A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA

MGLEP: Multimodal Graph Learning for Modeling Emerging Pandemics with Big Data

Accurate forecasting and analysis of emerging pandemics play a crucial role in effective public health management and decision-making. Traditional approaches primarily rely on epidemiological data, overlooking other valuable sources of information that could act as sensors or indicators of pandemic patterns. In this paper, we propose a novel framework, MGLEP, that integrates temporal graph neural networks and multi-modal data for learning and forecasting. We incorporate big data sources, including social media content, by utilizing specific pre-trained language models and discovering the underlying graph structure among users. This integration provides rich indicators of pandemic dynamics through learning with temporal graph neural networks. Extensive experiments demonstrate the effectiveness of our framework in pandemic forecasting and analysis, outperforming baseline methods across different areas, pandemic situations, and prediction horizons. The fusion of temporal graph learning and multi-modal data enables a comprehensive understanding of the pandemic landscape with less time lag, cheap cost, and more potential information indicators.

A data-driven framework to assess population dynamics during novel coronavirus outbreaks: A case study on Xiamen Island, China

The outbreak of the Coronavirus Disease 2019 (COVID-19) has profoundly influenced daily life, necessitating the understanding of the relationship between the epidemic's progression and population dynamics. In this study, we present a data-driven framework that integrates GIS-based data mining technology and a Susceptible, Exposed, Infected and Recovered (SEIR) model. This approach helps delineate population dynamics at the grid and community scales and analyze the impacts of government policies, urban functional areas, and intercity flows on population dynamics during the pandemic. Xiamen Island was selected as a case study to validate the effectiveness of the data-driven framework. The results of the high/low cluster analysis provide 99% certainty (P < 0.01) that the population distribution between January 23 and March 16, 2020, was not random, a phenomenon referred to as high-value clustering. The SEIR model predicts that a ten-day delay in implementing a lockdown policy during an epidemic can lead to a significant increase in the number of individuals infected by the virus. Throughout the epidemic prevention and control period (January 23 to February 21, 2020), residential and transportation areas housed more residents. After the resumption of regular activities, the population was mainly concentrated in residential, industrial, and transportation, as well as road facility areas. Notably, the migration patterns into and out of Xiamen were primarily centered on neighboring cities both before and after the outbreak. However, migration indices from cities outside the affected province drastically decreased and approached zero following the COVID-19 outbreak. Our findings offer new insights into the interplay between the epidemic's development and population dynamics, which enhances the prevention and control of the coronavirus epidemic.

Explicit modeling of antibody levels for infectious disease simulations in the context of SARS-CoV-2

Measurable levels of immunoglobulin G antibodies develop after infections with and vaccinations against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). These antibody levels are dynamic: due to waning, antibody levels will drop over time. During the COVID-19 pandemic, multiple models predicting infection dynamics were used by policymakers to support the planning of public health policies. Explicitly integrating antibody and waning effects into the models is crucial for reliable calculations of individual infection risk. However, only few approaches have been suggested that explicitly treat these effects. This paper presents a methodology that explicitly models antibody levels and the resulting protection against infection for individuals within an agent-based model. The model was developed in response to the complexity of different immunization sequences and types and is based on neutralization titer studies. This approach allows complex population studies with explicit antibody and waning effects. We demonstrate the usefulness of our model in two use cases.

Explainable Artificial Intelligence (XAI) for Deep Learning Based Medical Imaging Classification

Recently, deep learning has gained significant attention as a noteworthy division of artificial intelligence (AI) due to its high accuracy and versatile applications. However, one of the major challenges of AI is the need for more interpretability, commonly referred to as the black-box problem. In this study, we introduce an explainable AI model for medical image classification to enhance the interpretability of the decision-making process. Our approach is based on segmenting the images to provide a better understanding of how the AI model arrives at its results. We evaluated our model on five datasets, including the COVID-19 and Pneumonia Chest X-ray dataset, Chest X-ray (COVID-19 and Pneumonia), COVID-19 Image Dataset (COVID-19, Viral Pneumonia, Normal), and COVID-19 Radiography Database. We achieved testing and validation accuracy of 90.6% on a relatively small dataset of 6432 images. Our proposed model improved accuracy and reduced time complexity, making it more practical for medical diagnosis. Our approach offers a more interpretable and transparent AI model that can enhance the accuracy and efficiency of medical diagnosis.

Machine Learning Algorithms Associate Case Numbers with SARS-CoV-2 Variants Rather Than with Impactful Mutations

During the SARS-CoV-2 pandemic, much effort has been geared towards creating models to predict case numbers. These models typically rely on epidemiological data, and as such overlook viral genomic information, which could be assumed to improve predictions, as different variants show varying levels of virulence. To test this hypothesis, we implemented simple models to predict future case numbers based on the genomic sequences of the Alpha and Delta variants, which were co-circulating in Texas and Minnesota early during the pandemic. Sequences were encoded, matched with case numbers at a future time based on collection date, and used to train two algorithms: one based on random forests and one based on a feed-forward neural network. While prediction accuracies were ≥93%, explainability analyses showed that the models were not associating case numbers with mutations known to have an impact on virulence, but with individual variants. This work highlights the necessity of gaining a better understanding of the data used for training and of conducting explainability analysis to assess whether model predictions are misleading.

Implicit feedback policies for COVID-19: why "zero-COVID" policies remain elusive

Successful epidemic modeling requires understanding the implicit feedback control strategies used by populations to modulate the spread of contagion. While such strategies can be replicated with intricate modeling assumptions, here we propose a simple model where infection dynamics are described by a three parameter feedback policy. Rather than model individuals as directly controlling the contact rate which governs the spread of disease, we model them as controlling the contact rate's derivative, resulting in a dynamic rather than kinematic model. The feedback policy used by populations across the United States which best fits observations is proportional-derivative control, where learned parameters strongly correlate with observed interventions (e.g., vaccination rates and mobility restrictions). However, this results in a non-zero "steady-state" of case counts, implying current mitigation strategies cannot eradicate COVID-19. Hence, we suggest making implicit policies a function of cumulative cases, resulting in proportional-integral-derivative control with higher potential to eliminate COVID-19.

Using geospatial social media data for infectious disease studies: a systematic review

Geospatial social media (GSM) data has been increasingly used in public health due to its rich, timely, and accessible spatial information, particularly in infectious disease research. This review synthesized 86 research articles that use GSM data in infectious diseases published between December 2013 and March 2022. These articles cover 12 infectious disease types ranging from respiratory infectious diseases to sexually transmitted diseases with spatial levels varying from the neighborhood, county, state, and country. We categorized these studies into three major infectious disease research domains: surveillance, explanation, and prediction. With the assistance of advanced statistical and spatial methods, GSM data has been widely and deeply applied to these domains, particularly in surveillance and explanation domains. We further identified four knowledge gaps in terms of contextual information use, application scopes, spatiotemporal dimension, and data limitations and proposed innovation opportunities for future research. Our findings will contribute to a better understanding of using GSM data in infectious diseases studies and provide insights into strategies for using GSM data more effectively in future research.

Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa

Coronavirus disease 2019 (COVID-19) has produced a global pandemic, which has devastating effects on health, economy and social interactions. Despite the less contraction and spread of COVID-19 in Africa compared to some other continents in the world, Africa remains amongst the most vulnerable regions due to less technology and unequipped or poor health system. Recent happenings showed that COVID-19 may stay for years owing to the discoveries of new variants (such as Omicron) and new wave of infections in several countries. Therefore, accurate prediction of new cases is vital to make informed decisions and in evaluating the measures that should be implemented. Studies on COVID-19 prediction are limited in Africa despite the risks and dangers that the virus possessed. Hence, this study was performed to predict daily COVID-19 cases in 10 African countries spread across the north, south, east, west and central Africa considering countries with few and large number of daily COVID-19 cases. Machine learning (ML) models due to their nonlinearity and accurate prediction capabilities were employed for this purpose, including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and conventional multiple linear regression (MLR) models. As any other natural process, the COVID-19 pandemic may contain both linear and nonlinear aspects. In such circumstances, neither nonlinear (ML) nor linear (MLR) models could be sufficient; hence, combining both ML and MLR models may produce better accuracy. Consequently, to improve the prediction efficiency of the ML models, novel ensemble approaches including ANN-E and SVM-E were employed. The advantage of using ensemble approaches is that they provide collective benefits of all the standalone models, thereby reducing their weaknesses and enhancing their prediction capabilities. The obtained results showed that ANFIS led to better prediction performance with MAD = 0.0106, MSE = 0.0003, RMSE = 0.0185 and R2 = 0.9059 in the validation step. The results of the proposed ensemble approaches demonstrated very high improvements in predicting the COVID-19 pandemic in Africa with MAD = 0.0073, MSE = 0.0002, RMSE = 0.0155 and R2 = 0.9616. The ANN-E improved the standalone models performance in the validation step up to 10%, 14%, 42%, 6%, 83%, 11%, 7%, 5%, 7% and 31% for Morocco, Sudan, Namibia, South Africa, Uganda, Rwanda, Nigeria, Senegal, Gabon and Cameroon, respectively. This study results offer a solid foundation in the application of ensemble approaches for predicting COVID-19 pandemic across all regions and countries in the world.

Space-Distributed Traffic-Enhanced LSTM-Based Machine Learning Model for COVID-19 Incidence Forecasting

The COVID-19 virus continues to generate waves of infections around the world. With major areas in developing countries still lagging behind in vaccination campaigns, the risk of new variants that can cause re-infections worldwide makes the monitoring and forecasting of the evolution of the virus a high priority. Having accurate models able to forecast the incidence of the spread of the virus provides help to policymakers and health professionals in managing the scarce resources in an optimal way. In this paper, a new machine learning model is proposed to forecast the spread of the virus one-week ahead in a geographic area which combines mobility and COVID-19 incidence data. The area is divided into zones or districts according to the location of the COVID-19 measuring points. A traffic-driven mobility estimate among adjacent districts is proposed to capture the spatial spread of the virus. Traffic-driven mobility in adjacent districts will be used together with COVID-19 incidence data to feed a new deep learning LSTM-based model which will extract patterns from mobility-modulated COVID-19 incidence spatiotemporal data in order to optimize one-week ahead estimations. The model is trained and validated with open data available for the city of Madrid (Spain) for 3 different validation scenarios. A baseline model based on previous literature able to extract temporal patterns in COVID-19 incidence time series is also trained with the same dataset. The results show that the proposed model, based on the combination of traffic and COVID-19 incidence data, is able to outperform the baseline model in all the validation scenarios.

Analytical investigation of compartmental models and measure for reactions of governments

The ongoing coronavirus disease 2019 (COVID-19) pandemic poses a major threat to the worldwide health care. In this context, epidemic modelling is an integral part of containment strategies. Compartmental models are typically used for this purpose. Analytical solutions of the two distinct but connected Susceptible-Infectious-Recovered-Deceased (SIRD) and Susceptible-Infectious-Quarantine-Recovered (SIQR) models are presented in this study. Furthermore, the behaviour at the start of a disease outbreak is derived. This analysis shows that a combination of transmission, recovery and isolation rates dominates the behaviour at the start of an epidemic. In addition, the loss occurring due to quarantine and lockdown measures is investigated, where it can be observed that quarantine procedures lead to a smaller loss in comparison with lockdown regulations. Within this framework, optimized strategies that lead to a constant epidemic peak or a minimized loss are presented.

A data-driven hybrid ensemble AI model for COVID-19 infection forecast using multiple neural networks and reinforced learning

The COVID-19 outbreak poses a huge challenge to international public health. Reliable forecast of the number of cases is of great significance to the planning of health resources and the investigation and evaluation of the epidemic situation. The data-driven machine learning models can adapt to complex changes in the epidemic situation without relying on correct physical dynamics modeling, which are sensitive and accurate in predicting the development of the epidemic. In this paper, an ensemble hybrid model based on Temporal Convolutional Networks (TCN), Gated Recurrent Unit (GRU), Deep Belief Networks (DBN), Q-learning, and Support Vector Machine (SVM) models, namely TCN-GRU-DBN-Q-SVM model, is proposed to achieve the forecasting of COVID-19 infections. Three widely-used predictors, TCN, GRU, and DBN are used as elements of the hybrid model ensembled by the weights provided by reinforcement learning method. Furthermore, an error predictor built by SVM, is trained with validation set, and the final prediction result could be obtained by combining the TCN-GRU-DBN-Q model with the SVM error predictor. In order to investigate the forecasting performance of the proposed hybrid model, several comparison models (TCN-GRU-DBN-Q, LSTM, N-BEATS, ANFIS, VMD-BP, WT-RVFL, and ARIMA models) are selected. The experimental results show that: (1) the prediction effect of the TCN-GRU-DBN-Q-SVM model on COVID-19 infection is satisfactory, which has been verified in three national infection data from the UK, India, and the US, and the proposed model has good generalization ability; (2) in the proposed hybrid model, SVM can efficiently predict the possible error of the predicted series given by TCN-GRU-DBN-Q components; (3) the integrated weights based on Q-learning can be adaptively adjusted according to the characteristics of the data in the forecasting tasks in different countries and multiple situations, which ensures the accuracy, robustness and generalization of the proposed model.