Forecasting COVID-19 cases by assessing control-intervention effects in Republic of Korea: A statistical modeling approach

Detection of COVID-19 epidemic outbreak using machine learning

Background

The coronavirus disease (COVID-19) pandemic has spread rapidly across the world, creating an urgent need for predictive models that can help healthcare providers prepare and respond to outbreaks more quickly and effectively, and ultimately improve patient care. Early detection and warning systems are crucial for preventing and controlling epidemic spread.

Objective

In this study, we aimed to propose a machine learning-based method to predict the transmission trend of COVID-19 and a new approach to detect the start time of new outbreaks by analyzing epidemiological data.

Methods

We developed a risk index to measure the change in the transmission trend. We applied machine learning (ML) techniques to predict COVID-19 transmission trends, categorized into three labels: decrease (L0), maintain (L1), and increase (L2). We used Support Vector Machine (SVM), Random Forest (RF), and XGBoost (XGB) as ML models. We employed grid search methods to determine the optimal hyperparameters for these three models. We proposed a new method to detect the start time of new outbreaks based on label 2, which was sustained for at least 14 days (i.e., the duration of maintenance). We compared the performance of different ML models to identify the most accurate approach for outbreak detection. We conducted sensitivity analysis for the duration of maintenance between 7 days and 28 days.

Results

ML methods demonstrated high accuracy (over 94%) in estimating the classification of the transmission trends. Our proposed method successfully predicted the start time of new outbreaks, enabling us to detect a total of seven estimated outbreaks, while there were five reported outbreaks between March 2020 and October 2022 in Korea. It means that our method could detect minor outbreaks. Among the ML models, the RF and XGB classifiers exhibited the highest accuracy in outbreak detection.

Conclusion

The study highlights the strength of our method in accurately predicting the timing of an outbreak using an interpretable and explainable approach. It could provide a standard for predicting the start time of new outbreaks and detecting future transmission trends. This method can contribute to the development of targeted prevention and control measures and enhance resource management during the pandemic.

Cost-effectiveness analysis of COVID-19 variants effects in an age-structured model

This study analyzes the impact of COVID-19 variants on cost-effectiveness across age groups, considering vaccination efforts and nonpharmaceutical interventions in Republic of Korea. We aim to assess the costs needed to reduce COVID-19 cases and deaths using age-structured model. The proposed age-structured model analyzes COVID-19 transmission dynamics, evaluates vaccination effectiveness, and assesses the impact of the Delta and Omicron variants. The model is fitted using data from the Republic of Korea between February 2021 and November 2022. The cost-effectiveness of interventions, medical costs, and the cost of death for different age groups are evaluated through analysis. The impact of different variants on cases and deaths is also analyzed, with the Omicron variant increasing transmission rates and decreasing case-fatality rates compared to the Delta variant. The cost of interventions and deaths is higher for older age groups during both outbreaks, with the Omicron outbreak resulting in a higher overall cost due to increased medical costs and interventions. This analysis shows that the daily cost per person for both the Delta and Omicron variants falls within a similar range of approximately $10-$35. This highlights the importance of conducting cost-effect analyses when evaluating the impact of COVID-19 variants.

Improved autoregressive integrated moving average model for COVID-19 prediction by using statistical significance and clustering techniques

Purpose

The COVID-19 pandemic has affected more than 192 countries. The condition results in a respiratory illness (e.g., influenza) with signs and symptoms such as cold, cough, fever, and breathing difficulties. Predicting new instances of COVID-19 is always a challenging task.

Methods

This study improved the autoregressive integrated moving average (ARIMA)-based time series prediction model by incorporating statistical significance for feature selection and k-means clustering for outlier detection. The accuracy of the improved model (ARIMAI) was examined using World Health Organization's official data on the COVID-19 pandemic worldwide and compared with that of many modern, cutting-edge algorithms.

Results

The ARIMAI model (RSS score = 0.279, accuracy = 97.75%) outperformed the current ARIMA model (RSS score = 0.659, accuracy = 93%).

Conclusions

The ARIMAI model is not only an efficient but also a rapid and simple technique to forecast COVID-19 trends. The usage of this model enables the prediction of any disease that will affect patients in the future pandemics.

Mathematical Modeling of COVID-19 Transmission and Intervention in South Korea: A Review of Literature

South Korea implemented interventions to curb the spread of the novel coronavirus disease 2019 (COVID-19) pandemic with discovery of the first case in early 2020. Mathematical modeling designed to reflect the dynamics of disease transmission has been shown to be an important tool for responding to COVID-19. This study aimed to review publications on the structure, method, and role of mathematical models focusing on COVID-19 transmission dynamics in Korea. In total, 42 papers published between August 7, 2020 and August 21, 2022 were studied and reviewed. This study highlights the construction and utilization of mathematical models to help craft strategies for predicting the course of an epidemic and evaluating the effectiveness of control strategies. Despite the limitations caused by a lack of available epidemiological and surveillance data, modeling studies could contribute to providing scientific evidence for policymaking by simulating various scenarios.

Predicting COVID-19 future trends for different European countries using Pearson correlation

The ability to accurately forecast the number of COVID-19 cases and future case trends would certainly assist governments and various organisations in strategising and preparing for the newly infected cases well in advance. Many predictions have failed to foresee future COVID-19 cases due to the lack of reliable data; however, such data are now widely available for predicting future trends in COVID-19 after more than one and a half years of the pandemic. Also, various countries are closely monitoring other countries that are experiencing a surge in COVID-19 cases in the expectation of similar scenarios, but this does not always produce correct results, as no research has identified specific correlations between different countries in terms of COVID-19 cases. During the past 18 months, many nations have watched countries whose COVID-19 cases have risen sharply, in anticipation of handling the situation themselves. However, this did not provide accurate results, as no research was conducted that compared countries to determine if their COVID-19 case trends were correlated. As official data on COVID-19 cases has become increasingly available, using the Pearson correlation technique to pinpoint the countries that should be closely monitored will help governments plan and prepare for the number of infections that are expected in the future at an early stage. In this study, a simple and real-time prediction of COVID-19 cases incorporating existing variables of coronavirus variants was used to explore the correlation among different European countries in terms of the number of COVID-19 cases officially recorded on a daily basis. Data from selected countries over the past 76 weeks were analysed using a Pearson correlation technique to determine if there were correlations between case trends and geographical position. The correlation coefficient (r) was employed for identifying whether the different countries in Europe were interrelated, with r > 0.85 indicating they were very strongly correlated, 0.85 > r > 0.8 indicating that they were strongly correlated, 0.8 > r > 0.7 indicating that they were moderately correlated, and r < 0.7 indicating that the examined countries were either weakly correlated or that a correlation did not exist. The results showed that although some neighbouring countries are strongly correlated, other countries that are not geographically close are also correlated. In addition, some countries on opposite sides of Europe (Belgium and Armenia) are also correlated. Other countries (France, Iceland, Israel, Kosovo, San Marino, Spain, Sweden and Turkey) were either weakly correlated or had no relationship at all.