic forecasts of the trajectory of the COVID-19 pandemic in the United States have served as a visible and important communication channel between the scientific modeling community and both the general public and decision-makers. Forecasting models provide specific, quantitative, and evaluable predictions that inform short-term decisions such as healthcare staffing needs, school closures, and allocation of medical supplies. Starting in April 2020, the US COVID-19 Forecast Hub (https://covid19forecasthub.org/) collected, disseminated, and synthesized tens of millions of specific predictions from more than 90 different academic, industry, and independent research groups. A multimodel ensemble forecast that combined predictions from dozens of groups every week provided the most consistently accurate probabilistic forecasts of incident deaths due to COVID-19 at the state and national level from April 2020 through October 2021. The performance of 27 individual models that submitted complete forecasts of COVID-19 deaths consistently throughout this year showed high variability in forecast skill across time, geospatial units, and forecast horizons. Two-thirds of the models evaluated showed better accuracy than a naïve baseline model. Forecast accuracy degraded as models made predictions further into the future, with probabilistic error at a 20-wk horizon three to five times larger than when predicting at a 1-wk horizon. This project underscores the role that collaboration and active coordination between governmental public-health agencies, academic modeling teams, and industry partners can play in developing modern modeling capabilities to support local, state, and federal response to outbreaks.

Using a Layered Ensemble of Physics-Guided Graph Attention Networks to Predict COVID-19 Trends

ABSTRACT The COVID-19 pandemic has spread rapidly and significantly impacted most countries in the world. Providing an accurate forecast of COVID-19 at multiple scales would help inform public health decisions, but recent forecasting models are typically used at the state or country level. Furthermore, traditional mathematical models are limited by simplifying assumptions, while machine learning algorithms struggle to generalize to unseen trends. This motivates the need for hybrid machine learning models that integrate domain knowledge for accurate long-term prediction. We propose a three-layer, geographically informed ensemble, an extensive peer-learning framework, for predicting COVID-19 trends at the country, continent, and global levels. As the base layer, we develop a country-level predictor using a hybrid Graph Attention Network that incorporates a modified SIR model, adaptive loss function, and edge weights informed by mobility data. We aggregated 163 country GATs to train the continent and world MLP layers of the ensemble. Our results indicate that incorporating quantitatively accurate equations and real-world data to model inter-community interactions improves the performance of spatio-temporal machine learning algorithms. Additionally, we demonstrate that integrating geographic information (continent composition) improves the performance of the world predictor in our layered architecture.

Forecasting and comparative analysis of Covid-19 cases in India and US.

The devastating waves of covid-19 have wreaked havoc on the world, particularly India and US. The article aims to predict the real-time forecasts of covid-19 confirm cases for India and US. To serve the purpose, ARIMA and NNAR based models have been used to the daily new covid-19 confirm cases. The proposed hybrid models are: (i) ARIMA-NNAR model, (ii) NNAR-ARIMA model, (iii) ARIMA-Wavelet ARIMA model, (iv) ARIMA-Wavelet ANN model, (v) NNAR-Wavelet ANN model, and (vi) NNAR-Wavelet ARIMA model. The models are performed to predict the next 45 days of daily new cases. These forecasts can help Govt. to predict the behavior of covid -19 and aware people about the upcoming third wave of covid-19. Our results suggest that hybrid models perform better than single models. We have also proved that our wavelet-based hybrid models can outdated the performance of previously defined hybrid models in terms of accuracy assessments (MAE and RMSE). We have also estimated the time-dependent reproduction number for India and US to observe the present situation.

Dynamics of SARS-CoV-2 spreading under the influence of environmental factors and strategies to tackle the pandemic: A systematic review.

COVID-19 is deemed as the most critical world health calamity of the 21st century, leading to dramatic life loss. There is a pressing need to understand the multi-stage dynamics, including transmission routes of the virus and environmental conditions due to the possibility of multiple waves of COVID-19 in the future. In this paper, a systematic examination of the literature is conducted associating the virus-laden-aerosol and transmission of these microparticles into the multimedia environment, including built environments. Particularly, this paper provides a critical review of state-of-the-art modelling tools apt for COVID-19 spread and transmission pathways. GIS-based, risk-based, and artificial intelligence-based tools are discussed for their application in the surveillance and forecasting of COVID-19. Primary environmental factors that act as simulators for the spread of the virus include meteorological variation, low air quality, pollen abundance, and spatial-temporal variation. However, the influence of these environmental factors on COVID-19 spread is still equivocal because of other non-pharmaceutical factors. The limitations of different modelling methods suggest the need for a multidisciplinary approach, including the ‘One-Health’ concept. Extended One-Health-based decision tools would assist policymakers in making informed decisions such as social gatherings, indoor environment improvement, and COVID-19 risk mitigation by adapting the control measurements.

Impact of COVID-19 forecast visualizations on pandemic risk perceptions

People worldwide use SARS-CoV-2 (COVID-19) visualizations to make life and death decisions about pandemic risks. Understanding how these visualizations influence risk perceptions to improve pandemic communication is crucial. To examine how COVID-19 visualizations influence risk perception, we conducted two experiments online in October and December of 2020 (N = 2549) where we presented participants with 34 visualization techniques (available at the time of publication on the CDC’s website) of the same COVID-19 mortality data. We found that visualizing data using a cumulative scale consistently led to participants believing that they and others were at more risk than before viewing the visualizations. In contrast, visualizing the same data with a weekly incident scale led to variable changes in risk perceptions. Further, uncertainty forecast visualizations also affected risk perceptions, with visualizations showing six or more models increasing risk estimates more than the others tested. Differences between COVID-19 visualizations of the same data produce different risk perceptions, fundamentally changing viewers’ interpretation of information.

Testing the predictive accuracy of COVID-19 forecasts

We test the predictive accuracy of forecasts of the number of COVID-19 fatalities produced by several forecasting teams and collected by the United States Centers for Disease Control and Prevention for the epidemic in the United States. We find three main results. First, at the short horizon (1 week ahead) no forecasting team outperforms a simple time-series benchmark. Second, at longer horizons (3 and 4 week ahead) forecasters are more successful and sometimes outperform the benchmark. Third, one of the best performing forecasts is the Ensemble forecast, that combines all available predictions using uniform weights. In view of these results, collecting a wide range of forecasts and combining them in an ensemble forecast may be a superior approach for health authorities, rather than relying on a small number of forecasts.