COVID-19 Prediction Models and Unexploited Data

An ensemble approach improves the prediction of the COVID-19 pandemic in South Korea

Background

Modelling can contribute to disease prevention and control strategies. Accurate predictions of future cases and mortality rates were essential for establishing appropriate policies during the COVID-19 pandemic. However, no single model yielded definite conclusions, with each having specific strengths and weaknesses. Here we propose an ensemble learning approach which can offset the limitations of each model and improve prediction performances.

Methods

We generated predictions for the transmission and impact of COVID-19 in South Korea using seven individual models, including mathematical, statistical, and machine learning approaches. We integrated these predictions using three ensemble methods: stacking, average, and weighted average ensemble (WAE). We used train and test errors to measure a model's performance and selected the best covariate combinations based on the lowest train error. We then evaluated model performance using five error measures (r2, weighted mean absolute percentage error (WMAPE), autoregressive integrated moving average (ARIMA), mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE)) and selected the optimal covariate combination accordingly. To validate the generalisability of our approach, we applied the same modelling framework to USA data.

Results

Booster shot rate + Omicron variant BA.5 rate was the most commonly selected combination of covariates. For raw data evaluated using the WMAPE, individual models achieved the following: Generalised additive modelling (GAM) reached a value of 0.244 for the daily number of confirmed cases, a value of 0.172 for the time series Poisson for the daily number of confirmed deaths, and a value of 0.022 for both ARIMA and time series Poisson for the daily number of ICU patients. For smoothed data, the Holt-Winters model achieved a value of 0.058 for daily confirmed cases, while ARIMA attained a value of 0.058 for the daily number of confirmed deaths and 0.013 for the daily number of ICU patients. Among ensemble models, the SVM-based stacking ensemble achieved error values of 0.235 for the daily number of confirmed cases, 0.118 for the daily number of deaths, and 0.019 for the daily number of ICU patients on raw data. For smoothed data, the average ensemble and weighted average ensemble achieved 0.060 for the daily number of confirmed cases and 0.013 for daily ICU patients. The ensemble models also generalised well when applied to data from the USA.Booster shot rate + Omicron variant BA.5 rate was the most commonly selected combination of covariates. For raw data, GAM (0.244) predicted daily confirmed cases best, time series Poisson (0.172) predicted daily confirmed deaths, and both ARIMA and time series Poisson (0.022) predicted daily ICU patients, based on WMAPE. For smoothed data, time series Poisson predicted daily confirmed cases (0.065) best, while ARIMA best predicted daily confirmed deaths (0.058) and ICU patients (0.013). For ensemble models, stacking ensemble using SVM was the best model for predicting daily confirmed cases (0.228), deaths (0.11), and ICU patients (0.02). With smoothed data, average ensemble and WAE were the best models for predicting daily confirmed cases (0.058) and ICU patients (0.011). The performance of ensemble models was generalised to other countries using the USA data for predictive performance.

Conclusions

No single model performed consistently. While the ensemble models did not always provide the best predictions, a comparison of first-best and second-best models showed that they performed considerably better than the single models. If an ensemble model was not the best performing model, its performance was always not far from the best single model: a look at the mean and variance of the error measures shows that ensemble models provided stable predictions without much variation in their performances compared to single models. These results can be used to inform policymaking during future pandemics.

Forecasting of hospitalizations for COVID-19: A hybrid intelligence approach for Disease X research

BackgroundThe COVID-19 pandemic underscores the necessity for proactive measures against emerging diseases, epitomized by WHO's "Disease X." Among the myriad of indicators tracking COVID-19 progression, the count of hospitalized patients assumes a pivotal role. This metric facilitates timely responses from government agencies, enabling proactive allocation and management of medical resources.ObjectiveIn this study, we introduce a novel hybrid intelligent approach, the EMD&LSTM-ARIMA model.Method: This model integrates three techniques: Empirical Mode Decomposition (EMD) to decompose the data into intrinsic mode functions, Long Short-Term Memory (LSTM) neural network for capturing long-term dependencies and nonlinear relationships, and the Auto-Regressive Integrated Moving Average (ARIMA) model for handling linear trends and time series forecasting. We verify its high predictive power and utility through training and forecasting COVID-19 hospitalizations in the UK, Canada, Italy, and Japan.ResultsOur analysis reveals that all forecasted error rates remain below 10%, with Mean Absolute Percentage Error (MAPE) values obtained for these four countries as 2.30%, 3.33%, 1.63%, and 2.89%, respectively.ConclusionOur proposed EMD&LSTM-ARIMA model demonstrates robust forecasting performance, particularly for COVID-19 hospitalization data.

Prediction of COVID-19 cases by multifactor driven long short-term memory (LSTM) model

Since December 2019, cases of COVID-19 have spread globally, caused millions of deaths and huge economic losses. To investigate the impact of different factors and predict the future trend, this study collects relevant data for 15 countries, containing 44 features in about 900 days, which can be classified into four groups: pandemic information, the characteristics of countries, climate, and prevention policies. Through the selection of several important features, we identified the factors that have stronger impact on the increase of new cases in different groups. Then, we use a long-time span data to predict the future COVID-19 new cases by training a long short-term memory (LSTM) model, a support vector regressor (SVR) and a temporal convolutional network (TCN), among which LSTM possessed the best performance and offered a good generalization ability. Under the metric of explained variance scores (EVS), the prediction performances were the most accurate for Germany (0.864), Italy (0.860) and the United States (0.766). Overall, the results of this study may provide insight for predictions of number of COVID-19 new cases in more countries/regions and offer some insightful recommendation for governments to carry out more effective policies to prevent COVID-19.

A predictive model for post-COVID-19 pulmonary parenchymal abnormalities based on dual-center data

Documented radiological and physiological anomalies among coronavirus disease 2019 survivors necessitate prompt recognition of residual pulmonary parenchymal abnormalities for effective management of chronic pulmonary consequences. This study aimed to devise a predictive model to identify patients at risk of such abnormalities post-COVID-19. Our prognostic model was derived from a dual-center retrospective cohort comprising 501 hospitalized COVID-19 cases from July 2022 to March 2023. Of these, 240 patients underwent Chest CT scans three months post-infection. A predictive model was developed using stepwise regression based on the Akaike Information Criterion, incorporating clinical and laboratory parameters. The model was trained and validated on a split dataset, revealing a 33.3% incidence of pulmonary abnormalities. It achieved strong discriminatory power in the training set (area under the curve: 0.885, 95% confidence interval 0.832-0.938), with excellent calibration and decision curve analysis suggesting substantial net benefits across various threshold settings. We have successfully developed a reliable prognostic tool, complemented by a user-friendly nomogram, to estimate the probability of residual pulmonary parenchymal abnormalities three months post-COVID-19 infection. This model, demonstrating high performance, holds promise for guiding clinical interventions and improving the management of COVID-19-related pulmonary sequela.

Advanced federated ensemble internet of learning approach for cloud based medical healthcare monitoring system

Medical image machines serve as a valuable tool to monitor and diagnose a variety of diseases. However, manual and centralized interpretation are both error-prone and time-consuming due to malicious attacks. Numerous diagnostic algorithms have been developed to improve precision and prevent poisoning attacks by integrating symptoms, test methods, and imaging data. But in today's digital technology world, it is necessary to have a global cloud-based diagnostic artificial intelligence model that is efficient in diagnosis and preventing poisoning attacks and might be used for multiple purposes. We propose the Healthcare Federated Ensemble Internet of Learning Cloud Doctor System (FDEIoL) model, which integrates different Internet of Things (IoT) devices to provide precise and accurate interpretation without poisoning attack problems, thereby facilitating IoT-enabled remote patient monitoring for smart healthcare systems. Furthermore, the FDEIoL system model uses a federated ensemble learning strategy to provide an automatic, up-to-date global prediction model based on input local models from the medical specialist. This assures biomedical security by safeguarding patient data and preserving the integrity of diagnostic processes. The FDEIoL system model utilizes local model feature selection to discriminate between malicious and non-malicious local models, and ensemble strategies use positive and negative samples to optimize the performance of the test dataset, enhancing its capability for remote patient monitoring. The FDEIoL system model achieved an exceptional accuracy rate of 99.24% on the Chest X-ray dataset and 99.0% on the MRI dataset of brain tumors compared to centralized models, demonstrating its ability for precision diagnosis in IoT-enabled healthcare systems.

COVINet: a deep learning-based and interpretable prediction model for the county-wise trajectories of COVID-19 in the United States

The devastating impact of COVID-19 on the United States has been profound since its onset in January 2020. Predicting the trajectory of epidemics accurately and devising strategies to curb their progression are currently formidable challenges. In response to this crisis, we propose COVINet, which combines the architecture of Long Short-Term Memory and Gated Recurrent Unit, incorporating actionable covariates to offer high-accuracy prediction and explainable response. First, we train COVINet models for confirmed cases and total deaths with five input features, and compare Mean Absolute Errors (MAEs) and Mean Relative Errors (MREs) of COVINet against ten competing models from the United States CDC in the last four weeks before April 26, 2021. The results show COVINet outperforms all competing models for MAEs and MREs when predicting total deaths. Then, we focus on prediction for the most severe county in each of the top 10 hot-spot states using COVINet. The MREs are small for all predictions made in the last 7 or 30 days before March 23, 2023. Beyond predictive accuracy, COVINet offers high interpretability, enhancing the understanding of pandemic dynamics. This dual capability positions COVINet as a powerful tool for informing effective strategies in pandemic prevention and governmental decision-making.

Comparative performance of hybrid model based on discrete wavelet transform and ARIMA models in prediction incidence of COVID-19

Objective

Public health surveillance is an important aspect of outbreak early warning based on prediction models. The present study compares a hybrid model based on discrete wavelet transform (DWT) and ARIMA (Autoregressive Integrated Moving Average) for predicting incidence cases due to COVID-19.

Methods

In the current cross-sectional stuady based on time-series data, the incidence data for confirmed daily cases of COVID-19 from February 26, 2019, to April 25, 2022, were used. A hybrid model based on DWT and ARIMA and a pure ARIMA model were used to predict the trend. All analyzes were performed by MATLAB 2018, stata 2015, and Excel 2013 computer software.

Results

Compared to the ARIMA model, the prediction results of the hybrid model were closer to the actual number of incident cases. The correlation between predicted values by the hybrid model with real data was higher than the correlation between predicted values by the ARIMA model with actual data.

Conclusions

Discreet Wavelet decomposition of the dataset was combined with an ARIMA model and showed better performance in predicting the future trend.

High-resolution short-term prediction of the COVID-19 epidemic based on spatial-temporal model modified by historical meteorological data

In the global challenge of Coronavirus disease 2019 (COVID-19) pandemic, accurate prediction of daily new cases is crucial for epidemic prevention and socioeconomic planning. In contrast to traditional local, one-dimensional time-series data-based infection models, the study introduces an innovative approach by formulating the short-term prediction problem of new cases in a region as multidimensional, gridded time series for both input and prediction targets. A spatial-temporal depth prediction model for COVID-19 (ConvLSTM) is presented, and further ConvLSTM by integrating historical meteorological factors (Meteor-ConvLSTM) is refined, considering the influence of meteorological factors on the propagation of COVID-19. The correlation between 10 meteorological factors and the dynamic progression of COVID-19 was evaluated, employing spatial analysis techniques (spatial autocorrelation analysis, trend surface analysis, etc.) to describe the spatial and temporal characteristics of the epidemic. Leveraging the original ConvLSTM, an artificial neural network layer is introduced to learn how meteorological factors impact the infection spread, providing a 5-day forecast at a 0.01° × 0.01° pixel resolution. Simulation results using real dataset from the 3.15 outbreak in Shanghai demonstrate the efficacy of Meteor-ConvLSTM, with reduced RMSE of 0.110 and increased R 2 of 0.125 (original ConvLSTM: RMSE = 0.702, R 2 = 0.567; Meteor-ConvLSTM: RMSE = 0.592, R 2 = 0.692), showcasing its utility for investigating the epidemiological characteristics, transmission dynamics, and epidemic development.

An overview for monitoring and prediction of pathogenic microorganisms in the atmosphere

Corona virus disease 2019 (COVID-19) has exerted a profound adverse impact on human health. Studies have demonstrated that aerosol transmission is one of the major transmission routes of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Pathogenic microorganisms such as SARS-CoV-2 can survive in the air and cause widespread infection among people. Early monitoring of pathogenic microorganism transmission in the atmosphere and accurate epidemic prediction are the frontier guarantee for preventing large-scale epidemic outbreaks. Monitoring of pathogenic microorganisms in the air, especially in densely populated areas, may raise the possibility to detect viruses before people are widely infected and contain the epidemic at an earlier stage. The multi-scale coupled accurate epidemic prediction system can provide support for governments to analyze the epidemic situation, allocate health resources, and formulate epidemic response policies. This review first elaborates on the effects of the atmospheric environment on pathogenic microorganism transmission, which lays a theoretical foundation for the monitoring and prediction of epidemic development. Secondly, the monitoring technique development and the necessity of monitoring pathogenic microorganisms in the atmosphere are summarized and emphasized. Subsequently, this review introduces the major epidemic prediction methods and highlights the significance to realize a multi-scale coupled epidemic prediction system by strengthening the multidisciplinary cooperation of epidemiology, atmospheric sciences, environmental sciences, sociology, demography, etc. By summarizing the achievements and challenges in monitoring and prediction of pathogenic microorganism transmission in the atmosphere, this review proposes suggestions for epidemic response, namely, the establishment of an integrated monitoring and prediction platform for pathogenic microorganism transmission in the atmosphere.

Deep learning in public health: Comparative predictive models for COVID-19 case forecasting

The COVID-19 pandemic has had a significant impact on both the United Arab Emirates (UAE) and Malaysia, emphasizing the importance of developing accurate and reliable forecasting mechanisms to guide public health responses and policies. In this study, we compared several cutting-edge deep learning models, including Long Short-Term Memory (LSTM), bidirectional LSTM, Convolutional Neural Networks (CNN), hybrid CNN-LSTM, Multilayer Perceptron's, and Recurrent Neural Networks (RNN), to project COVID-19 cases in the aforementioned regions. These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. To enhance the performance of these models, Bayesian optimization techniques were employed. Subsequently, the models were re-evaluated to compare their effectiveness. Analytic approaches, both predictive and retrospective in nature, were used to interpret the data. Our primary objective was to determine the most effective model for predicting COVID-19 cases in the United Arab Emirates (UAE) and Malaysia. The findings indicate that the selected deep learning algorithms were proficient in forecasting COVID-19 cases, although their efficacy varied across different models. After a thorough evaluation, the model architectures most suitable for the specific conditions in the UAE and Malaysia were identified. Our study contributes significantly to the ongoing efforts to combat the COVID-19 pandemic, providing crucial insights into the application of sophisticated deep learning algorithms for the precise and timely forecasting of COVID-19 cases. These insights hold substantial value for shaping public health strategies, enabling authorities to develop targeted and evidence-based interventions to manage the virus spread and its impact on the populations of the UAE and Malaysia. The study confirms the usefulness of deep learning methodologies in efficiently processing complex datasets and generating reliable projections, a skill of great importance in healthcare and professional settings.

Robust Medical Diagnosis: A Novel Two-Phase Deep Learning Framework for Adversarial Proof Disease Detection in Radiology Images

In the realm of medical diagnostics, the utilization of deep learning techniques, notably in the context of radiology images, has emerged as a transformative force. The significance of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), lies in their capacity to rapidly and accurately diagnose diseases from radiology images. This capability has been particularly vital during the COVID-19 pandemic, where rapid and precise diagnosis played a pivotal role in managing the spread of the virus. DL models, trained on vast datasets of radiology images, have showcased remarkable proficiency in distinguishing between normal and COVID-19-affected cases, offering a ray of hope amidst the crisis. However, as with any technological advancement, vulnerabilities emerge. Deep learning-based diagnostic models, although proficient, are not immune to adversarial attacks. These attacks, characterized by carefully crafted perturbations to input data, can potentially disrupt the models' decision-making processes. In the medical context, such vulnerabilities could have dire consequences, leading to misdiagnoses and compromised patient care. To address this, we propose a two-phase defense framework that combines advanced adversarial learning and adversarial image filtering techniques. We use a modified adversarial learning algorithm to enhance the model's resilience against adversarial examples during the training phase. During the inference phase, we apply JPEG compression to mitigate perturbations that cause misclassification. We evaluate our approach on three models based on ResNet-50, VGG-16, and Inception-V3. These models perform exceptionally in classifying radiology images (X-ray and CT) of lung regions into normal, pneumonia, and COVID-19 pneumonia categories. We then assess the vulnerability of these models to three targeted adversarial attacks: fast gradient sign method (FGSM), projected gradient descent (PGD), and basic iterative method (BIM). The results show a significant drop in model performance after the attacks. However, our defense framework greatly improves the models' resistance to adversarial attacks, maintaining high accuracy on adversarial examples. Importantly, our framework ensures the reliability of the models in diagnosing COVID-19 from clean images.

Influenza-type epidemic risks by spatio-temporal Gaidai-Yakimov method

Background

Global public health was recently hampered by reported widespread spread of new coronavirus illness, although morbidity and fatality rates were low. Future coronavirus infection rates may be accurately predicted over a long-time horizon, using novel bio-reliability approach, being especially well suitable for environmental multi-regional health and biological systems. The high regional dimensionality along with cross-correlations between various regional datasets being challenging for conventional statistical tools to manage.

Methods

To assess future risks of epidemiological outbreak in any province of interest, novel spatio-temporal technique has been proposed. In a multicenter, population-based environment, assess raw clinical data using state-of-the-art, cutting-edge statistical methodologies.

Results

Authors have developed novel reliable long-term risk assessment methodology for future coronavirus infection outbreaks.

Conclusions

Based on national clinical patient monitoring raw dataset, it is concluded that although underlying data set data quality is questionable, the proposed method may be still applied.

A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022

The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.

Exposure notification system activity as a leading indicator for SARS-COV-2 caseload forecasting

PURPOSE

Digital methods to augment traditional contact tracing approaches were developed and deployed globally during the COVID-19 pandemic. These "Exposure Notification (EN)" systems present new opportunities to support public health interventions. To date, there have been attempts to model the impact of such systems, yet no reports have explored the value of real-time system data for predictive epidemiological modeling.

METHODS

We investigated the potential to short-term forecast COVID-19 caseloads using data from California's implementation of the Google Apple Exposure Notification (GAEN) platform, branded as CA Notify. CA Notify is a digital public health intervention leveraging resident's smartphones for anonymous EN. We extended a published statistical model that uses prior case counts to investigate the possibility of predicting short-term future case counts and then added EN activity to test for improved forecast performance. Additional predictive value was assessed by comparing the pandemic forecasting models with and without EN activity to the actual reported caseloads from 1-7 days in the future.

RESULTS

Observation of time series presents noticeable evidence for temporal association of system activity and caseloads. Incorporating earlier ENs in our model improved prediction of the caseload counts. Using Bayesian inference, we found nonzero influence of EN terms with probability one. Furthermore, we found a reduction in both the mean absolute percentage error and the mean squared prediction error, the latter of at least 5% and up to 32% when using ENs over the model without.

CONCLUSIONS

This preliminary investigation suggests smartphone based ENs can significantly improve the accuracy of short-term forecasting. These predictive models can be readily deployed as local early warning systems to triage resources and interventions.

A Novel AUC Maximization Imbalanced Learning Approach for Predicting Composite Outcomes in COVID-19 Hospitalized Patients

The COVID-19 patient data for composite outcome prediction often comes with class imbalance issues, i.e., only a small group of patients develop severe composite events after hospital admission, while the rest do not. An ideal COVID-19 composite outcome prediction model should possess strong imbalanced learning capability. The model also should have fewer tuning hyperparameters to ensure good usability and exhibit potential for fast incremental learning. Towards this goal, this study proposes a novel imbalanced learning approach called Imbalanced maximizing-Area Under the Curve (AUC) Proximal Support Vector Machine (ImAUC-PSVM) by the means of classical PSVM to predict the composite outcomes of hospitalized COVID-19 patients within 30 days of hospitalization. ImAUC-PSVM offers the following merits: (1) it incorporates straightforward AUC maximization into the objective function, resulting in fewer parameters to tune. This makes it suitable for handling imbalanced COVID-19 data with a simplified training process. (2) Theoretical derivations reveal that ImAUC-PSVM has the same analytical solution form as PSVM, thus inheriting the advantages of PSVM for handling incremental COVID-19 cases through fast incremental updating. We built and internally and externally validated our proposed classifier using real COVID-19 patient data obtained from three separate sites of Mayo Clinic in the United States. Additionally, we validated it on public datasets using various performance metrics. Experimental results demonstrate that ImAUC-PSVM outperforms other methods in most cases, showcasing its potential to assist clinicians in triaging COVID-19 patients at an early stage in hospital settings, as well as in other prediction applications.

Unraveling complex relationships between COVID-19 risk factors using machine learning based models for predicting mortality of hospitalized patients and identification of high-risk group: a large retrospective study

Background

At the end of 2019, the coronavirus disease 2019 (COVID-19) pandemic increased the hospital burden of COVID-19 caused by the SARS-Cov-2 and became the most significant health challenge for nations worldwide. The severity and high mortality of COVID-19 have been correlated with various demographic characteristics and clinical manifestations. Prediction of mortality rate, identification of risk factors, and classification of patients played a crucial role in managing COVID-19 patients. Our purpose was to develop machine learning (ML)-based models for the prediction of mortality and severity among patients with COVID-19. Identifying the most important predictors and unraveling their relationships by classification of patients to the low-, moderate- and high-risk groups might guide prioritizing treatment decisions and a better understanding of interactions between factors. A detailed evaluation of patient data is believed to be important since COVID-19 resurgence is underway in many countries.

Results

The findings of this study revealed that the ML-based statistically inspired modification of the partial least square (SIMPLS) method could predict the in-hospital mortality among COVID-19 patients. The prediction model was developed using 19 predictors including clinical variables, comorbidities, and blood markers with moderate predictability (Q² = 0.24) to separate survivors and non-survivors. Oxygen saturation level, loss of consciousness, and chronic kidney disease (CKD) were the top mortality predictors. Correlation analysis showed different correlation patterns among predictors for each non-survivor and survivor cohort separately. The main prediction model was verified using other ML-based analyses with a high area under the curve (AUC) (0.81-0.93) and specificity (0.94-0.99). The obtained data revealed that the mortality prediction model can be different for males and females with diverse predictors. Patients were classified into four clusters of mortality risk and identified the patients at the highest risk of mortality, which accentuated the most significant predictors correlating with mortality.

Conclusion

An ML model for predicting mortality among hospitalized COVID-19 patients was developed considering the interactions between factors that may reduce the complexity of clinical decision-making processes. The most predictive factors related to patient mortality were identified by assessing and classifying patients into different groups based on their sex and mortality risk (low-, moderate-, and high-risk groups).

Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics

This essay discusses a potential method for predicting the behavior of various physical processes and uses the COVID-19 outbreak to demonstrate its applicability. This study assumes that the current data set reflects the output of a dynamic system that is governed by a nonlinear ordinary differential equation. This dynamic system may be described by a Differential Neural Network (DNN) with time-varying weights matrix parameters. A new hybrid learning scheme based on the decomposition of the signal to be predicted. The decomposition considers the slow and fast components of the signal which is more natural to signals such as the ones corresponding to the number of infected and deceased patients who suffered of COVID 2019 sickness. The paper results demonstrate the recommended method offers competitive performance (70 days of COVID prediction) in comparison to similar studies.

Is It Possible to Predict COVID-19? Stochastic System Dynamic Model of Infection Spread in Kazakhstan

BACKGROUND

Since the start of the COVID-19 pandemic, scientists have begun to actively use models to determine the epidemiological characteristics of the pathogen. The transmission rate, recovery rate and loss of immunity to the COVID-19 virus change over time and depend on many factors, such as the seasonality of pneumonia, mobility, testing frequency, the use of masks, the weather, social behavior, stress, public health measures, etc. Therefore, the aim of our study was to predict COVID-19 using a stochastic model based on the system dynamics approach.

METHOD

We developed a modified SIR model in AnyLogic software. The key stochastic component of the model is the transmission rate, which we consider as an implementation of Gaussian random walks with unknown variance, which was learned from real data.

RESULTS

The real data of total cases turned out to be outside the predicted minimum-maximum interval. The minimum predicted values of total cases were closest to the real data. Thus, the stochastic model we propose gives satisfactory results for predicting COVID-19 from 25 to 100 days. The information we currently have about this infection does not allow us to make predictions with high accuracy in the medium and long term.

CONCLUSIONS

In our opinion, the problem of the long-term forecasting of COVID-19 is associated with the absence of any educated guess regarding the dynamics of β(t) in the future. The proposed model requires improvement with the elimination of limitations and the inclusion of more stochastic parameters.

SecureFed: federated learning empowered medical imaging technique to analyze lung abnormalities in chest X-rays

Machine learning is an effective and accurate technique to diagnose COVID-19 infections using image data, and chest X-Ray (CXR) is no exception. Considering privacy issues, machine learning scientists end up receiving less medical imaging data. Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm that generates an unbiased global model that follows local model (from clients) without exposing their personal data. In the case of heterogeneous data among clients, vanilla or default FL mechanism still introduces an insecure method for updating models. Therefore, we proposed SecureFed-a secure aggregation method-which ensures fairness and robustness. In our experiments, we employed COVID-19 CXR dataset (of size 2100 positive cases) and compared it with the existing FL frameworks such as FedAvg, FedMGDA+, and FedRAD. In our comparison, we primarily considered robustness (accuracy) and fairness (consistency). As the SecureFed produced consistently better results, it is generic enough to be considered for multimodal data.

An intelligent deep convolutional network based COVID-19 detection from chest X-rays

Coronavirus disease-2019 (COVID-19) seems to be a fast spreading contagious illness that affects both humans and animals. This catastrophic deadly virus has an impact on people's daily lives, their wellbeing, and a nation's economy. According to a clinical research of COVID-19 affected patients, these individuals have been most commonly infected with a lung illness after coming into touch with the virus. A chest X-ray (also known as radiography) or a chest CT scan seems to be more efficient imaging techniques for detecting lung issues. Nonetheless, when compared to a chest CT, a significant chest X-ray remains a less expensive procedure. Thus, in this research, a novel Deep convolution neural network algorithm is presented to detect the COVID-19 from X-ray image. Moreover, to enhance diagnostics sensitivity and reduce error rate, a hybrid Two-step-AS clustering approach with Ensemble Bootstrap aggregating training and Multiple NN methods used. In addition, TSEBANN model has been employed to explore the qualification procedure effects. The proposed algorithm was trained before and after classification while compared to traditional Convolutional Neural Network (CNN). After, the process of pre-processing and feature extraction, the CNN strategy was adopted as an identification approach to categorize the information depending on Chest X-ray recognition. These examples were then classified using the CNN classification technique. The testing was conducted on the COVID-19 X-ray dataset, and the cross-validation approach was used to determine the model’s validity. The result indicated that a CNN system classification has attained an accuracy of 98.062 %.

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Background: Sarcopenia is an aging syndrome that increases the risks of various adverse outcomes, including falls, fractures, physical disability, and death. Sarcopenia can be diagnosed through medical images-based body part analysis, which requires laborious and time-consuming outlining of irregular contours of abdominal body parts. Therefore, it is critical to develop an efficient computational method for automatically segmenting body parts and predicting diseases. Methods: In this study, we designed an Artificial Intelligence Body Part Measure System (AIBMS) based on deep learning to automate body parts segmentation from abdominal CT scans and quantification of body part areas and volumes. The system was developed using three network models, including SEG-NET, U-NET, and Attention U-NET, and trained on abdominal CT plain scan data. Results: This segmentation model was evaluated using multi-device developmental and independent test datasets and demonstrated a high level of accuracy with over 0.9 DSC score in segment body parts. Based on the characteristics of the three network models, we gave recommendations for the appropriate model selection in various clinical scenarios. We constructed a sarcopenia classification model based on cutoff values (Auto SMI model), which demonstrated high accuracy in predicting sarcopenia with an AUC of 0.874. We used Youden index to optimize the Auto SMI model and found a better threshold of 40.69. Conclusion: We developed an AI system to segment body parts in abdominal CT images and constructed a model based on cutoff value to achieve the prediction of sarcopenia with high accuracy.

The value of chest X-ray and CT severity scoring systems in the diagnosis of COVID-19: A review

Coronavirus disease 2019 (COVID-19) is caused by a coronavirus family member known as severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). The main laboratory test to confirm the quick diagnosis of COVID-19 infection is reverse transcription-polymerase chain reaction (RT-PCR) based on nasal or throat swab sampling. A small percentage of false-negative RT-PCR results have been reported. The RT-PCR test has a sensitivity of 50-72%, which could be attributed to a low viral load in test specimens or laboratory errors. In contrast, chest CT has shown 56-98% of sensitivity in diagnosing COVID-19 at initial presentation and has been suggested to be useful in correcting false negatives from RT-PCR. Chest X-rays and CT scans have been proposed to predict COVID-19 disease severity by displaying the score of lung involvement and thus providing information about the diagnosis and prognosis of COVID-19 infection. As a result, the current study provides a comprehensive overview of the utility of the severity score index using X-rays and CT scans in diagnosing patients with COVID-19 when compared to RT-PCR.

Prediction of the COVID-19 infectivity and the sustainable impact on public health under deep learning algorithm

The aim is to explore the development trend of COVID-19 (Corona Virus Disease 2019) and predict the infectivity of 2019-nCoV (2019 Novel Coronavirus), as well as its impact on public health. First, the existing data are analyzed through data pre-processing to extract useful feature factors. Then, the LSTM (Long-Short Term Memory) prediction model in the deep learning algorithm is used to predict the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country, respectively. Meanwhile, the impact of intervention time changes on the epidemic situation is compared. The results show that the prediction results are almost consistent with the actual values. Specifically, Hubei Province abolishes quarantine restrictions after the Spring Festival holiday, and the first COVID-19 peak is reached in late February, while the second COVID-19 peak has been reached in early March. Finally, the cumulative number of diagnoses reaches 85,000 cases, with an increase of 15,000 cases compared with the nationwide cases outside Hubei under the continuous implementation of prevention and control measures. Under the prediction of the proposed LSTM model, if the nationwide implementation of prevention and control interventions is postponed by 5 days, the epidemic will peak in early March, and the cumulative number of diagnoses will be about 200,000; and if the intervention measures are implemented five days earlier, the epidemic will peak in mid-February, with a cumulative number of diagnoses of approximately 40,000. Meanwhile, the proposed LSTM model predicts the RMSE values of the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country as 34.63, 75.42, and 50.27, respectively. Under model comparison analysis, the prediction error of the proposed LSTM model is small and has better applicability over similar algorithms. The results show that the LSTM model is effective and has high performance in infectious disease prediction, and the research results can provide scientific and effective references for subsequent related research.

Stochastic Modeling and Forecasting of Covid-19 Deaths: Analysis for the Fifty States in the United States

In this work, we study and analyze the aggregate death counts of COVID-19 reported by the United States Centers for Disease Control and Prevention (CDC) for the fifty states in the United States. To do this, we derive a stochastic model describing the cumulative number of deaths reported daily by CDC from the first time Covid-19 death is recorded to June 20, 2021 in the United States, and provide a forecast for the death cases. The stochastic model derived in this work performs better than existing deterministic logistic models because it is able to capture irregularities in the sample path of the aggregate death counts. The probability distribution of the aggregate death counts is derived, analyzed, and used to estimate the count’s per capita initial growth rate, carrying capacity, and the expected value for each given day as at the time this research is conducted. Using this distribution, we estimate the expected first passage time when the aggregate death count is slowing down. Our result shows that the expected aggregate death count is slowing down in all states as at the time this analysis is conducted (June 2021). A formula for predicting the end of Covid-19 deaths is derived. The daily expected death count for each states is plotted as a function of time. The probability density function for the current day, together with the forecast and its confidence interval for the next four days, and the root mean square error for our simulation results are estimated.

A Survey on Applications of Artificial Intelligence in Fighting Against COVID-19

The COVID-19 pandemic caused by the SARS-CoV-2 virus has spread rapidly worldwide, leading to a global outbreak. Most governments, enterprises, and scientific research institutions are participating in the COVID-19 struggle to curb the spread of the pandemic. As a powerful tool against COVID-19, artificial intelligence (AI) technologies are widely used in combating this pandemic. In this survey, we investigate the main scope and contributions of AI in combating COVID-19 from the aspects of disease detection and diagnosis, virology and pathogenesis, drug and vaccine development, and epidemic and transmission prediction. In addition, we summarize the available data and resources that can be used for AI-based COVID-19 research. Finally, the main challenges and potential directions of AI in fighting against COVID-19 are discussed. Currently, AI mainly focuses on medical image inspection, genomics, drug development, and transmission prediction, and thus AI still has great potential in this field. This survey presents medical and AI researchers with a comprehensive view of the existing and potential applications of AI technology in combating COVID-19 with the goal of inspiring researchers to continue to maximize the advantages of AI and big data to fight COVID-19.

Future forecasting prediction of Covid-19 using hybrid deep learning algorithm

Due the quick spread of coronavirus disease 2019 (COVID-19), identification of that disease, prediction of mortality rate and recovery rate are considered as one of the critical challenges in the whole world. The occurrence of COVID-19 dissemination beyond the world is analyzed in this research and an artificial-intelligence (AI) based deep learning algorithm is suggested to detect positive cases of COVID19 patients, mortality rate and recovery rate using real-world datasets. Initially, the unwanted data like prepositions, links, hashtags etc., are removed using some pre-processing techniques. After that, term frequency inverse-term frequency (TF-IDF) andBag of Words (BoW) techniques are utilized to extract the features from pre-processed dataset. Then, Mayfly Optimization (MO) algorithm is performed to pick the relevant features from the set of features. Finally, two deep learning procedures, ResNet model and GoogleNet model, are hybridized to achieve the prediction process. Our system examines two different kinds of publicly available text datasets to identify COVID-19 disease as well as to predict mortality rate and recovery rate using those datasets. There are four different datasets are taken to analyse the performance, in which the proposed method achieves 97.56% accuracy which is 1.40% greater than Linear Regression (LR) and Multinomial Naive Bayesian (MNB), 3.39% higher than Random Forest (RF) and Stochastic gradient boosting (SGB) as well as 5.32% higher than Decision tree (DT) and Bagging techniques if first dataset. When compared to existing machine learning models, the simulation result indicates that a proposed hybrid deep learning method is valuable in corona virus identification and future mortality forecast study.

Prediction of COVID-19 Infections for Municipalities in the Netherlands: Algorithm Development and Interpretation

Background

COVID-19 was first identified in December 2019 in the city of Wuhan, China. The virus quickly spread and was declared a pandemic on March 11, 2020. After infection, symptoms such as fever, a (dry) cough, nasal congestion, and fatigue can develop. In some cases, the virus causes severe complications such as pneumonia and dyspnea and could result in death. The virus also spread rapidly in the Netherlands, a small and densely populated country with an aging population. Health care in the Netherlands is of a high standard, but there were nevertheless problems with hospital capacity, such as the number of available beds and staff. There were also regions and municipalities that were hit harder than others. In the Netherlands, there are important data sources available for daily COVID-19 numbers and information about municipalities.

Objective

We aimed to predict the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands, using a data set with the properties of 355 municipalities in the Netherlands and advanced modeling techniques.

Methods

We collected relevant static data per municipality from data sources that were available in the Dutch public domain and merged these data with the dynamic daily number of infections from January 1, 2020, to May 9, 2021, resulting in a data set with 355 municipalities in the Netherlands and variables grouped into 20 topics. The modeling techniques random forest and multiple fractional polynomials were used to construct a prediction model for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands.

Results

The final prediction model had an R² of 0.63. Important properties for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality in the Netherlands were exposure to particulate matter with diameters <10 μm (PM10) in the air, the percentage of Labour party voters, and the number of children in a household.

Conclusions

Data about municipality properties in relation to the cumulative number of confirmed infections in a municipality in the Netherlands can give insight into the most important properties of a municipality for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality. This insight can provide policy makers with tools to cope with COVID-19 and may also be of value in the event of a future pandemic, so that municipalities are better prepared.

Artificial intelligence and IoT based prediction of Covid-19 using chest X-ray images

Coronavirus illness (COVID-19), discovered in late 2019, has spread rapidly worldwide, resulting in significant mortality. This study analyzed the performance of studies that employed machines and DL on chest X-ray pictures and CT scans for COVID-19 diagnosis. ML approaches on CT and X-ray images aided incorrectly in identifying COVID-19. The fast spread of COVID-19 worldwide and the growing number of deaths necessitates an immediate response from all sectors. Authorities will be able to deal with the effects more efficiently if such illnesses can be predicted in the future. Furthermore, it is crucial to maintain track of the number of infected persons through regular check-ups, and it is frequently required to confine affected people and implement medical treatments. In addition, various additional elements, such as environmental influences and commonalities among the most afflicted places, should be considered to slow the spread of COVID-19, and precautions should be taken. AI-based approaches for the prediction and diagnosis of COVID-19 were suggested in this paper. This Review Article discusses current advances in AI technology and its biological applications, particularly the coronavirus.

Incidence and characteristics of COVID-19 in French professional football players during the 2020–2021 season

Objectives

To describe the epidemiology of COVID-19 in French professional football players, and to compare the infection incidence with the general population across the first three waves.

Methods

During the 2020–2021 season, all professional football players (n = 1217) in the two primary French leagues underwent weekly testing for SARS-CoV-2 infection by nasopharyngeal PCR, in combination with rigorous infection control measures.

Results

Among all players, 572 (47%) tested positive at least once, with no COVID-19-related death or hospital admission. Monthly incidence estimates in players ranged from 1486 to 6731 per 100,000 individuals, i.e. 2–17 times higher than incidence estimates in the general population in France during the study period.

Conclusion

Almost 50% of professional football players developed SARS-CoV-2 infection during the 2020–2021 season in France, with no severe complication.

Mathematical modeling of SARS-nCoV-2 virus in Tamil Nadu, South India

The purpose of this paper is to build a mathematical model for the study of the roles of lock-down, social distancing, vaccination, detection efficiency, and health care capacity planning of the COVID-19 pandemic taking into account the demographic topology of the State of Tamil Nadu, India. Two mathematical models are proposed for the evolution of the first and second wave of COVID-19 pandemic. The model for the first wave considers lock-down orders, social distancing measures, and detection efficiency. The model for the second wave considers more sub-populations and incorporates two more elements, vaccination and health care capacity. Daily reported data on the evolution of the COVID-19 pandemic are used to determine the parameter values. The dynamics produced by the mathematical model closely follow the evolution of COVID-19 in the State of Tamil Nadu. Numerical simulation shows that the lock-down effect is limited. Social distancing implementation and detection of positive cases are relatively ineffective compared with other big cities. Shortage of health care resources is one of the factors responsible for rapidly spreading in the second wave in Tamil Nadu.

Predicting COVID-19 county-level case number trend by combining demographic characteristics and social distancing policies

Objective

Predicting daily trends in the Coronavirus Disease 2019 (COVID-19) case number is important to support individual decisions in taking preventative measures. This study aims to use COVID-19 case number history, demographic characteristics, and social distancing policies both independently/interdependently to predict the daily trend in the rise or fall of county-level cases.

Materials and Methods

We extracted 2093 features (5 from the US COVID-19 case number history, 1824 from the demographic characteristics independently/interdependently, and 264 from the social distancing policies independently/interdependently) for 3142 US counties. Using the top selected 200 features, we built 4 machine learning models: Logistic Regression, Naïve Bayes, Multi-Layer Perceptron, and Random Forest, along with 4 Ensemble methods: Average, Product, Minimum, and Maximum, and compared their performances.

Results

The Ensemble Average method had the highest area-under the receiver operator characteristic curve (AUC) of 0.692. The top ranked features were all interdependent features.

Conclusion

The findings of this study suggest the predictive power of diverse features, especially when combined, in predicting county-level trends of COVID-19 cases and can be helpful to individuals in making their daily decisions. Our results may guide future studies to consider more features interdependently from conventionally distinct data sources in county-level predictive models. Our code is available at: https://doi.org/10.5281/zenodo.6332944.

Understanding the Security and Privacy Concerns About the Use of Identifiable Health Data in the Context of the COVID-19 Pandemic: Survey Study of Public Attitudes Toward COVID-19 and Data-Sharing

BACKGROUND

The COVID-19 pandemic increased the availability and use of population and individual health data to optimize tracking and analysis of the spread of the virus. Many health care services have had to rapidly digitalize in order to maintain the continuity of care provision. Data collection and dissemination have provided critical support for defending against the spread of the virus since the beginning of the pandemic; however, little is known about public perceptions of and attitudes toward the use, privacy, and security of data.

OBJECTIVE

The goal of this study is to better understand people's willingness to share data in the context of the COVID-19 pandemic.

METHODS

A web-based survey was conducted on individuals' use of and attitudes toward health data for individuals aged 18 years and older, and in particular, with a reported diagnosis of a chronic health condition placing them at the highest risk of severe COVID-19.

RESULTS

In total, 4764 individuals responded to this web-based survey, of whom 4674 (98.1%) reported a medical diagnosis of at least 1 health condition (3 per person on average), with type 2 diabetes (n=2974, 62.7%), hypertension (n=2147, 45.2%), and type 1 diabetes (n=1299, 27.4%) being most prominent in our sample. In general, more people are comfortable with sharing anonymized data than personally identifiable data. People reported feeling comfortable sharing data that were able to benefit others; 66% (3121 respondents) would share personal identifiable data if its primary purpose was deemed beneficial for the health of others. Almost two-thirds (n=3026; 63.9%) would consent to sharing personal, sensitive health data with government or health authority organizations. Conversely, over a quarter of respondents (n=1297, 27.8%) stated that they did not trust any organization to protect their data, and 54% (n=2528) of them reported concerns about the implications of sharing personal information. Almost two-thirds (n=3054, 65%) of respondents were concerned about the provisions of appropriate legislation that seeks to prevent data misuse and hold organizations accountable in the case of data misuse.

CONCLUSIONS

Although our survey focused mainly on the views of those living with chronic health conditions, the results indicate that data sensitivity is highly contextual. More people are more comfortable with sharing anonymized data rather than personally identifiable data. Willingness to share data also depended on the receiving body, highlighting trust as a key theme, in particular who may have access to shared personal health data and how they may be used in the future. The nascency of legal guidance in this area suggests a need for humanitarian guidelines for data responsibility during disaster relief operations such as pandemics and for involving the public in their development.

Model-based assessment of COVID-19 epidemic dynamics by wastewater analysis

Continuous surveillance of COVID-19 diffusion remains crucial to control its diffusion and to anticipate infection waves. Detecting viral RNA load in wastewater samples has been suggested as an effective approach for epidemic monitoring and the development of an effective warning system. However, its quantitative link to the epidemic status and the stages of outbreak is still elusive. Modelling is thus crucial to address these challenges. In this study, we present a novel mechanistic model-based approach to reconstruct the complete epidemic dynamics from SARS-CoV-2 viral load in wastewater. Our approach integrates noisy wastewater data and daily case numbers into a dynamical epidemiological model. As demonstrated for various regions and sampling protocols, it quantifies the case numbers, provides epidemic indicators and accurately infers future epidemic trends. Following its quantitative analysis, we also provide recommendations for wastewater data standards and for their use as warning indicators against new infection waves. In situations of reduced testing capacity, our modelling approach can enhance the surveillance of wastewater for early epidemic prediction and robust and cost-effective real-time monitoring of local COVID-19 dynamics.

COVID-Net CXR-2: An Enhanced Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest X-ray Images

As the COVID-19 pandemic devastates globally, the use of chest X-ray (CXR) imaging as a complimentary screening strategy to RT-PCR testing continues to grow given its routine clinical use for respiratory complaint. As part of the COVID-Net open source initiative, we introduce COVID-Net CXR-2, an enhanced deep convolutional neural network design for COVID-19 detection from CXR images built using a greater quantity and diversity of patients than the original COVID-Net. We also introduce a new benchmark dataset composed of 19,203 CXR images from a multinational cohort of 16,656 patients from at least 51 countries, making it the largest, most diverse COVID-19 CXR dataset in open access form. The COVID-Net CXR-2 network achieves sensitivity and positive predictive value of 95.5 and 97.0%, respectively, and was audited in a transparent and responsible manner. Explainability-driven performance validation was used during auditing to gain deeper insights in its decision-making behavior and to ensure clinically relevant factors are leveraged for improving trust in its usage. Radiologist validation was also conducted, where select cases were reviewed and reported on by two board-certified radiologists with over 10 and 19 years of experience, respectively, and showed that the critical factors leveraged by COVID-Net CXR-2 are consistent with radiologist interpretations.

Predicting COVID-19 Cases in South Korea Using Stringency and Niño Sea Surface Temperature Indices

Most coronavirus disease 2019 (COVID-19) models use a combination of agent-based and equation-based models with only a few incorporating environmental factors in their prediction models. Many studies have shown that human and environmental factors play huge roles in disease transmission and spread, but few have combined the use of both factors, especially for SARS-CoV-2. In this study, both man-made policies (Stringency Index) and environment variables (Niño SST Index) were combined to predict the number of COVID-19 cases in South Korea. The performance indicators showed satisfactory results in modeling COVID-19 cases using the Non-linear Autoregressive Exogenous Model (NARX) as the modeling method, and Stringency Index (SI) and Niño Sea Surface Temperature (SST) as model variables. In this study, we showed that the accuracy of SARS-CoV-2 transmission forecasts may be further improved by incorporating both the Niño SST and SI variables and combining these variables with NARX may outperform other models. Future forecasting work by modelers should consider including climate or environmental variables (i.e., Niño SST) to enhance the prediction of transmission and spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Estimating the effect of non-pharmaceutical interventions on US SARS-CoV-2 infections in the first year of the pandemic

SARS-CoV-2 emerged in late 2019 as a zoonotic infection of humans, and proceeded to cause a worldwide pandemic of historic magnitude. Here, we use a simple epidemiological model and consider the full range of initial estimates from published studies for infection and recovery rates, seasonality, changes in mobility, the effectiveness of masks and the fraction of people wearing them. Monte Carlo simulations are used to simulate the progression of possible pandemics and we show a match for the real progression of the pandemic during 2020 with an R 2 of 0.91. The results show that the combination of masks and changes in mobility avoided approximately 248.3 million (σ = 31.2 million) infections in the US before vaccinations became available.

Forecasting of a complex phenomenon using stochastic data-based techniques under non-conventional schemes: The SARS-CoV-2 virus spread case

Epidemics are complex dynamical processes that are difficult to model. As revealed by the SARS-CoV-2 pandemic, the social behavior and policy decisions contribute to the rapidly changing behavior of the virus' spread during outbreaks and recessions. In practice, reliable forecasting estimations are needed, especially during early contagion stages when knowledge and data are insipient. When stochastic models are used to address the problem, it is necessary to consider new modeling strategies. Such strategies should aim to predict the different contagious phases and fast changes between recessions and outbreaks. At the same time, it is desirable to take advantage of existing modeling frameworks, knowledge and tools. In that line, we take Autoregressive models with exogenous variables (ARX) and Vector autoregressive (VAR) techniques as a basis. We then consider analogies with epidemic's differential equations to define the structure of the models. To predict recessions and outbreaks, the possibility of updating the model's parameters and stochastic structures is considered, providing non-stationarity properties and flexibility for accommodating the incoming data to the models. The Generalized-Random-Walk (GRW) and the State-Dependent-Parameter (SDP) techniques shape the parameters' variability. The stochastic structures are identified following the Akaike (AIC) criterion. The models use the daily rates of infected, death, and healed individuals, which are the most common and accurate data retrieved in the early stages. Additionally, different experiments aim to explore the individual and complementary role of these variables. The results show that although both the ARX-based and VAR-based techniques have good statistical accuracy for seven-day ahead predictions, some ARX models can anticipate outbreaks and recessions. We argue that short-time predictions for complex problems could be attained through stochastic models that mimic the fundamentals of dynamic equations, updating their parameters and structures according to incoming data.

Deep Learning for Covid-19 Screening Using Chest X-Rays in 2020: A Systematic Review

Artificial Intelligence (AI) has promoted countless contributions in the field of healthcare and medical imaging. In this paper, we thoroughly analyze peer-reviewed research findings/articles on AI-guided tools for Covid-19 analysis/screening using chest X-ray images in the year 2020. We discuss on how far deep learning algorithms help in decision-making. We identify/address data collections, methodical contributions, promising methods, and challenges. However, a fair comparison is not trivial as dataset sizes vary over time, throughout the year 2020. Even though their unprecedented efforts in building AI-guided tools to detect, localize, and segment Covid-19 cases are limited to education and training, we elaborate on their strengths and possible weaknesses when we consider the need of cross-population train/test models. In total, with search keywords: (Covid-19 OR Coronavirus) AND chest x-ray AND deep learning AND artificial intelligence AND medical imaging in both PubMed Central Repository and Web of Science, we systematically reviewed 58 research articles and performed meta-analysis.

Symptom-based analysis of COVID-19 cases using supervised machine learning approaches to improve medical decision-making

The world today faces a new challenge that is unprecedented in the last 100 years. The emergence of a new coronavirus has led to a human catastrophe. Scientists in various sciences have been looking for solutions to this problem so far. In addition to general vaccination, maintaining social distance and adherence to government guidelines on safety precaution measures are the most well-known strategies to prevent COVID-19 infection. In this research, we tried to examine the symptoms of COVID-19 cases through different supervised machine learning methods. We solved the class imbalance problem using the synthetic minority over-sampling (SMOTE) method and then developed some classification models to predict the outcome of COVID-19 cases (recovery or death). Besides, we implemented a rule-based technique to identify different combinations of variables with specific ranges of their values that together affect disease severity. Our results showed that the random forest model with 95.6% accuracy, 97.1% sensitivity, 94.0% specification, 94.4% precision, 95.8% F-score, and 99.3% AUC-score outperforms state-of-the-art classification models. Finally, we identified the most significant rules that state various combinations of 6 features in certain ranges of their values lead to patients’ recovery with a confidence value of 90%. In conclusion, the classification results in this study show better performance than recent studies, and the extracted rules help physicians consider other important factors to improve health services and medical decision-making for different groups of COVID-19 patients.

The allometric propagation of COVID-19 is explained by human travel

We analyzed the number of cumulative positive cases of COVID-19 as a function of time in countries around the World. We tracked the increase in cases from the onset of the pandemic in each region for up to 150 days. We found that in 81 out of 146 regions the trajectory was described with a power-law function for up to 30 days. We also detected scale-free properties in the majority of sub-regions in Australia, Canada, China, and the United States (US). We developed an allometric model that was capable of fitting the initial phase of the pandemic and was the best predictor for the propagation of the illness for up to 100 days. We then determined that the power-law COVID-19 exponent correlated with measurements of human mobility. The COVID-19 exponent correlated with the magnitude of air passengers per country. This correlation persisted when we analyzed the number of air passengers per US states, and even per US metropolitan areas. Furthermore, the COVID-19 exponent correlated with the number of vehicle miles traveled in the US. Together, air and vehicular travel explained 70% of the variability of the COVID-19 exponent. Taken together, our results suggest that the scale-free propagation of the virus is present at multiple geographical scales and is correlated with human mobility. We conclude that models of disease transmission should integrate scale-free dynamics as part of the modeling strategy and not only as an emergent phenomenological property.

Intelligent Data Analysis for Infection Spread Prediction

Intelligent data analysis based on artificial intelligence and Big Data tools is widely used by the scientific community to overcome global challenges. One of these challenges is the worldwide coronavirus pandemic, which began in early 2020. Data science not only provides an opportunity to assess the impact caused by a pandemic, but also to predict the infection spread. In addition, the model expansion by economic, social, and infrastructural factors makes it possible to predict changes in all spheres of human activity in competitive epidemiological conditions. This article is devoted to the use of anonymized and personal data in predicting the coronavirus infection spread. The basic “Susceptible–Exposed–Infected–Recovered” model was extended by including a set of demographic, administrative, and social factors. The developed model is more predictive and applicable in assessing future pandemic impact. After a series of simulation experiment results, we concluded that personal data use in high-level modeling of the infection spread is excessive.

Forecasting Covid-19 Transmission with ARIMA and LSTM Techniques in Morocco

In this paper, we are interested to forecast and predict the time evolution of the Covid-19 in Morocco based on two different time series forecasting models. We used Auto-Regressive Integrated Moving Average (ARIMA) and Long short-term memory (LSTM) models to predict the outbreak of Covid-19 in the upcoming 2 months in Morocco. In this work, we measured the effective reproduction number using the real data and also the fitted forecasted data produced by the two used approaches, to reveal how effective the measures taken by the Moroccan government have been controlling the Covid-19 outbreak. The prediction results for the next 2 months show a strong evolution in the number of confirmed and death cases in Morocco. According to the measures of the effective reproduction number, the transmissibility of the disease will continue to expand in the next 2 months, but fortunately, the higher value of the effective reproduction number is not considered to be dramatic and, therefore, may give hope for controlling the disease.

SIMLR: Machine Learning inside the SIR Model for COVID-19 Forecasting

Accurate forecasts of the number of newly infected people during an epidemic are critical for making effective timely decisions. This paper addresses this challenge using the SIMLR model, which incorporates machine learning (ML) into the epidemiological SIR model. For each region, SIMLR tracks the changes in the policies implemented at the government level, which it uses to estimate the time-varying parameters of an SIR model for forecasting the number of new infections one to four weeks in advance. It also forecasts the probability of changes in those government policies at each of these future times, which is essential for the longer-range forecasts. We applied SIMLR to data from in Canada and the United States, and show that its mean average percentage error is as good as state-of-the-art forecasting models, with the added advantage of being an interpretable model. We expect that this approach will be useful not only for forecasting COVID-19 infections, but also in predicting the evolution of other infectious diseases.

Multi-criteria text mining model for COVID-19 testing reasons and symptoms and temporal predictive model for COVID-19 test results in rural communities

This study is conducted to build a multi-criteria text mining model for COVID-19 testing reasons and symptoms. The model is integrated with a temporal predictive classification model for COVID-19 test results in rural underserved areas. A dataset of 6895 testing appointments and 14 features is used in this study. The text mining model classifies the notes related to the testing reasons and reported symptoms into one or more categories using look-up wordlists and a multi-criteria mapping process. The model converts an unstructured feature to a categorical feature that is used in building the temporal predictive classification model for COVID-19 test results and conducting some population analytics. The classification model is a temporal model (ordered and indexed by testing date) that uses machine learning classifiers to predict test results that are either positive or negative. Two types of classifiers and performance measures that include balanced and regular methods are used: (1) balanced random forest and (2) balanced bagged decision tree. The balanced or weighted methods are used to address and account for the biased and imbalanced dataset and to ensure correct detection of patients with COVID-19 (minority class). The model is tested in two stages using validation and testing sets to ensure robustness and reliability. The balanced classifiers outperformed regular classifiers using the balanced performance measures (balanced accuracy and G-score), which means the balanced classifiers are better at detecting patients with positive COVID-19 results. The balanced random forest achieved the best average balanced accuracy (86.1%) and G-score (86.1%) using the validation set. The balanced bagged decision tree achieved the best average balanced accuracy (83.0%) and G-score (82.8%) using the testing set. Also, it was found that the patient history, age, testing reasons, and time are the key features to classify the testing results.

A new hybrid prediction model of cumulative COVID-19 confirmed data

Establishing an accurate and efficient prediction model is of great significance for governments and other social organizations to formulate prevention and control policies and curb the explosive spread of the pandemic. To improve prediction accuracy of cumulative COVID-19 confirmed data, a new hybrid prediction model based on gradient-based optimizer variational mode decomposition (GVMD), extreme learning machine (ELM), and autoregressive integrated moving average (ARIMA), named GVMD-ELM-ARIMA, is proposed. To solve the problem of selecting the k value and the penalty factor α in variational mode decomposition (VMD), this paper proposes gradient-based optimizer variational mode decomposition (GVMD), which realizes the self-adaptive determination of k value and α value. Firstly, GVMD decomposes the cumulative COVID-19 confirmed data into some intrinsic mode functions (IMFs) and a residual component (IMFr). Secondly, IMFs are predicted by ELM. Then, IMFr is predicted by ARIMA. Finally, the final prediction results are obtained by reconstructing the prediction result of IMFs and IMFr. The cumulative COVID-19 confirmed data of the United States, India and Russia is used to verify its effectiveness. Taking the United States as an example, compared with the average MAPE, RMSE and MAE of the single model, the average MAPE of the hybrid model is reduced by 47.27%, the average RMSE is reduced by 44.50%, and the average MAE is reduced by 55.34%. Compared with GVMD-ELM-ELM, GVMD-ELM-ARIMA proposed in this paper reduces the MAPE by 60%, the RMSE by 56.85%, and the MAE by 61.61%. The experimental results show that GVMD-ELM-ARIMA has best prediction accuracy, and it provides a new method for predicting the cumulative COVID-19 confirmed data.

COVID-19: prediction, screening, and decision-making

In this chapter, we mainly focus on the use of AI-driven tools for COVID-19 predictive modeling, screening, and decision-making. We first discuss prediction models, their merits, and pitfalls. We then review deep learning models for COVID-19 detection and/or screening (with experiments) by taking different dataset sizes into account, which is followed by a conclusive study on how big data is big. The chapter provides a journey of deep neural networks for lung abnormality screening, where we consider COVID-19 as a particular case.

Spatiotemporal prediction of COVID-19 cases using inter- and intra-county proxies of human interactions

Measurements of human interaction through proxies such as social connectedness or movement patterns have proved useful for predictive modeling of COVID-19, which is a challenging task, especially at high spatial resolutions. In this study, we develop a Spatiotemporal autoregressive model to predict county-level new cases of COVID-19 in the coterminous US using spatiotemporal lags of infection rates, human interactions, human mobility, and socioeconomic composition of counties as predictive features. We capture human interactions through 1) Facebook- and 2) cell phone-derived measures of connectivity and human mobility, and use them in two separate models for predicting county-level new cases of COVID-19. We evaluate the model on 14 forecast dates between 2020/10/25 and 2021/01/24 over one- to four-week prediction horizons. Comparing our predictions with a Baseline model developed by the COVID-19 Forecast Hub indicates an average 6.46% improvement in prediction Mean Absolute Errors (MAE) over the two-week prediction horizon up to 20.22% improvement in the four-week prediction horizon, pointing to the strong predictive power of our model in the longer prediction horizons.

Decision Intelligence for Nationwide Ventilator Allocation During the COVID-19 Pandemic

Many states in the U.S. have faced shortages of medical resources because of the surge in the number of patients suffering from COVID-19. As many projections indicate, the situation will be far worse in coming months. The upcoming challenge is not only due to the exponential growth in cases but also because of inherent uncertainty and lags associated with disease progression. In this paper, we present a collection of models for decision intelligence which provide decision-support for ventilator allocation based on predictions from well-accepted oracles of disease progression. It is clear from our study that without coordination among states, there is a very high risk of ventilator shortages in certain states. However, such shortages can be reduced, provided neighboring states agree to share ventilators as suggested by our models. We show that despite the explosive growth in cases and associated uncertainty in ventilator demand, our simulation results hold the promise of reducing unmet demand, even in the face of significant uncertainty. This paper also provides the first evidence that coordination between neighboring states can lead to significant reduction in ventilator shortages across the U.S.