For the novel coronavirus disease 2019 (COVID-19), predictive modeling, in the literature, uses broadly susceptible exposed infected recoverd (SEIR)/SIR, agent-based, curve-fitting models. Governments and legislative bodies rely on insights from prediction models to suggest new policies and to assess the effectiveness of enforced policies. Therefore, access to accurate outbreak prediction models is essential to obtain insights into the likely spread and consequences of infectious diseases. The objective of this study is to predict the future COVID-19 situation of Korea. Here, we employed 5 models for this analysis; SEIR, local linear regression (LLR), negative binomial (NB) regression, segment Poisson, deep-learning based long short-term memory models (LSTM) and tree based gradient boosting machine (GBM). After prediction, model performance comparison was evelauated using relative mean squared errors (RMSE) for two sets of train (January 20, 2020‒December 31, 2020 and January 20, 2020‒January 31, 2021) and testing data (January 1, 2021‒February 28, 2021 and February 1, 2021‒February 28, 2021) . Except for segmented Poisson model, the other models predicted a decline in the daily confirmed cases in the country for the coming future. RMSE values’ comparison showed that LLR, GBM, SEIR, NB, and LSTM respectively, performed well in the forecasting of the pandemic situation of the country. A good understanding of the epidemic dynamics would greatly enhance the control and prevention of COVID-19 and other infectious diseases. Therefore, with increasing daily confirmed cases since this year, these results could help in the pandemic response by informing decisions about planning, resource allocation, and decision concerning social distancing policies.

For the novel coronavirus disease 2019 (COVID-19), predictive modeling, in the literature, uses broadly susceptible exposed infected recoverd (SEIR)/SIR, agent-based, curve-fitting models. Governments and legislative bodies rely on insights from prediction models to suggest new policies and to assess the effectiveness of enforced policies. Therefore, access to accurate outbreak prediction models is essential to obtain insights into the likely spread and consequences of infectious diseases. The objective of this study is to predict the future COVID-19 situation of Korea. Here, we employed 5 models for this analysis; SEIR, local linear regression (LLR), negative binomial (NB) regression, segment Poisson, deep-learning based long short-term memory models (LSTM) and tree based gradient boosting machine (GBM). After prediction, model performance comparison was evelauated using relative mean squared errors (RMSE) for two sets of train (January 20, 2020‒December 31, 2020 and January 20, 2020‒January 31, 2021) and testing data (January 1, 2021‒February 28, 2021 and February 1, 2021‒February 28, 2021) . Except for segmented Poisson model, the other models predicted a decline in the daily confirmed cases in the country for the coming future. RMSE values’ comparison showed that LLR, GBM, SEIR, NB, and LSTM respectively, performed well in the forecasting of the pandemic situation of the country. A good understanding of the epidemic dynamics would greatly enhance the control and prevention of COVID-19 and other infectious diseases. Therefore, with increasing daily confirmed cases since this year, these results could help in the pandemic response by informing decisions about planning, resource allocation, and decision concerning social distancing policies.

Background: Currently, little is known about the relationship between the temporal radiographic latent trajectories, which are based on the extent of coronavirus disease 2019 (COVID-19) pneumonia and clinical outcomes. This study aimed to elucidate the differences in the temporal trends of critical laboratory biomarkers, utilization of critical care support, and clinical outcomes according to temporal radiographic latent trajectories. Methods: We enrolled 2,385 patients who were hospitalized with COVID-19 and underwent serial chest radiographs from December 2019 to March 2022. The extent of radiographic pneumonia was quantified as a percentage using a previously developed deep-learning algorithm. A latent class growth model was used to identify the trajectories of the longitudinal changes of COVID-19 pneumonia extents during hospitalization. We investigated the differences in the temporal trends of critical laboratory biomarkers among the temporal radiographic trajectory groups. Cox regression analyses were conducted to investigate differences in the utilization of critical care supports and clinical outcomes among the temporal radiographic trajectory groups. Results: The mean age of the enrolled patients was 58.0 ± 16.9 years old, with 1,149 (48.2%) being male. Radiographic pneumonia trajectories were classified into three groups: The steady group (n = 1,925, 80.7%) exhibited stable minimal pneumonia, the downhill group (n = 135, 5.7%) exhibited initial worsening followed by improving pneumonia, and the uphill group (n = 325, 13.6%) exhibited progressive deterioration of pneumonia. There were distinct differences in the patterns of temporal blood urea nitrogen (BUN) and C-reactive protein (CRP) levels between the uphill group and the other two groups. Cox regression analyses revealed that the hazard ratios (HRs) for the need for critical care support and the risk of intensive care unit admission were significantly higher in both the downhill and uphill groups compared to the steady group. However, regarding in-hospital mortality, only the uphill group demonstrated a significantly higher risk than the steady group (HR, 8.2; 95% confidence interval, 3.08–21.98). Conclusion Stratified pneumonia trajectories, identified through serial chest radiographs, are linked to different patterns of temporal changes in BUN and CRP levels. These changes can predict the need for critical care support and clinical outcomes in COVID-19 pneumonia.Appropriate therapeutic strategies should be tailored based on these disease trajectories.

Background: Currently, little is known about the relationship between the temporal radiographic latent trajectories, which are based on the extent of coronavirus disease 2019 (COVID-19) pneumonia and clinical outcomes. This study aimed to elucidate the differences in the temporal trends of critical laboratory biomarkers, utilization of critical care support, and clinical outcomes according to temporal radiographic latent trajectories. Methods: We enrolled 2,385 patients who were hospitalized with COVID-19 and underwent serial chest radiographs from December 2019 to March 2022. The extent of radiographic pneumonia was quantified as a percentage using a previously developed deep-learning algorithm. A latent class growth model was used to identify the trajectories of the longitudinal changes of COVID-19 pneumonia extents during hospitalization. We investigated the differences in the temporal trends of critical laboratory biomarkers among the temporal radiographic trajectory groups. Cox regression analyses were conducted to investigate differences in the utilization of critical care supports and clinical outcomes among the temporal radiographic trajectory groups. Results: The mean age of the enrolled patients was 58.0 ± 16.9 years old, with 1,149 (48.2%) being male. Radiographic pneumonia trajectories were classified into three groups: The steady group (n = 1,925, 80.7%) exhibited stable minimal pneumonia, the downhill group (n = 135, 5.7%) exhibited initial worsening followed by improving pneumonia, and the uphill group (n = 325, 13.6%) exhibited progressive deterioration of pneumonia. There were distinct differences in the patterns of temporal blood urea nitrogen (BUN) and C-reactive protein (CRP) levels between the uphill group and the other two groups. Cox regression analyses revealed that the hazard ratios (HRs) for the need for critical care support and the risk of intensive care unit admission were significantly higher in both the downhill and uphill groups compared to the steady group. However, regarding in-hospital mortality, only the uphill group demonstrated a significantly higher risk than the steady group (HR, 8.2; 95% confidence interval, 3.08–21.98). Conclusion Stratified pneumonia trajectories, identified through serial chest radiographs, are linked to different patterns of temporal changes in BUN and CRP levels. These changes can predict the need for critical care support and clinical outcomes in COVID-19 pneumonia.Appropriate therapeutic strategies should be tailored based on these disease trajectories.

Background: Currently, little is known about the relationship between the temporal radiographic latent trajectories, which are based on the extent of coronavirus disease 2019 (COVID-19) pneumonia and clinical outcomes. This study aimed to elucidate the differences in the temporal trends of critical laboratory biomarkers, utilization of critical care support, and clinical outcomes according to temporal radiographic latent trajectories. Methods: We enrolled 2,385 patients who were hospitalized with COVID-19 and underwent serial chest radiographs from December 2019 to March 2022. The extent of radiographic pneumonia was quantified as a percentage using a previously developed deep-learning algorithm. A latent class growth model was used to identify the trajectories of the longitudinal changes of COVID-19 pneumonia extents during hospitalization. We investigated the differences in the temporal trends of critical laboratory biomarkers among the temporal radiographic trajectory groups. Cox regression analyses were conducted to investigate differences in the utilization of critical care supports and clinical outcomes among the temporal radiographic trajectory groups. Results: The mean age of the enrolled patients was 58.0 ± 16.9 years old, with 1,149 (48.2%) being male. Radiographic pneumonia trajectories were classified into three groups: The steady group (n = 1,925, 80.7%) exhibited stable minimal pneumonia, the downhill group (n = 135, 5.7%) exhibited initial worsening followed by improving pneumonia, and the uphill group (n = 325, 13.6%) exhibited progressive deterioration of pneumonia. There were distinct differences in the patterns of temporal blood urea nitrogen (BUN) and C-reactive protein (CRP) levels between the uphill group and the other two groups. Cox regression analyses revealed that the hazard ratios (HRs) for the need for critical care support and the risk of intensive care unit admission were significantly higher in both the downhill and uphill groups compared to the steady group. However, regarding in-hospital mortality, only the uphill group demonstrated a significantly higher risk than the steady group (HR, 8.2; 95% confidence interval, 3.08–21.98). Conclusion Stratified pneumonia trajectories, identified through serial chest radiographs, are linked to different patterns of temporal changes in BUN and CRP levels. These changes can predict the need for critical care support and clinical outcomes in COVID-19 pneumonia.Appropriate therapeutic strategies should be tailored based on these disease trajectories.

Background: Currently, little is known about the relationship between the temporal radiographic latent trajectories, which are based on the extent of coronavirus disease 2019 (COVID-19) pneumonia and clinical outcomes. This study aimed to elucidate the differences in the temporal trends of critical laboratory biomarkers, utilization of critical care support, and clinical outcomes according to temporal radiographic latent trajectories. Methods: We enrolled 2,385 patients who were hospitalized with COVID-19 and underwent serial chest radiographs from December 2019 to March 2022. The extent of radiographic pneumonia was quantified as a percentage using a previously developed deep-learning algorithm. A latent class growth model was used to identify the trajectories of the longitudinal changes of COVID-19 pneumonia extents during hospitalization. We investigated the differences in the temporal trends of critical laboratory biomarkers among the temporal radiographic trajectory groups. Cox regression analyses were conducted to investigate differences in the utilization of critical care supports and clinical outcomes among the temporal radiographic trajectory groups. Results: The mean age of the enrolled patients was 58.0 ± 16.9 years old, with 1,149 (48.2%) being male. Radiographic pneumonia trajectories were classified into three groups: The steady group (n = 1,925, 80.7%) exhibited stable minimal pneumonia, the downhill group (n = 135, 5.7%) exhibited initial worsening followed by improving pneumonia, and the uphill group (n = 325, 13.6%) exhibited progressive deterioration of pneumonia. There were distinct differences in the patterns of temporal blood urea nitrogen (BUN) and C-reactive protein (CRP) levels between the uphill group and the other two groups. Cox regression analyses revealed that the hazard ratios (HRs) for the need for critical care support and the risk of intensive care unit admission were significantly higher in both the downhill and uphill groups compared to the steady group. However, regarding in-hospital mortality, only the uphill group demonstrated a significantly higher risk than the steady group (HR, 8.2; 95% confidence interval, 3.08–21.98). Conclusion Stratified pneumonia trajectories, identified through serial chest radiographs, are linked to different patterns of temporal changes in BUN and CRP levels. These changes can predict the need for critical care support and clinical outcomes in COVID-19 pneumonia.Appropriate therapeutic strategies should be tailored based on these disease trajectories.