DeepCOVIDNet: An Interpretable Deep Learning Model for Predictive Surveillance of COVID-19 Using Heterogeneous Features and Their Interactions

Identifying First-Trimester Risk Factors for SGA-LGA Using Weighted Inheritance Voting Ensemble Learning

The classification of fetuses as Small for Gestational Age (SGA) and Large for Gestational Age (LGA) is a critical aspect of neonatal health assessment. SGA and LGA, terms used to describe fetal weights that fall below or above the expected weights for Appropriate for Gestational Age (AGA) fetuses, indicate intrauterine growth restriction and excessive fetal growth, respectively. Early prediction and assessment of latent risk factors associated with these classifications can facilitate timely medical interventions, thereby optimizing the health outcomes for both the infant and the mother. This study aims to leverage first-trimester data to achieve these objectives. This study analyzed data from 7943 pregnant women, including 424 SGA, 928 LGA, and 6591 AGA cases, collected from 2015 to 2021 at the Third Affiliated Hospital of Sun Yat-sen University in Guangzhou, China. We propose a novel algorithm, named the Weighted Inheritance Voting Ensemble Learning Algorithm (WIVELA), to predict the classification of fetuses into SGA, LGA, and AGA categories based on biochemical parameters, maternal factors, and morbidity during pregnancy. Additionally, we proposed algorithms for relevance determination based on the classifier to ascertain the importance of features associated with SGA and LGA. The proposed classification solution demonstrated a notable average accuracy rate of 92.12% on 10-fold cross-validation over 100 loops, outperforming five state-of-the-art machine learning algorithms. Furthermore, we identified significant latent maternal risk factors directly associated with SGA and LGA conditions, such as weight change during the first trimester, prepregnancy weight, height, age, and obstetric factors like fetal growth restriction and birthing LGA baby. This study also underscored the importance of biomarker features at the end of the first trimester, including HDL, TG, OGTT-1h, OGTT-0h, OGTT-2h, TC, FPG, and LDL, which reflect the status of SGA or LGA fetuses. This study presents innovative solutions for classifying and identifying relevant attributes, offering valuable tools for medical teams in the clinical monitoring of fetuses predisposed to SGA and LGA conditions during the initial stage of pregnancy. These proposed solutions facilitate early intervention in nutritional care and prenatal healthcare, thereby contributing to enhanced strategies for managing the health and well-being of both the fetus and the expectant mother.

Changes to Public Health Surveillance Methods Due to the COVID-19 Pandemic: Scoping Review

BACKGROUND

Public health surveillance plays a vital role in informing public health decision-making. The onset of the COVID-19 pandemic in early 2020 caused a widespread shift in public health priorities. Global efforts focused on COVID-19 monitoring and contact tracing. Existing public health programs were interrupted due to physical distancing measures and reallocation of resources. The onset of the COVID-19 pandemic intersected with advancements in technologies that have the potential to support public health surveillance efforts.

OBJECTIVE

This scoping review aims to explore emergent public health surveillance methods during the early COVID-19 pandemic to characterize the impact of the pandemic on surveillance methods.

METHODS

A scoping search was conducted in multiple databases and by scanning key government and public health organization websites from March 2020 to January 2022. Published papers and gray literature that described the application of new or revised approaches to public health surveillance were included. Papers that discussed the implications of novel public health surveillance approaches from ethical, legal, security, and equity perspectives were also included. The surveillance subject, method, location, and setting were extracted from each paper to identify trends in surveillance practices. Two public health epidemiologists were invited to provide their perspectives as peer reviewers.

RESULTS

Of the 14,238 unique papers, a total of 241 papers describing novel surveillance methods and changes to surveillance methods are included. Eighty papers were review papers and 161 were single studies. Overall, the literature heavily featured papers detailing surveillance of COVID-19 transmission (n=187). Surveillance of other infectious diseases was also described, including other pathogens (n=12). Other public health topics included vaccines (n=9), mental health (n=11), substance use (n=4), healthy nutrition (n=1), maternal and child health (n=3), antimicrobial resistance (n=2), and misinformation (n=6). The literature was dominated by applications of digital surveillance, for example, by using big data through mobility tracking and infodemiology (n=163). Wastewater surveillance was also heavily represented (n=48). Other papers described adaptations to programs or methods that existed prior to the COVID-19 pandemic (n=9). The scoping search also found 109 papers that discuss the ethical, legal, security, and equity implications of emerging surveillance methods. The peer reviewer public health epidemiologists noted that additional changes likely exist, beyond what has been reported and available for evidence syntheses.

CONCLUSIONS

The COVID-19 pandemic accelerated advancements in surveillance and the adoption of new technologies, especially for digital and wastewater surveillance methods. Given the investments in these systems, further applications for public health surveillance are likely. The literature for surveillance methods was dominated by surveillance of infectious diseases, particularly COVID-19. A substantial amount of literature on the ethical, legal, security, and equity implications of these emerging surveillance methods also points to a need for cautious consideration of potential harm.

Applying an interpretable machine learning framework to study mobility inequity in the recovery phase of COVID-19 pandemic

The COVID-19 pandemic is a public health crisis that also fuels the pervasive social inequity in the United States. Existing studies have extensively analyzed the inequity issues on mobility across different demographic groups during the lockdown phase. However, it is unclear whether the mobility inequity is perennial and will continue into the mobility recovery phase. This study utilizes ride-hailing data from Jan 1st, 2019, to Mar 31st, 2022, in Chicago to analyze the impact of various factors, such as demographic, land use, and transit connectivity, on mobility inequity in the different recovery phases. Instead of commonly used statistical methods, this study leverages advanced time-series clustering and an interpretable machine learning algorithm. The result demonstrates that inequity still exists in the mobility recovery phase of the COVID-19 pandemic, and the degree of mobility inequity in different recovery phases is varied. Furthermore, mobility inequity is more likely to exist in the census tract with more families without children, lower health insurance coverage, inflexible workstyle, more African Americans, higher poverty rate, fewer commercial land use, and higher Gini index. This study aims to further the understanding of the social inequity issue during the mobility recovery phase of the COVID-19 pandemic and help governments propose proper policies to tackle the unequal impact of the pandemic.

Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task

The black-box nature of machine learning models hinders the deployment of some high-accuracy medical diagnosis algorithms. It is risky to put one's life in the hands of models that medical researchers do not fully understand or trust. However, through model interpretation, black-box models can promptly reveal significant biomarkers that medical practitioners may have overlooked due to the surge of infected patients in the COVID-19 pandemic. This research leverages a database of 92 patients with confirmed SARS-CoV-2 laboratory tests between 18th January 2020 and 5th March 2020, in Zhuhai, China, to identify biomarkers indicative of infection severity prediction. Through the interpretation of four machine learning models, decision tree, random forests, gradient boosted trees, and neural networks using permutation feature importance, partial dependence plot, individual conditional expectation, accumulated local effects, local interpretable model-agnostic explanations, and Shapley additive explanation, we identify an increase in N-terminal pro-brain natriuretic peptide, C-reaction protein, and lactic dehydrogenase, a decrease in lymphocyte is associated with severe infection and an increased risk of death, which is consistent with recent medical research on COVID-19 and other research using dedicated models. We further validate our methods on a large open dataset with 5644 confirmed patients from the Hospital Israelita Albert Einstein, at São Paulo, Brazil from Kaggle, and unveil leukocytes, eosinophils, and platelets as three indicative biomarkers for COVID-19.

Forecasting COVID-19 spreading through an ensemble of classical and machine learning models: Spain's case study

In this work the applicability of an ensemble of population and machine learning models to predict the evolution of the COVID-19 pandemic in Spain is evaluated, relying solely on public datasets. Firstly, using only incidence data, we trained machine learning models and adjusted classical ODE-based population models, especially suited to capture long term trends. As a novel approach, we then made an ensemble of these two families of models in order to obtain a more robust and accurate prediction. We then proceed to improve machine learning models by adding more input features: vaccination, human mobility and weather conditions. However, these improvements did not translate to the overall ensemble, as the different model families had also different prediction patterns. Additionally, machine learning models degraded when new COVID variants appeared after training. We finally used Shapley Additive Explanation values to discern the relative importance of the different input features for the machine learning models' predictions. The conclusion of this work is that the ensemble of machine learning models and population models can be a promising alternative to SEIR-like compartmental models, especially given that the former do not need data from recovered patients, which are hard to collect and generally unavailable.

Human behavior in the time of COVID-19: Learning from big data

Since the World Health Organization (WHO) characterized COVID-19 as a pandemic in March 2020, there have been over 600 million confirmed cases of COVID-19 and more than six million deaths as of October 2022. The relationship between the COVID-19 pandemic and human behavior is complicated. On one hand, human behavior is found to shape the spread of the disease. On the other hand, the pandemic has impacted and even changed human behavior in almost every aspect. To provide a holistic understanding of the complex interplay between human behavior and the COVID-19 pandemic, researchers have been employing big data techniques such as natural language processing, computer vision, audio signal processing, frequent pattern mining, and machine learning. In this study, we present an overview of the existing studies on using big data techniques to study human behavior in the time of the COVID-19 pandemic. In particular, we categorize these studies into three groups-using big data to measure, model, and leverage human behavior, respectively. The related tasks, data, and methods are summarized accordingly. To provide more insights into how to fight the COVID-19 pandemic and future global catastrophes, we further discuss challenges and potential opportunities.

Incorporating variant frequencies data into short-term forecasting for COVID-19 cases and deaths in the USA: a deep learning approach

BACKGROUND

Since the US reported its first COVID-19 case on January 21, 2020, the science community has been applying various techniques to forecast incident cases and deaths. To date, providing an accurate and robust forecast at a high spatial resolution has proved challenging, even in the short term.

METHOD

Here we present a novel multi-stage deep learning model to forecast the number of COVID-19 cases and deaths for each US state at a weekly level for a forecast horizon of 1-4 weeks. The model is heavily data driven, and relies on epidemiological, mobility, survey, climate, demographic, and SARS-CoV-2 variant frequencies data. We implement a rigorous and robust evaluation of our model-specifically we report on weekly performance over a one-year period based on multiple error metrics, and explicitly assess how our model performance varies over space, chronological time, and different outbreak phases.

FINDINGS

The proposed model is shown to consistently outperform the CDC ensemble model for all evaluation metrics in multiple spatiotemporal settings, especially for the longer-term (3 and 4 weeks ahead) forecast horizon. Our case study also highlights the potential value of variant frequencies data for use in short-term forecasting to identify forthcoming surges driven by new variants.

INTERPRETATION

Based on our findings, the proposed forecasting framework improves upon the available state-of-the-art forecasting tools currently used to support public health decision making with respect to COVID-19 risk.

FUNDING

This work was funded the NSF Rapid Response Research (RAPID) grant Award ID 2108526 and the CDC Contract #75D30120C09570.

Computational decision-support tools for urban design to improve resilience against COVID-19 and other infectious diseases: A systematic review

The COVID-19 pandemic highlighted the need for decision-support tools to help cities become more resilient to infectious diseases. Through urban design and planning, non-pharmaceutical interventions can be enabled, impelling behaviour change and facilitating the construction of lower risk buildings and public spaces. Computational tools, including computer simulation, statistical models, and artificial intelligence, have been used to support responses to the current pandemic as well as to the spread of previous infectious diseases. Our multidisciplinary research group systematically reviewed state-of-the-art literature to propose a toolkit that employs computational modelling for various interventions and urban design processes. We selected 109 out of 8,737 studies retrieved from databases and analysed them based on the pathogen type, transmission mode and phase, design intervention and process, as well as modelling methodology (method, goal, motivation, focus, and indication to urban design). We also explored the relationship between infectious disease and urban design, as well as computational modelling support, including specific models and parameters. The proposed toolkit will help designers, planners, and computer modellers to select relevant approaches for evaluating design decisions depending on the target disease, geographic context, design stages, and spatial and temporal scales. The findings herein can be regarded as stand-alone tools, particularly for fighting against COVID-19, or be incorporated into broader frameworks to help cities become more resilient to future disasters.

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics

We seek to transform how new and emergent variants of pandemic-causing viruses, specifically SARS-CoV-2, are identified and classified. By adapting large language models (LLMs) for genomic data, we build genome-scale language models (GenSLMs) which can learn the evolutionary landscape of SARS-CoV-2 genomes. By pre-training on over 110 million prokaryotic gene sequences and fine-tuning a SARS-CoV-2-specific model on 1.5 million genomes, we show that GenSLMs can accurately and rapidly identify variants of concern. Thus, to our knowledge, GenSLMs represents one of the first whole genome scale foundation models which can generalize to other prediction tasks. We demonstrate scaling of GenSLMs on GPU-based supercomputers and AI-hardware accelerators utilizing 1.63 Zettaflops in training runs with a sustained performance of 121 PFLOPS in mixed precision and peak of 850 PFLOPS. We present initial scientific insights from examining GenSLMs in tracking evolutionary dynamics of SARS-CoV-2, paving the path to realizing this on large biological data.

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

Since the start of the COVID-19 pandemic, social distancing (SD) has played an essential role in controlling and slowing down the spread of the virus in smart cities. To ensure the respect of SD in public areas, visual SD monitoring (VSDM) provides promising opportunities by (i) controlling and analyzing the physical distance between pedestrians in real-time, (ii) detecting SD violations among the crowds, and (iii) tracking and reporting individuals violating SD norms. To the authors' best knowledge, this paper proposes the first comprehensive survey of VSDM frameworks and identifies their challenges and future perspectives. Typically, we review existing contributions by presenting the background of VSDM, describing evaluation metrics, and discussing SD datasets. Then, VSDM techniques are carefully reviewed after dividing them into two main categories: hand-crafted feature-based and deep-learning-based methods. A significant focus is paid to convolutional neural networks (CNN)-based methodologies as most of the frameworks have used either one-stage, two-stage, or multi-stage CNN models. A comparative study is also conducted to identify their pros and cons. Thereafter, a critical analysis is performed to highlight the issues and impediments that hold back the expansion of VSDM systems. Finally, future directions attracting significant research and development are derived.

Data-driven contact network models of COVID-19 reveal trade-offs between costs and infections for optimal local containment policies

While several non-pharmacological measures have been implemented for a few months in an effort to slow the coronavirus disease (COVID-19) pandemic in the United States, the disease remains a danger in a number of counties as restrictions are lifted to revive the economy. Making a trade-off between economic recovery and infection control is a major challenge confronting many hard-hit counties. Understanding the transmission process and quantifying the costs of local policies are essential to the task of tackling this challenge. Here, we investigate the dynamic contact patterns of the populations from anonymized, geo-localized mobility data and census and demographic data to create data-driven, agent-based contact networks. We then simulate the epidemic spread with a time-varying contagion model in ten large metropolitan counties in the United States and evaluate a combination of mobility reduction, mask use, and reopening policies. We find that our model captures the spatial-temporal and heterogeneous case trajectory within various counties based on dynamic population behaviors. Our results show that a decision-making tool that considers both economic cost and infection outcomes of policies can be informative in making decisions of local containment strategies for optimal balancing of economic slowdown and virus spread.

Body Language Analysis in Healthcare: An Overview

Given the current COVID-19 pandemic, medical research today focuses on epidemic diseases. Innovative technology is incorporated in most medical applications, emphasizing the automatic recognition of physical and emotional states. Most research is concerned with the automatic identification of symptoms displayed by patients through analyzing their body language. The development of technologies for recognizing and interpreting arm and leg gestures, facial features, and body postures is still in its early stage. More extensive research is needed using artificial intelligence (AI) techniques in disease detection. This paper presents a comprehensive survey of the research performed on body language processing. Upon defining and explaining the different types of body language, we justify the use of automatic recognition and its application in healthcare. We briefly describe the automatic recognition framework using AI to recognize various body language elements and discuss automatic gesture recognition approaches that help better identify the external symptoms of epidemic and pandemic diseases. From this study, we found that since there are studies that have proven that the body has a language called body language, it has proven that language can be analyzed and understood by machine learning (ML). Since diseases also show clear and different symptoms in the body, the body language here will be affected and have special features related to a particular disease. From this examination, we discovered that it is possible to specialize the features and language changes of each disease in the body. Hence, ML can understand and detect diseases such as pandemic and epidemic diseases and others.

A survey on the interpretability of deep learning in medical diagnosis

Deep learning has demonstrated remarkable performance in the medical domain, with accuracy that rivals or even exceeds that of human experts. However, it has a significant problem that these models are "black-box" structures, which means they are opaque, non-intuitive, and difficult for people to understand. This creates a barrier to the application of deep learning models in clinical practice due to lack of interpretability, trust, and transparency. To overcome this problem, several studies on interpretability have been proposed. Therefore, in this paper, we comprehensively review the interpretability of deep learning in medical diagnosis based on the current literature, including some common interpretability methods used in the medical domain, various applications with interpretability for disease diagnosis, prevalent evaluation metrics, and several disease datasets. In addition, the challenges of interpretability and future research directions are also discussed here. To the best of our knowledge, this is the first time that various applications of interpretability methods for disease diagnosis have been summarized.

Artificial intelligence for forecasting and diagnosing COVID-19 pandemic: A focused review

The outbreak of novel corona virus 2019 (COVID-19) has been treated as a public health crisis of global concern by the World Health Organization (WHO). COVID-19 pandemic hugely affected countries worldwide raising the need to exploit novel, alternative and emerging technologies to respond to the emergency created by the weak health-care systems. In this context, Artificial Intelligence (AI) techniques can give a valid support to public health authorities, complementing traditional approaches with advanced tools. This study provides a comprehensive review of methods, algorithms, applications, and emerging AI technologies that can be utilized for forecasting and diagnosing COVID-19. The main objectives of this review are summarized as follows. (i) Understanding the importance of AI approaches such as machine learning and deep learning for COVID-19 pandemic; (ii) discussing the efficiency and impact of these methods for COVID-19 forecasting and diagnosing; (iii) providing an extensive background description of AI techniques to help non-expert to better catch the underlying concepts; (iv) for each work surveyed, give a detailed analysis of the rationale behind the approach, highlighting the method used, the type and size of data analyzed, the validation method, the target application and the results achieved; (v) focusing on some future challenges in COVID-19 forecasting and diagnosing.

A comparison of Covid-19 cases and deaths in Turkey and in other countries

In this study, the characteristics of the Covid-19 pandemic in Turkey are examined in terms of the number of cases and deaths, and a characteristic prediction is made with an approach that employs artificial intelligence. The number of cases and deaths are estimated using the number of tests, the numbers of seriously ill and recovered patients as parameters. The machine learning methods used are linear regression, polynomial regression, support vector regression with different kernel functions, decision tree and artificial neural networks. The obtained results are compared by calculating the coefficient of determination (R ²), and the mean absolute percentage error (MAPE) values. When R ² and MAPE values are compared, it is seen that the optimal results for cases in Turkey are obtained with the decision tree, for deaths with polynomial regression method. The results reached for the United States of America and Russia are similar and the optimal results are obtained by polynomial regression. However, while the optimal results are obtained by neural networks in the Indian data, linear regression for the cases in the Brazilian data, neural network for the deaths, decision tree for the cases in France, polynomial regression for the deaths, neural network for the cases in the UK data and decision tree for the deaths are the methods that produced the optimal results. These results also give an idea about the similarities and differences of country characteristics.

Leveraging weather data for forecasting cases-to-mortality rates due to COVID-19

There are several recent publications criticizing the failure of COVID-19 forecasting models, with swinging over predictions and underpredictions, which have made it difficult for decision and policy making. Observing the failures of several COVID-19 forecasting models and the alarming spread of the virus, we seek to use some stable response for forecasting COVID-19, viz., ratios of COVID-19 cases to mortalities, rather than COVID-19 cases or fatalities. A trend of low COVID-19 cases-to-mortality ratios calls for urgent attention: the need for vaccines, for instance. Studies have shown that there are influences of weather parameters on COVID-19; and COVID-19 may have come to stay and could manifest a seasonal outbreak profile similar to other infectious respiratory diseases. In this paper, the influences of some weather, geographical, economic and demographic covariates were evaluated on COVID-19 response based on a series of Granger-causality tests. The effect of four weather parameters, viz., temperature, rainfall, solar irradiation and relative humidity, on daily COVID-19 cases-to-mortality ratios of 36 countries from 5 continents of the world were determined through regression analysis. Regression studies show that these four weather factors impact ratios of COVID-19 cases-to-mortality differently. The most impactful factor is temperature which is positively correlated with COVID-19 cases-to-mortality responses in 24 out of 36 countries. Temperature minimally affects COVID-19 cases-to-mortality ratios in the tropical countries. The most influential weather factor - temperature - was incorporated in training random forest and deep learning models for forecasting the cases-to-mortality rate of COVID-19 in clusters of countries in the world with similar weather conditions. Evaluation of trained forecasting models incorporating temperature features show better performance compared to a similar set of models trained without temperature features. This implies that COVID-19 forecasting models will predict more accurately if temperature features are factored in, especially for temperate countries.

Recurrent Neural Network and Reinforcement Learning Model for COVID-19 Prediction

Detection and prediction of the novel Coronavirus present new challenges for the medical research community due to its widespread across the globe. Methods driven by Artificial Intelligence can help predict specific parameters, hazards, and outcomes of such a pandemic. Recently, deep learning-based approaches have proven a novel opportunity to determine various difficulties in prediction. In this work, two learning algorithms, namely deep learning and reinforcement learning, were developed to forecast COVID-19. This article constructs a model using Recurrent Neural Networks (RNN), particularly the Modified Long Short-Term Memory (MLSTM) model, to forecast the count of newly affected individuals, losses, and cures in the following few days. This study also suggests deep learning reinforcement to optimize COVID-19's predictive outcome based on symptoms. Real-world data was utilized to analyze the success of the suggested system. The findings show that the established approach promises prognosticating outcomes concerning the current COVID-19 pandemic and outperformed the Long Short-Term Memory (LSTM) model and the Machine Learning model, Logistic Regresion (LR) in terms of error rate.

Unraveling the dynamic importance of county-level features in trajectory of COVID-19

The objective of this study was to investigate the importance of multiple county-level features in the trajectory of COVID-19. We examined feature importance across 2787 counties in the United States using data-driven machine learning models. Existing mathematical models of disease spread usually focused on the case prediction with different infection rates without incorporating multiple heterogeneous features that could impact the spatial and temporal trajectory of COVID-19. Recognizing this, we trained a data-driven model using 23 features representing six key influencing factors affecting the pandemic spread: social demographics of counties, population activities, mobility within the counties, movement across counties, disease attributes, and social network structure. Also, we categorized counties into multiple groups according to their population densities, and we divided the trajectory of COVID-19 into three stages: the outbreak stage, the social distancing stage, and the reopening stage. The study aimed to answer two research questions: (1) The extent to which the importance of heterogeneous features evolved at different stages; (2) The extent to which the importance of heterogeneous features varied across counties with different characteristics. We fitted a set of random forest models to determine weekly feature importance. The results showed that: (1) Social demographic features, such as gross domestic product, population density, and minority status maintained high-importance features throughout stages of COVID-19 across 2787 studied counties; (2) Within-county mobility features had the highest importance in counties with higher population densities; (3) The feature reflecting the social network structure (Facebook, social connectedness index), had higher importance for counties with higher population densities. The results showed that the data-driven machine learning models could provide important insights to inform policymakers regarding feature importance for counties with various population densities and at different stages of a pandemic life cycle.

The Role of Artificial Intelligence in Fighting the COVID-19 Pandemic

The first few months of 2020 have profoundly changed the way we live our lives and carry out our daily activities. Although the widespread use of futuristic robotaxis and self-driving commercial vehicles has not yet become a reality, the COVID-19 pandemic has dramatically accelerated the adoption of Artificial Intelligence (AI) in different fields. We have witnessed the equivalent of two years of digital transformation compressed into just a few months. Whether it is in tracing epidemiological peaks or in transacting contactless payments, the impact of these developments has been almost immediate, and a window has opened up on what is to come. Here we analyze and discuss how AI can support us in facing the ongoing pandemic. Despite the numerous and undeniable contributions of AI, clinical trials and human skills are still required. Even if different strategies have been developed in different states worldwide, the fight against the pandemic seems to have found everywhere a valuable ally in AI, a global and open-source tool capable of providing assistance in this health emergency. A careful AI application would enable us to operate within this complex scenario involving healthcare, society and research.

Effects of population co-location reduction on cross-county transmission risk of COVID-19 in the United States

The objective of this study is to examine the transmission risk of COVID-19 based on cross-county population co-location data from Facebook. The rapid spread of COVID-19 in the United States has imposed a major threat to public health, the real economy, and human well-being. With the absence of effective vaccines, the preventive actions of social distancing, travel reduction and stay-at-home orders are recognized as essential non-pharmacologic approaches to control the infection and spatial spread of COVID-19. Prior studies demonstrated that human movement and mobility drove the spatiotemporal distribution of COVID-19 in China. Little is known, however, about the patterns and effects of co-location reduction on cross-county transmission risk of COVID-19. This study utilizes Facebook co-location data for all counties in the United States from March to early May 2020 for conducting spatial network analysis where nodes represent counties and edge weights are associated with the co-location probability of populations of the counties. The analysis examines the synchronicity and time lag between travel reduction and pandemic growth trajectory to evaluate the efficacy of social distancing in ceasing the population co-location probabilities, and subsequently the growth in weekly new cases across counties. The results show that the mitigation effects of co-location reduction appear in the growth of weekly new confirmed cases with one week of delay. The analysis categorizes counties based on the number of confirmed COVID-19 cases and examines co-location patterns within and across groups. Significant segregation is found among different county groups. The results suggest that within-group co-location probabilities (e.g., co-location probabilities among counties with high numbers of cases) remain stable, and social distancing policies primarily resulted in reduced cross-group co-location probabilities (due to travel reduction from counties with large number of cases to counties with low numbers of cases). These findings could have important practical implications for local governments to inform their intervention measures for monitoring and reducing the spread of COVID-19, as well as for adoption in future pandemics. Public policy, economic forecasting, and epidemic modeling need to account for population co-location patterns in evaluating transmission risk of COVID-19 across counties.

Benchmarking Attention-Based Interpretability of Deep Learning in Multivariate Time Series Predictions

The adaptation of deep learning models within safety-critical systems cannot rely only on good prediction performance but needs to provide interpretable and robust explanations for their decisions. When modeling complex sequences, attention mechanisms are regarded as the established approach to support deep neural networks with intrinsic interpretability. This paper focuses on the emerging trend of specifically designing diagnostic datasets for understanding the inner workings of attention mechanism based deep learning models for multivariate forecasting tasks. We design a novel benchmark of synthetically designed datasets with the transparent underlying generating process of multiple time series interactions with increasing complexity. The benchmark enables empirical evaluation of the performance of attention based deep neural networks in three different aspects: (i) prediction performance score, (ii) interpretability correctness, (iii) sensitivity analysis. Our analysis shows that although most models have satisfying and stable prediction performance results, they often fail to give correct interpretability. The only model with both a satisfying performance score and correct interpretability is IMV-LSTM, capturing both autocorrelations and crosscorrelations between multiple time series. Interestingly, while evaluating IMV-LSTM on simulated data from statistical and mechanistic models, the correctness of interpretability increases with more complex datasets.

On the Application of Advanced Machine Learning Methods to Analyze Enhanced, Multimodal Data from Persons Infected with COVID-19

The current COVID-19 pandemic, caused by the rapid worldwide spread of the SARS-CoV-2 virus, is having severe consequences for human health and the world economy. The virus affects different individuals differently, with many infected patients showing only mild symptoms, and others showing critical illness. To lessen the impact of the epidemic, one problem is to determine which factors play an important role in a patient’s progression of the disease. Here, we construct an enhanced COVID-19 structured dataset from more than one source, using natural language processing to add local weather conditions and country-specific research sentiment. The enhanced structured dataset contains 301,363 samples and 43 features, and we applied both machine learning algorithms and deep learning algorithms on it so as to forecast patient’s survival probability. In addition, we import alignment sequence data to improve the performance of the model. Application of Extreme Gradient Boosting (XGBoost) on the enhanced structured dataset achieves 97% accuracy in predicting patient’s survival; with climatic factors, and then age, showing the most importance. Similarly, the application of a Multi-Layer Perceptron (MLP) achieves 98% accuracy. This work suggests that enhancing the available data, mostly basic information on patients, so as to include additional, potentially important features, such as weather conditions, is useful. The explored models suggest that textual weather descriptions can improve outcome forecast.