Predict COVID-19 Case Research Articles

Analyzing the Relationship Between COVID-19 and Sociodemographic and Environmental Factors: A Case Study in Toronto

COVID-19 has disproportionately impacted communities based on sociodemographic and environmental factors. Previous studies have largely focused on traditional statistical models to investigate these disparities with limited attention to within-city variations. This research addresses this gap by employing advanced machine learning models to predict COVID-19 case counts at the neighborhood level within Toronto. Using algorithms such as Support Vector Regression, Random Forest, Gradient Boosting, and XGBoost, along with SHAP (SHapley Additive exPlanations) analysis, we identify key factors impacting COVID-19 transmission, including air pollution, socioeconomic status, and racialized group membership. Our results demonstrate that sociodemographic factors significantly influence sporadic cases, while environmental factors, particularly air pollutants, are critical in outbreak cases. This study highlights the value of machine learning in understanding complex interactions between risk factors with implications for targeted public health interventions to mitigate COVID-19 disparities.

Predicting COVID-19 Cases in Nursing Homes of California and Ohio: Does the Work Environment Matter?

The cross-sectional study evaluates if the prepandemic work environments in nursing homes predict coronavirus disease 2019 (COVID-19) cases among residents and staff, accounting for other factors. Leveraging data from a survey of California and Ohio nursing homes (n = 340), we examined if Workplace Integrated Safety and Health domains - Leadership, Participation, and Comprehensive and Collaborative Strategies predicted cumulative COVID-19 cases among nursing home residents and staff. In Ohio, a 1-unit increase in Leadership score was associated with 2 fewer staff cases and 4 fewer resident cases. A 1-unit increase in Comprehensive and Collaborative Strategies score in California showed an average marginal effect of approximately 1 less staff case and 2 fewer resident cases. These findings suggest that leadership commitment and interdepartment collaboration to prioritize worker safety may have protected against COVID-19 cases in nursing homes.

Comparative analyses of SARS-CoV-2 RNA concentrations in Detroit wastewater quantified with CDC N1, N2, and SC2 assays reveal optimal target for predicting COVID-19 cases

To monitor COVID-19 through wastewater surveillance, global researchers dedicated significant endeavors and resources to develop and implement diverse RT-qPCR or RT-ddPCR assays targeting different genes of SARS-CoV-2. Effective wastewater surveillance hinges on the appropriate selection of the most suitable assay, especially for resource-constrained regions where scant technical and socioeconomic resources restrict the options for testing with multiple assays. Further research is imperative to evaluate the existing assays through comprehensive comparative analyses. Such analyses are crucial for health agencies and wastewater surveillance practitioners in the selection of appropriate methods for monitoring COVID-19. In this study, untreated wastewater samples were collected weekly from the Detroit wastewater treatment plant, Michigan, USA, between January and December 2023. Polyethylene glycol precipitation (PEG) was applied to concentrate the samples followed by RNA extraction and RT-ddPCR. Three assays including N1, N2 (US CDC Real-Time Reverse Transcription PCR Panel for Detection of SARS-CoV-2), and SC2 assay (US CDC Influenza SARS-CoV-2 Multiplex Assay) were implemented to detect SARS-CoV-2 in wastewater. The limit of blank and limit of detection for the three assays were experimentally determined. SARS-CoV-2 RNA concentrations were evaluated and compared through three statistical approaches, including Pearson and Spearman's rank correlations, Dynamic Time Warping, and vector autoregressive models. N1 and N2 demonstrated the highest correlation and most similar time series patterns. Conversely, N2 and SC2 assay demonstrated the lowest correlation and least similar time series patterns. N2 was identified as the optimal target to predict COVID-19 cases. This study presents a rigorous effort in evaluating and comparing SARS-CoV-2 RNA concentrations quantified with N1, N2, and SC2 assays and their interrelations and correlations with clinical cases. This study provides valuable insights into identifying the optimal target for monitoring COVID-19 through wastewater surveillance.

Network-based time series modeling for COVID-19 incidence in the Republic of Ireland

Network-based time series models have experienced a surge in popularity over the past years due to their ability to model temporal and spatial dependencies, arising from the spread of infectious disease. The generalised network autoregressive (GNAR) model conceptualises time series on the vertices of a network; it has an autoregressive component for temporal dependence and a spatial autoregressive component for dependence between neighbouring vertices in the network. Consequently, the choice of underlying network is essential. This paper assesses the performance of GNAR models on different networks in predicting COVID-19 cases for the 26 counties in the Republic of Ireland, over two distinct pandemic phases (restricted and unrestricted), characterised by inter-county movement restrictions. Ten static networks are constructed, in which vertices represent counties, and edges are built upon neighbourhood relations, such as railway lines. We find that a GNAR model based on the fairly sparse Economic hub network explains the data best for the restricted pandemic phase while the fairly dense 21-nearest neighbour network performs best for the unrestricted phase. Across phases, GNAR models have higher predictive accuracy than standard ARIMA models which ignore the network structure. For county-specific predictions, in pandemic phases with more lenient or no COVID-19 regulation, the network effect is not quite as pronounced. The results indicate some robustness to the precise network architecture as long as the densities of the networks are similar. An analysis of the residuals justifies the model assumptions for the restricted phase but raises questions regarding their validity for the unrestricted phase. While generally performing better than ARIMA models which ignore network effects, there is scope for further development of the GNAR model to better model complex infectious diseases, including COVID-19.

A Comprehensive Analysis of various Covid-19 Detection and Pandemic Prevention Systems and Methods Using Data Science

Abstract: The paper proposes a technique for early Covid-19 test prediction using AI and data science. The study analyzes various data sources to understand the patterns and trends of the pandemic and the impact of various interventions on the spread of the virus. The proposed system integrates data from multiple sources to identify potential cases and can also track the spread of the virus in real-time. The system has high accuracy in predicting positive cases and has the potential to improve our ability to detect and predict Covid-19 cases, ultimately saving lives and reducing the economic impact of the pandemic. The proposed technique for early Covid-19 test prediction using AI and data science can be a game- changer in our fight against the pandemic. With the integration of multiple data sources, including individual health records, social media, and geographic data, the system can identify potential cases even before symptoms appear. This early detection can help individuals get timely medical attention and prevent the spread of the virus to others.

Long short-term memory model for COVID-19 forecasting

Every time new variants of COVID-19, back to the pandemic, could bring massive loss to human society and traditional models have failed to catch the complexities of COVID-19. Thus, to handle the unpredictable challenges posed by the dynamic nature of COVID-19, Long Short-Term Memory (LSTM) models were utilized to make accurate short and long-term predictions about different variants and prepare the model for another variant or virus similar to COVID-19 by learning the data of different COVID-19 variants. The dataset, sourced from owid-covid-data, is cleaned and divided into original, alpha, delta, and mixed variants in the United States from March 1, 2020, to April 30, 2022. MSE, RMSE, MAE, and R2 are used to compare the difference between real and predicted values to evaluate how accurately the model performs. Results demonstrate the model excels in long-term and short-term predicting COVID-19 cases and deaths for various variants, and mixed variants even promote accuracy. Thus, the proposed LSTM model shows promise for infectious disease forecasting, providing a foundation for anticipating future outbreaks to help policymakers make better decisions or early prevention.

Predicting COVID-19 Cases and Deaths Utilizing Hygiene Hypothesis Surrogate Factors: A Global Analysis

Predicting COVID-19 Cases and Deaths Utilizing Hygiene Hypothesis Surrogate Factors: A Global Analysis

An Adaptive Research Approach to COVID-19 Forecasting for Regional Health Systems in England

A team of researchers worked with public health officials and clinical decision makers to create real-time models to help predict COVID-19 cases and hospital bed needs in the East of England. These models used up-to-date data and allowed officials to explore different scenarios and make informed plans. The models have also been applied in other countries and can be a valuable tool in future epidemics.

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.

Predicting COVID-19 cases in Belo Horizonte-Brazil taking into account mobility and vaccination issues.

The pandemic caused millions of deaths around the world and forced governments to take drastic measures to reduce the spread of Coronavirus. Understanding the impact of social distancing measures on urban mobility and the number of COVID-19 cases allows governments to change public policies according to the evolution of the pandemic and plan ahead. Given the increasing rates of vaccination worldwide, immunization data may also represent an important predictor of COVID-19 cases. This study investigates the impact of urban mobility and vaccination upon COVID-19 cases in Belo Horizonte, Brazil using Prophet and ARIMA models to predict future outcomes. The developed models generated projections fairly close to real numbers, and some inferences were drawn through experimentation. Brazil became the epicenter of the COVID-19 epidemic shortly after the first case was officially registered on February 25th, 2020. In response, several municipalities adopted lockdown (total or partial) measures to minimize the risk of new infections. Here, we propose prediction models which take into account mobility and vaccination data to predict new COVID-19 cases.

Monitoring of over-the-counter (OTC) and COVID-19 treatment drugs complement wastewater surveillance of SARS-CoV-2

BackgroundThe application of wastewater-based epidemiology to track the outbreak and prevalence of coronavirus disease (COVID-19) in communities has been tested and validated by several researchers across the globe. However, the RNA-based surveillance has its inherent limitations and uncertainties.ObjectiveThis study aims to complement the ongoing wastewater surveillance efforts by analyzing other chemical biomarkers in wastewater to help assess community response (hospitalization and treatment) during the pandemic (2020–2021).MethodsWastewater samples (n = 183) were collected from the largest wastewater treatment facility in Suffolk County, NY, USA and analyzed for COVID-19 treatment drugs (remdesivir, chloroquine, and hydroxychloroquine (HCQ)) and their human metabolites. We additionally monitored 26 pharmaceuticals including common over-the-counter (OTC) drugs. Lastly, we developed a Bayesian model that uses viral RNA, COVID-19 treatment drugs, and pharmaceuticals data to predict the confirmed COVID-19 cases within the catchment area.ResultsThe viral RNA levels in wastewater tracked the actual COVID-19 case numbers well as expected. COVID-19 treatment drugs were detected with varying frequency (9–100%) partly due to their instability in wastewater. We observed a significant correlation (R = 0.30, p < 0.01) between the SARS-CoV-2 genes and desethylhydroxychloroquine (DHCQ, metabolite of HCQ). Remdesivir levels peaked immediately after the Emergency Use Authorization approved by the FDA. Although, 13 out of 26 pharmaceuticals assessed were consistently detected (DF = 100%, n = 111), only acetaminophen was significantly correlated with viral loads, especially when the Omicron variant was dominant. The Bayesian models were capable of reproducing the temporal trend of the confirmed cases.ImpactIn this study, for the first time, we measured COVID-19 treatment and pharmaceutical drugs and their metabolites in wastewater to complement ongoing COVID-19 viral RNA surveillance efforts. Our results highlighted that, although the COVID-19 treatment drugs were not very stable in wastewater, their detection matched with usage trends in the community. Acetaminophen, an OTC drug, was significantly correlated with viral loads and confirmed cases, especially when the Omicron variant was dominant. A Bayesian model was developed which could predict COVID-19 cases more accurately when incorporating other drugs data along with viral RNA levels in wastewater.

2308. Exploring the Seasonality of COVID-19 with Machine Learning: A Distinct Bimodal Pattern?

Abstract Background Respiratory viruses, such as influenza and RSV, occur annually during the winter season in temperate regions. It is essential to determine if SARS-CoV-2 exhibits seasonal patterns for public health planning and vaccination policies. Although winter spikes in COVID-19 cases have been observed, the higher transmissibility of SARS-CoV-2 suggests its seasonality may have a different pattern. Methods We plotted the time-series data on COVID-19, Influenza, and RSV from January 2020-February 2023 at Stanford Healthcare, to compare seasonal patterns. We then modeled predictions for COVID-19 cases in the United States for the next 913 days, using data from January 2020-February 2023. This data was split into a training set and a test set, then Facebook Prophet machine learning library was used to fit a model to the training set and generate forecasts for the test set and future time periods. Cross-validation of the model was performed by calculating the root mean squared error (RMSE) and mean absolute percentage error (MAPE). Results The time-series data of cases for Influenza, RSV, and COVID-19 were plotted from January 1, 2020, to February 28, 2023, revealing bimodal peaks for COVID-19 during the winter (December - February) and summer (July - September) months (Figure 1). This differed from the unimodal patterns observed for Influenza and RSV cases (Figures 2 and 3, respectively). The Prophet model for COVID-19 cases over the next 913 days in the United States demonstrated an additional peak during the summer months (Figure 4). However, other external factors that may influence seasonality, such as the stochastic development of new SARS-CoV-2 variants, weaning of immunity, and testing intensity were not modeled.Figure 1.COVID-19 time-series at Stanford Healthcare during January 2020–February 2023Time-series of COVID-19 cases demonstrates bimodal peaks during the winter (December - February) and summer (July - September) months.Figure 2.Influenza time-series at Stanford Healthcare during January 2020–February 2023Time-series of Influenza cases demonstrates one peak during the winter (December - February) months.Figure 3.RSV time-series at Stanford Healthcare during January 2020–February 2023Time-series of RSV cases demonstrates one peak during the winter (December - February) months. Conclusion COVID-19 may exhibit distinct bimodal seasonal patterns that are not observed for other respiratory viruses. Future public health interventions should consider the distinct seasonal patterns of COVID-19 when developing prevention and control strategies.Figure 4.Prophet Model forecasting COVID-19 peaks in the United States for the next 3 years Cross-validation results for the Prophet model's performance in predicting COVID-19 cases in the United States over a 5-day horizon. The model's RMSE was 110,342.81, indicating an average deviation from the actual values. The MAPE was 0.486, reflecting the model's average percentage error. The coverage was 0.35, indicating that the actual value fell within the 80% prediction interval of the model only 35% of the time, which may suggest limitations for longer-term forecasting. Disclosures All Authors: No reported disclosures

Unraveling COVID-19 Progression: A Comprehensive Com-parison of Advanced Deep Learning Methods for Precise Pre-dictions

The COVID-19 pandemic has significantly impacted the United Arab Emirates (UAE), necessitating effective and accurate forecasting tools to inform public health policies and strategies. This study presents a comparative analysis of advanced deep-learning models for predicting COVID-19 cases in the UAE. We investigate the performance of Long Short-Term Memory (LSTM), Bi-directional LSTM, Convolutional Neural Networks (CNN), CNN-LSTM, Multilayer perceptron, and Recurrent Neural Networks (RNN). The models are trained and evaluated using a comprehensive dataset of confirmed cases, demographic information, and relevant socio-economic indicators. The models are further optimized using a Bayesian optimizer and comparison is performed before and after the optimization of models. We have used predictive and perspective analytics on the COVID-19 dataset. Our research goal is to identify the most accurate and reliable model for forecasting COVID-19 cases in the region.&#x0D; The results demonstrate the effectiveness of these deep learning techniques in predicting COVID-19 cases, with each model exhibiting varying levels of accuracy and precision. A thorough and rigorous evaluation of the models' performances reveals the most suitable architecture for the UAE's specific context. This study contributes to the ongoing efforts to combat the pandemic by providing valuable insights into the application of advanced deep-learning models for accurate and timely COVID-19 case predictions. It was found that the RNN model performed the best without any optimization. The findings have significant implications for public health decision-making, enabling authorities to develop targeted and data-driven interventions to curb the spread of the virus and mitigate its impact on the UAE's population. This demonstrates the potential of deep learning algorithms in handling complex datasets and making accurate predictions which is a valuable capability to enhance accuracy in professional and healthcare environments.

A Natural Language Processing Model for COVID-19 Detection Based on Dutch General Practice Electronic Health Records by Using Bidirectional Encoder Representations From Transformers: Development and Validation Study.

Natural language processing (NLP) models such as bidirectional encoder representations from transformers (BERT) hold promise in revolutionizing disease identification from electronic health records (EHRs) by potentially enhancing efficiency and accuracy. However, their practical application in practice settings demands a comprehensive and multidisciplinary approach to development and validation. The COVID-19 pandemic highlighted challenges in disease identification due to limited testing availability and challenges in handling unstructured data. In the Netherlands, where general practitioners (GPs) serve as the first point of contact for health care, EHRs generated by these primary care providers contain a wealth of potentially valuable information. Nonetheless, the unstructured nature of free-text entries in EHRs poses challenges in identifying trends, detecting disease outbreaks, or accurately pinpointing COVID-19 cases. This study aims to develop and validate a BERT model for detecting COVID-19 consultations in general practice EHRs in the Netherlands. The BERT model was initially pretrained on Dutch language data and fine-tuned using a comprehensive EHR data set comprising confirmed COVID-19 GP consultations and non-COVID-19-related consultations. The data set was partitioned into a training and development set, and the model's performance was evaluated on an independent test set that served as the primary measure of its effectiveness in COVID-19 detection. To validate the final model, its performance was assessed through 3 approaches. First, external validation was applied on an EHR data set from a different geographic region in the Netherlands. Second, validation was conducted using results of polymerase chain reaction (PCR) test data obtained from municipal health services. Lastly, correlation between predicted outcomes and COVID-19-related hospitalizations in the Netherlands was assessed, encompassing the period around the outbreak of the pandemic in the Netherlands, that is, the period before widespread testing. The model development used 300,359 GP consultations. We developed a highly accurate model for COVID-19 consultations (accuracy 0.97, F1-score 0.90, precision 0.85, recall 0.85, specificity 0.99). External validations showed comparable high performance. Validation on PCR test data showed high recall but low precision and specificity. Validation using hospital data showed significant correlation between COVID-19 predictions of the model and COVID-19-related hospitalizations (F1-score 96.8; P<.001; R2=0.69). Most importantly, the model was able to predict COVID-19 cases weeks before the first confirmed case in the Netherlands. The developed BERT model was able to accurately identify COVID-19 cases among GP consultations even preceding confirmed cases. The validated efficacy of our BERT model highlights the potential of NLP models to identify disease outbreaks early, exemplifying the power of multidisciplinary efforts in harnessing technology for disease identification. Moreover, the implications of this study extend beyond COVID-19 and offer a blueprint for the early recognition of various illnesses, revealing that such models could revolutionize disease surveillance.

An interpretable time series machine learning method for varying forecast and nowcast lengths in wastewater-based epidemiology

Wastewater-based epidemiology has emerged as a viable tool for monitoring disease prevalence in a population. This paper details a time series machine learning (TSML) method for predicting COVID-19 cases from wastewater and environmental variables. The TSML method utilizes a number of techniques to create an interpretable, hypothesis-driven framework for machine learning that can handle different nowcast and forecast lengths. Some of the techniques employed include:•Feature engineering to construct interpretable features, like site-specific lead times, hypothesized to be potential predictors of COVID-19 cases.•Feature selection to identify features with the best predictive performance for the tasks of nowcasting and forecasting.•Prequential evaluation to prevent data leakage while evaluating the performance of the machine learning algorithm.

Univariate and Multivariate Long Short Term Memory (LSTM) Model to Predict Covid-19 Cases in Malaysia Using Integrated Meteorological Data

The rate of transmission of coronavirus disease (COVID-19) has been very fast since the first reported case in December 2019 in Wuhan, China. The disease has infected more than 3 million people worldwide and resulted in more than 224 thousand deaths as of May 1, 2020, reported by The World Health Organization (WHO). In the past, meteorological parameters such as temperature and humidity were essential and effective factors against serious infectious diseases such as influenza and Severe Acute Respiratory Syndrome (SARS). Therefore, exploring the relationship between meteorological factors and active COVID-19 cases is essential. This study employs the long-short term memory (LSTM) method to predict Covid-19 Cases in Malaysia. We propose a univariate and multivariate model using Covid-19 cases and meteorology data. The univariate LSTM model uses Covid-19 active cases data in a year as a control attribute for model development. The multivariate LSTM model uses the integrated Covid-19 cases, and meteorology data consists of attributes: minimum, maximum, and average values of Humidity, Temperature, Windspeed, and Pressure from 13 states of Malaysia. The model's performance is evaluated using errors such as MAE, RMSE, MAPE, and the R2 Score. The low errors and higher R2 score indicate the model's excellent performance. We observed that the univariate LSTM model gives the least error in five states, indicating that those states' daily active cases are the main contributing factors. In the multivariate LSTM model, the daily cases and humidity, temperature, and windspeed are the main factors in several different states. The result of the study is to help the government to prevent and manage the spread of the COVID-19 and other upcoming pandemic better.

Forecasting daily confirmed COVID-19 cases in Algeria using ARIMA models.

COVID-19 has become a threat worldwide, affecting every country. This study aimed to identify COVID-19 cases in Algeria using times series models for forecasting the disease. Confirmed COVID-19 daily cases data were obtained from 21 March 2020 to 26 November 2020 from the Algerian Ministry of Health. Forecasting was done using the Autoregressive Integrated Moving Average (ARIMA) models (0,1,1) with Minitab 17 software. Observed cases during the forecast period were accurately predicted and placed within prediction intervals generated by ARIMA. Forecasted values of COVID-19 positive cases, recoveries and deaths showed an accurate trend, which corresponded to actual cases reported during 252, 253 and 254 days. Results were strengthened by variations of less than 5% between forecast and observed cases in 100% of forecasted data. ARIMA models with optimally selected covariates are useful tools for predicting COVID-19 cases in Algeria.

Data-Driven Modeling and Analysis for COVID-19 Pandemic Hospital Beds Planning

The COVID-19 pandemic presents unprecedented challenges for the US healthcare system, and the critical care settings are heavily impacted by the pressures of caring for COVID-19 patients. However, hospital pandemic preparedness has been hampered by a lack of disease specific planning guidelines. In this paper, we proposed a holistic modeling and analysis approach, with a system dynamics model to predict COVID-19 cases and a discrete-event simulation to evaluate hospital bed utilization, to support the hospital planning decisions. Our model was trained using the public data from the JHU Coronavirus Resource Center and was validated using historical patient census data from the University of Florida Health Jacksonville, Jacksonville, FL and public data from the Florida Department of Health (FDOH). Various experiments were conducted to investigate different control measures and the variants of the virus and their impact on the disease transmission, and subsequently, the hospital planning needs. Our proposed approach can be tailored to a given hospital setting of interest and is also generalizable to other hospitals to tackle the pandemic planning challenge. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —We proposed a holistic modeling and analysis approach to support hospital preparedness and resource planning during the COVID-19 pandemic. To capture the highly dynamic pandemic environment, we developed a numerical method to estimate <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R_0$</tex-math> </inline-formula> , the effective basic reproductive rate, and used the most recent estimated data series of daily <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R_0$</tex-math> </inline-formula> to project the change in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R_0$</tex-math> </inline-formula> in a short-term forecast window. The prediction of the daily confirmed cases in that forecast window were then obtained based on recursively solving the system dynamics model, and was validated to be very close to the real confirmed cases from the public record. This data-driven approach allows us to gain a systematic understanding of the common trends across different states and regions, and to evaluate the effect of the control measures like the stay-at-home order and the impact of the virus variants on the disease transmission behavior. Furthermore, the dynamic prediction allows us to evaluate the hospital resource needs during different stages of the pandemic. The insights obtained through this effort shed light on the impact of interventions (e.g., vaccines and control measures) on the hospital preparedness to support appropriate hospital resource allocation.

Predicting COVID-19 Cases on a Large Chest X-Ray Dataset Using Modified Pre-trained CNN Architectures

Abstract The Coronavirus is a virus that spreads very quickly. Therefore, it has had very destructive effects in many areas worldwide. Because X-ray images are an easily accessible, fast, and inexpensive method, they are widely used worldwide to diagnose COVID-19. This study tried detecting COVID-19 from X-ray images using pre-trained VGG16, VGG19, InceptionV3, and Resnet50 CNN architectures and modified versions of these architectures. The fully connected layers of the pre-trained architectures have been reorganized in the modified CNN architectures. These architectures were trained on binary and three-class datasets, revealing their classification performance. The data set was collected from four different sources and consisted of 594 COVID-19, 1345 viral pneumonia, and 1341 normal X-ray images. Models are built using Tensorflow and Keras Libraries with Python programming language. Preprocessing was performed on the dataset by applying resizing, normalization, and one hot encoding operation. Model performances were evaluated according to many performance metrics such as recall, specificity, accuracy, precision, F1-score, confusion matrix, ROC analysis, etc., using 5-fold cross-validation. The highest classification performance was obtained in the modified VGG19 model with 99.84 % accuracy for binary classification (COVID-19 vs. Normal) and in the modified VGG16 model with 98.26 % accuracy for triple classification (COVID-19 vs. Pneumonia vs. Normal). These models have a higher accuracy rate than other studies in the literature. In addition, the number of COVID-19 X-ray images in the dataset used in this study is approximately two times higher than in other studies. Since it is obtained from different sources, it is irregular and does not have a standard. Despite this, it is noteworthy that higher classification performance was achieved than in previous studies. Modified VGG16 and VGG19 models (available at github.com/akaraci/LargeDatasetCovid19) can be used as an auxiliary tool in slight healthcare organizations’ shortage of specialists to detect COVID-19.

FORECASTING OF COVID–19 WITH AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA) METHOD IN EAST JAVA PROVINCE

Background: The COVID-19 pandemic has had a major impact on the world's health system, including Indonesia. The national health system is facing challenges with increasing cases of COVID-19. With the forecasting of COVID-19 cases, it is hoped that it can be one of the references in dealing with COVID-19 and one form of mitigation in dealing with COVID-19. Purpose: This research aims to predict COVID-19 cases in East Java Province for the coming year using the Autoregressive Integrated Moving Average (ARIMA) method based on patient data from March 2020 to January 2022. Methods: This type of research is analytic. Forecasting future COVID-19 cases using the Autoregressive Integrated Moving Average (ARIMA) method based on COVID-19 data from March 2020 to January 2022. Results: Based on the results of ARIMA analysis, the best forecasting model for confirmed cases of COVID-19 is the model (1:0:1) with AIC values ​​(14.22672), SIC (14.33357), while for cured cases is the model (1:2: 3) with the value of AIC (13.93054), SIC (13.03738), and for the case of death is the model (1:2:1) with the value of AIC (10.76105) and SIC (10.86790). Conclusion: From the results of this study, it is predicted that there will be an increase in COVID-19 cases in July 2022, January 2023 and June 2023.