Towards Providing Effective Data-Driven Responses to Predict the Covid-19 in São Paulo and Brazil

A data-driven epidemic model with human mobility and vaccination protection for COVID-19 prediction

Epidemiological models allow for quantifying the dynamic characteristics of large-scale outbreaks. However, capturing detailed and accurate epidemiological information often requires consideration of multiple kinetic mechanisms and parameters. Due to the uncertainty of pandemic evolution, such as pathogen variation, host immune response and changes in mitigation strategies, the parameter evaluation and state prediction of complex epidemiological models are challenging. Here, we develop a data-driven epidemic model with a generalized SEIR mechanistic structure that includes new compartments, human mobility and vaccination protection. To address the issue of model complexity, we embed the epidemiological model dynamics into physics-informed neural networks (PINN), taking the observed series of time instances as direct input of the network to simultaneously infer unknown parameters and unobserved dynamics of the underlying model. Using actual data during the COVID-19 outbreak in Australia, Israel, and Switzerland, our model framework demonstrates satisfactory performance in multi-step ahead predictions compared to several benchmark models. Moreover, our model infers time-varying parameters such as transmission rates, hospitalization ratios, and effective reproduction numbers, as well as calculates the latent period and asymptomatic infection count, which are typically unreported in public data. Finally, we employ the proposed data-driven model to analyze the impact of different mitigation strategies on COVID-19.

Local protection bubbles: an interpretation of the slowdown in the spread of coronavirus in the city of São Paulo, Brazil, in July 2020

After four months of fighting the pandemic, the city of São Paulo, Brazil, entered a phase of relaxed social distancing measures in July 2020. Simultaneously, there was a decline in the social distancing rate and a reduction in the number of cases, fatalities, and hospital bed occupancy. To understand the pandemic dynamics in the city of São Paulo, we developed a multi-agent simulation model. Surprisingly, the counter-intuitive results of the model followed the city's reality. We argue that this phenomenon could be attributed to local bubbles of protection that emerged in the absence of contagion networks. These bubbles reduced the transmission rate of the virus, causing short and temporary reductions in the epidemic curve - but manifested as an unstable equilibrium. Our hypothesis aligns with the virus spread dynamics observed thus far, without the need for ad hoc assumptions regarding the natural thresholds of collective immunity or the heterogeneity of the population's transmission rate, which may lead to erroneous predictions. Our model was designed to be user-friendly and does not require any scientific or programming expertise to generate outcomes on virus transmission in a given location. Furthermore, as an input to start our simulation model, we developed the COVID-19 Protection Index as an alternative to the Human Development Index, which measures a given territory vulnerability to the coronavirus and includes characteristics of the health system and socioeconomic development, as well as the infrastructure of the city of São Paulo.

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.

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.

Using machine learning models to predict the duration of the recovery of COVID-19 patients hospitalized in Fangcang shelter hospital during the Omicron BA. 2.2 pandemic

Background

Factors that may influence the recovery of patients with confirmed SARS-CoV-2 infection hospitalized in the Fangcang shelter were explored, and machine learning models were constructed to predict the duration of recovery during the Omicron BA. 2.2 pandemic.

Methods

A retrospective study was conducted at Hongqiao National Exhibition and Convention Center Fangcang shelter (Shanghai, China) from April 9, 2022 to April 25, 2022. The demographics, clinical data, inoculation history, and recovery information of the 13,162 enrolled participants were collected. A multivariable logistic regression model was used to identify independent factors associated with 7-day recovery and 14-day recovery. Machine learning algorithms (DT, SVM, RF, DT/AdaBoost, AdaBoost, SMOTEENN/DT, SMOTEENN/SVM, SMOTEENN/RF, SMOTEENN+DT/AdaBoost, and SMOTEENN/AdaBoost) were used to build models for predicting 7-day and 14-day recovery.

Results

Of the 13,162 patients in the study, the median duration of recovery was 8 days (interquartile range IQR, 6–10 d), 41.31% recovered within 7 days, and 94.83% recovered within 14 days. Univariate analysis showed that the administrative region, age, cough medicine, comorbidities, diabetes, coronary artery disease (CAD), hypertension, number of comorbidities, CT value of the ORF gene, CT value of the N gene, ratio of ORF/IC, and ratio of N/IC were associated with a duration of recovery within 7 days. Age, gender, vaccination dose, cough medicine, comorbidities, diabetes, CAD, hypertension, number of comorbidities, CT value of the ORF gene, CT value of the N gene, ratio of ORF/IC, and ratio of N/IC were related to a duration of recovery within 14 days. In the multivariable analysis, the receipt of two doses of the vaccination vs. unvaccinated (OR = 1.118, 95% CI = 1.003–1.248; p = 0.045), receipt of three doses of the vaccination vs. unvaccinated (OR = 1.114, 95% CI = 1.004–1.236; p = 0.043), diabetes (OR = 0.383, 95% CI = 0.194–0.749; p = 0.005), CAD (OR = 0.107, 95% CI = 0.016–0.421; p = 0.005), hypertension (OR = 0.371, 95% CI = 0.202–0.674; p = 0.001), and ratio of N/IC (OR = 3.686, 95% CI = 2.939–4.629; p < 0.001) were significantly and independently associated with a duration of recovery within 7 days. Gender (OR = 0.736, 95% CI = 0.63–0.861; p < 0.001), age (30–70) (OR = 0.738, 95% CI = 0.594–0.911; p < 0.001), age (>70) (OR = 0.38, 95% CI = 0292–0.494; p < 0.001), receipt of three doses of the vaccination vs. unvaccinated (OR = 1.391, 95% CI = 1.12–1.719; p = 0.0033), cough medicine (OR = 1.509, 95% CI = 1.075–2.19; p = 0.023), and symptoms (OR = 1.619, 95% CI = 1.306–2.028; p < 0.001) were significantly and independently associated with a duration of recovery within 14 days. The SMOTEEN/RF algorithm performed best, with an accuracy of 90.32%, sensitivity of 92.22%, specificity of 88.31%, F1 score of 90.71%, and AUC of 89.75% for the 7-day recovery prediction; and an accuracy of 93.81%, sensitivity of 93.40%, specificity of 93.81%, F1 score of 93.42%, and AUC of 93.53% for the 14-day recovery prediction.

Conclusion

Age and vaccination dose were factors robustly associated with accelerated recovery both on day 7 and day 14 from the onset of disease during the Omicron BA. 2.2 wave. The results suggest that the SMOTEEN/RF-based model could be used to predict the probability of 7-day and 14-day recovery from the Omicron variant of SARS-CoV-2 infection for COVID-19 prevention and control policy in other regions or countries. This may also help to generate external validation for the model.

Risk Factors Associated with Mortality in Hospitalized Patients with COVID-19 during the Omicron Wave in Brazil

Considering the imminence of new SARS-CoV-2 variants and COVID-19 vaccine availability, it is essential to understand the impact of the disease on the most vulnerable groups and those at risk of death from the disease. To this end, the odds ratio (OR) for mortality and hospitalization was calculated for different groups of patients by applying an adjusted logistic regression model based on the following variables of interest: gender, booster vaccination, age group, and comorbidity occurrence. A massive number of data were extracted and compiled from official Brazilian government resources, which include all reported cases of hospitalizations and deaths associated with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in Brazil during the “wave” of the Omicron variant (BA.1 substrain). Males (1.242; 95% CI 1.196–1.290) aged 60–79 (3.348; 95% CI 3.050–3.674) and 80 years or older (5.453; 95% CI 4.966–5.989), and hospitalized patients with comorbidities (1.418; 95% CI 1.355–1.483), were more likely to die. There was a reduction in the risk of death (0.907; 95% CI 0.866–0.951) among patients who had received the third dose of the anti-SARS-CoV-2 vaccine (booster). Additionally, this big data investigation has found statistical evidence that vaccination can support mitigation plans concerning the current scenario of COVID-19 in Brazil since the Omicron variant and its substrains are now prevalent across the entire country.

Dual attention-based sequential auto-encoder for Covid-19 outbreak forecasting: A case study in Vietnam

For preventing the outbreaks of Covid-19 infection in different countries, many organizations and governments have extensively studied and applied different kinds of quarantine isolation policies, medical treatments as well as organized massive/fast vaccination strategy for over-18 citizens. There are several valuable lessons have been achieved in different countries this Covid-19 battle. These studies have presented the usefulness of prompt actions in testing, isolating confirmed infectious cases from community as well as social resource planning/optimization through data-driven anticipation. In recent times, many studies have demonstrated the effectiveness of short/long-term forecasting in number of new Covid-19 cases in forms of time-series data. These predictions have directly supported to effectively optimize the available healthcare resources as well as imposing suitable policies for slowing down the Covid-19 spreads, especially in high-populated cities/regions/nations. There are several progresses of deep neural architectures, such as recurrent neural network (RNN) have demonstrated significant improvements in analyzing and learning the time-series datasets for conducting better predictions. However, most of recent RNN-based techniques are considered as unable to handle chaotic/non-smooth sequential datasets. The consecutive disturbances and lagged observations from chaotic time-series dataset like as routine Covid-19 confirmed cases have led to the low performance in temporal feature learning process through recent RNN-based models. To meet this challenge, in this paper, we proposed a novel dual attention-based sequential auto-encoding architecture, called as: DAttAE. Our proposed model supports to effectively learn and predict the new Covid-19 cases in forms of chaotic and non-smooth time series dataset. Specifically, the integration between dual self-attention mechanism in a given Bi-LSTM based auto-encoder in our proposed model supports to directly focus the model on a specific time-range sequence in order to achieve better prediction. We evaluated the performance of our proposed DAttAE model by comparing with multiple traditional and state-of-the-art deep learning-based techniques for time-series prediction task upon different real-world datasets. Experimental outputs demonstrated the effectiveness of our proposed attention-based deep neural approach in comparing with state-of-the-art RNN-based architectures for time series based Covid-19 outbreak prediction task.

A Novel Approach on Deep Learning—Based Decision Support System Applying Multiple Output LSTM-Autoencoder: Focusing on Identifying Variations by PHSMs’ Effect over COVID-19 Pandemic

Following the outbreak of the COVID-19 pandemic, the continued emergence of major variant viruses has caused enormous damage worldwide by generating social and economic ripple effects, and the importance of PHSMs (Public Health and Social Measures) is being highlighted to cope with this severe situation. Accordingly, there has also been an increase in research related to a decision support system based on simulation approaches used as a basis for PHSMs. However, previous studies showed limitations impeding utilization as a decision support system for policy establishment and implementation, such as the failure to reflect changes in the effectiveness of PHSMs and the restriction to short-term forecasts. Therefore, this study proposes an LSTM-Autoencoder-based decision support system for establishing and implementing PHSMs. To overcome the limitations of existing studies, the proposed decision support system used a methodology for predicting the number of daily confirmed cases over multiple periods based on multiple output strategies and a methodology for rapidly identifying varies in policy effects based on anomaly detection. It was confirmed that the proposed decision support system demonstrated excellent performance compared to models used for time series analysis such as statistical models and deep learning models. In addition, we endeavored to increase the usability of the proposed decision support system by suggesting a transfer learning-based methodology that can efficiently reflect variations in policy effects. Finally, the decision support system proposed in this study provides a methodology that provides multi-period forecasts, identifying variations in policy effects, and efficiently reflects the effects of variation policies. It was intended to provide reasonable and realistic information for the establishment and implementation of PHSMs and, through this, to yield information expected to be highly useful, which had not been provided in the decision support systems presented in previous studies.

Temporal deep learning architecture for prediction of COVID-19 cases in India

To combat the recent coronavirus disease 2019 (COVID-19), academician and clinician are in search of new approaches to predict the COVID-19 outbreak dynamic trends that may slow down or stop the pandemic. Epidemiological models like Susceptible-Infected-Recovered (SIR) and its variants are helpful to understand the dynamics trend of pandemic that may be used in decision making to optimize possible controls from the infectious disease. But these epidemiological models based on mathematical assumptions may not predict the real pandemic situation. Recently the new machine learning approaches are being used to understand the dynamic trend of COVID-19 spread. In this paper, we designed the recurrent and convolutional neural network models: vanilla LSTM, stacked LSTM, ED_LSTM, BiLSTM, CNN, and hybrid CNN+LSTM model to capture the complex trend of COVID-19 outbreak and perform the forecasting of COVID-19 daily confirmed cases of 7, 14, 21 days for India and its four most affected states (Maharashtra, Kerala, Karnataka, and Tamil Nadu). The root mean square error (RMSE) and mean absolute percentage error (MAPE) evaluation metric are computed on the testing data to demonstrate the relative performance of these models. The results show that the stacked LSTM and hybrid CNN+LSTM models perform best relative to other models.

Interpretable Temporal Attention Network for COVID-19 forecasting

The worldwide outbreak of coronavirus disease 2019 (COVID-19) has triggered an unprecedented global health and economic crisis. Early and accurate forecasts of COVID-19 and evaluation of government interventions are crucial for governments to take appropriate interventions to contain the spread of COVID-19. In this work, we propose the Interpretable Temporal Attention Network (ITANet) for COVID-19 forecasting and inferring the importance of government interventions. The proposed model is with an encoder–decoder architecture and employs long short-term memory (LSTM) for temporal feature extraction and multi-head attention for long-term dependency caption. The model simultaneously takes historical information, a priori known future information, and pseudo future information into consideration, where the pseudo future information is learned with the covariate forecasting network (CFN) and multi-task learning (MTL). In addition, we also propose the degraded teacher forcing (DTF) method to train the model efficiently. Compared with other models, the ITANet is more effective in the forecasting of COVID-19 new confirmed cases. The importance of government interventions against COVID-19 is further inferred by the Temporal Covariate Interpreter (TCI) of the model.

Tracking machine learning models for pandemic scenarios: a systematic review of machine learning models that predict local and global evolution of pandemics

This systematic review aims to study and classify machine learning models that predict pandemics' evolution within affected regions or countries. The advantage of this systematic review is that it allows the health authorities to decide what prediction model fits best depending upon the region's criticality and optimize hospitals' approaches to preparing and anticipating patient care. We searched ACM Digital Library, Biomed Central, BioRxiv+MedRxiv, BMJ, Computers and Applied Sciences, IEEEXplore, JMIR Medical Informatics, Medline Daily Updates, Nature, Oxford Academic, PubMed, Sage Online, ScienceDirect, Scopus, SpringerLink, Web of Science, and Wiley Online Library between 1 January 2020 and 31 July 2022. We divided the interventions into similarities between cumulative COVID-19 real cases and machine learning prediction models' ability to track pandemics trending. We included 45 studies that rated low to high risk of bias. The standardized mean differences (SMD) for the two groups were 0.18, 95% CI, with interval of [0.01, 0.35], I 2 =0, and p value=0.04. We built a taxonomic analysis of the included studies and determined two domains: pandemics trending prediction models and geolocation tracking models. We performed the meta-analysis and data synthesis and got low publication bias because of missing results. The level of certainty varied from very low to high. By submitting the 45 studies on the risk of bias, the levels of certainty, the summary of findings, and the statistical analysis via the forest and funnel plots assessments, we could determine the satisfactory statistical significance homogeneity across the included studies to simulate the progress of the pandemics and help the healthcare authorities to take preventive decisions.

Data-Driven Analytics Leveraging Artificial Intelligence in the Era of COVID-19: An Insightful Review of Recent Developments

This paper presents the role of artificial intelligence (AI) and other latest technologies that were employed to fight the recent pandemic (i.e., novel coronavirus disease-2019 (COVID-19)). These technologies assisted the early detection/diagnosis, trends analysis, intervention planning, healthcare burden forecasting, comorbidity analysis, and mitigation and control, to name a few. The key-enablers of these technologies was data that was obtained from heterogeneous sources (i.e., social networks (SN), internet of (medical) things (IoT/IoMT), cellular networks, transport usage, epidemiological investigations, and other digital/sensing platforms). To this end, we provide an insightful overview of the role of data-driven analytics leveraging AI in the era of COVID-19. Specifically, we discuss major services that AI can provide in the context of COVID-19 pandemic based on six grounds, (i) AI role in seven different epidemic containment strategies (a.k.a non-pharmaceutical interventions (NPIs)), (ii) AI role in data life cycle phases employed to control pandemic via digital solutions, (iii) AI role in performing analytics on heterogeneous types of data stemming from the COVID-19 pandemic, (iv) AI role in the healthcare sector in the context of COVID-19 pandemic, (v) general-purpose applications of AI in COVID-19 era, and (vi) AI role in drug design and repurposing (e.g., iteratively aligning protein spikes and applying three/four-fold symmetry to yield a low-resolution candidate template) against COVID-19. Further, we discuss the challenges involved in applying AI to the available data and privacy issues that can arise from personal data transitioning into cyberspace. We also provide a concise overview of other latest technologies that were increasingly applied to limit the spread of the ongoing pandemic. Finally, we discuss the avenues of future research in the respective area. This insightful review aims to highlight existing AI-based technological developments and future research dynamics in this area.

Forecasting the Long-Term Trends of Coronavirus Disease 2019 (COVID-19) Epidemic Using the Susceptible-Infectious-Recovered (SIR) Model

A simple model for predicting Coronavirus Disease 2019 (COVID-19) epidemic is presented in this study. The prediction model is presented based on the classic Susceptible-Infectious-Recovered (SIR) model, which has been widely used to describe the epidemic time evolution of infectious diseases. The original version of the Kermack and McKendrick model is used in this study. This included the daily rates of infection spread by infected individuals when these individuals interact with a susceptible population, which is denoted by the parameter β, while the recovery rates to determine the number of recovered individuals is expressed by the parameter γ. The parameters estimation of the three-compartment SIR model is determined through using a mathematical sequential reduction process from the logistic growth model equation. As the parameters are the basic characteristics of epidemic time evolution, the model is always tested and applied to the latest actual data of confirmed COVID-19 cases. It seems that this simple model is still reliable enough to describe the dynamics of the COVID-19 epidemic, not only qualitatively but also quantitatively with a high degree of correlation between actual data and prediction results. Therefore, it is possible to apply this model to predict cases of COVID-19 in several countries. In addition, the parameter characteristics of the classic SIR model can provide information on how these parameters reflect the efforts by each country to prevent the spread of the COVID-19 outbreak. This is clearly seen from the changes of the parameters shown by the classic SIR model.

High SARS-CoV-2 infection rate after resuming professional football in São Paulo, Brazil

OBJECTIVE

To examine the SARS-CoV-2 infection rate in a cohort of 6500 professional athletes and staff during the 2020 football (soccer) season in São Paulo, Brazil.

METHODS

This retrospective cohort study included 4269 players (87% male, age: 21.7±4.2 years) and 2231 staff (87% male, age: 42.6±11.9 years) from 122 teams (women: n=16) involved in eight leagues (women: n=2), which took place in São Paulo, Brazil. Between 4 July 2020 and 21 December 2020, swab samples were collected weekly (n=29 507) and tested for SARS-Cov-2 via reverse transcription-PCR by an accredited laboratory commissioned by the São Paulo Football Federation. We contacted the medical staff of each team with positive cases to collect information on disease severity.

RESULTS

Among 662 PCR-confirmed cases, 501 were athletes and 161 were staff. The new infection rate was 11.7% and 7.2% for athletes and staff, respectively. Athletes were more susceptible to infection than staff (OR: 1.71, 95% CI: 1.42, 2.06, p<0.001), although with lower chance for moderate to severe disease (OR: 0.06, 95% CI: 0.01, 0.54, p=0.012). Six teams had ≥20 individuals testing positive for SARS-CoV-2, whereas 19 teams had ≥10 confirmed cases. Twenty-five mass outbreaks were identified (≥5 infections within a team in a 2-week period). The prevalence of SARS-CoV-2 infections was similar in athletes and staff as the general population in São Paulo.

CONCLUSION

Despite weekly testing and other preventive measures, we found a high SARS-CoV-2 infection rate in athletes and staff after resuming football, which coincides with the high prevalence of infection in the community during the same period. These data may assist policy-makers and sports federations for determining if and when it is safe to resume competitions.

Modeling Provincial Covid-19 Epidemic Data Using an Adjusted Time-Dependent SIRD Model

In this paper, we develop a forecasting model for the spread of COVID-19 infection at a provincial (i.e., EU NUTS-3) level in Italy by using official data from the Italian Ministry of Health integrated with data extracted from daily official press conferences of regional authorities and local newspaper websites. This data integration is needed as COVID-19 death data are not available at the NUTS-3 level from official open data channels. An adjusted time-dependent SIRD model is used to predict the behavior of the epidemic; specifically, the number of susceptible, infected, deceased, recovered people and epidemiological parameters. Predictive model performance is evaluated using comparison with real data.

Disjoint and Functional Principal Component Analysis for Infected Cases and Deaths Due to COVID-19 in South American Countries with Sensor-Related Data

In this paper, we group South American countries based on the number of infected cases and deaths due to COVID-19. The countries considered are: Argentina, Bolivia, Brazil, Chile, Colombia, Ecuador, Peru, Paraguay, Uruguay, and Venezuela. The data used are collected from a database of Johns Hopkins University, an institution that is dedicated to sensing and monitoring the evolution of the COVID-19 pandemic. A statistical analysis, based on principal components with modern and recent techniques, is conducted. Initially, utilizing the correlation matrix, standard components and varimax rotations are calculated. Then, by using disjoint components and functional components, the countries are grouped. An algorithm that allows us to keep the principal component analysis updated with a sensor in the data warehouse is designed. As reported in the conclusions, this grouping changes depending on the number of components considered, the type of principal component (standard, disjoint or functional) and the variable to be considered (infected cases or deaths). The results obtained are compared to the k-means technique. The COVID-19 cases and their deaths vary in the different countries due to diverse reasons, as reported in the conclusions.

Multi-generational SIR modeling: Determination of parameters, epidemiological forecasting and age-dependent vaccination policies

We use an age-dependent SIR system of equations to model the evolution of the COVID-19. Parameters that measure the amount of interaction in different locations (home, work, school, other) are approximated from in-sample data using a random optimization scheme, and indicate changes in social distancing along the course of the pandemic. That allows the estimation of the time evolution of classical and age-dependent reproduction numbers. With those parameters we predict the disease dynamics, and compare our results with out-of-sample data from the City of Rio de Janeiro. Finally, we provide a numerical investigation regarding age-based vaccination policies, shedding some light on whether is preferable to vaccinate those at most risk (the elderly) or those who spread the disease the most (the youngest). There is no clear upshot, as the results depend on the age of those immunized, contagious parameters, vaccination schedules and efficiency.