Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study

Next-generation sequencing of host genetics risk factors associated with COVID-19 severity and long-COVID in Colombian population

Coronavirus disease 2019 (COVID-19) was considered a major public health burden worldwide. Multiple studies have shown that susceptibility to severe infections and the development of long-term symptoms is significantly influenced by viral and host factors. These findings have highlighted the potential of host genetic markers to identify high-risk individuals and develop target interventions to reduce morbimortality. Despite its importance, genetic host factors remain largely understudied in Latin-American populations. Using a case-control design and a custom next-generation sequencing (NGS) panel encompassing 81 genetic variants and 74 genes previously associated with COVID-19 severity and long-COVID, we analyzed 56 individuals with asymptomatic or mild COVID-19 and 56 severe and critical cases. In agreement with previous studies, our results support the association between several clinical variables, including male sex, obesity and common symptoms like cough and dyspnea, and severe COVID-19. Remarkably, thirteen genetic variants showed an association with COVID-19 severity. Among these variants, rs11385942 (p < 0.01; OR = 10.88; 95% CI = 1.36-86.51) located in the LZTFL1 gene, and rs35775079 (p = 0.02; OR = 8.53; 95% CI = 1.05-69.45) located in CCR3 showed the strongest associations. Various respiratory and systemic symptoms, along with the rs8178521 variant (p < 0.01; OR = 2.51; 95% CI = 1.27-4.94) in the IL10RB gene, were significantly associated with the presence of long-COVID. The results of the predictive model comparison showed that the mixed model, which incorporates genetic and non-genetic variables, outperforms clinical and genetic models. To our knowledge, this is the first study in Colombia and Latin-America proposing a predictive model for COVID-19 severity and long-COVID based on genomic analysis. Our study highlights the usefulness of genomic approaches to studying host genetic risk factors in specific populations. The methodology used allowed us to validate several genetic variants previously associated with COVID-19 severity and long-COVID. Finally, the integrated model illustrates the importance of considering genetic factors in precision medicine of infectious diseases.

Predicting COVID-19 severity: Challenges in reproducibility and deployment of machine learning methods

The increasing use of electronic health records (EHR) based computable phenotypes in clinical research is providing new opportunities for development of data-driven medical applications. Adopted widely in the United States and globally, EHRs facilitate systematic collection of patients' longitudinal information, which serves as one of the important foundations for artificial intelligence applications in medicine. Harmonization of input variables and outcome definitions is critically important for wider clinical applicability of artificial intelligence (AI) methodologies. In this review, we focused on Coronavirus Disease 2019 (COVID-19) severity machine learning prediction models and explored the pipeline for standardizing future disease severity model development using EHR information. We identified 2,967 studies published between 01/01/2020 and 02/15/2022 and selected 135 independent studies that had built machine learning prediction models to predict severity related outcomes of COVID-19 patients based on EHR data for the final review. These 135 studies spanning across 27 counties covered a broad range of severity related prediction outcomes. We observed substantial inconsistency in COVID-19 severity phenotype definitions among models in these studies. Moreover, there was a gap between the outcome of these models and clinician-recognized clinical concepts. Accordingly, we recommend that robust clinical input metrics, with outcome definitions which eliminate ambiguity in interpretation, to reduce algorithmic bias, mitigate model brittleness and improve generalizability of a universal model for COVID-19 severity. This framework can potentially be extended to broader clinical application.

Plasma metabolomics profiling identifies new predictive biomarkers for disease severity in COVID-19 patients

Recently, numerous studies have reported on different predictive models of disease severity in COVID-19 patients. Herein, we propose a highly predictive model of disease severity by integrating routine laboratory findings and plasma metabolites including cytosine as a potential biomarker of COVID-19 disease severity. One model was developed and internally validated on the basis of ROC-AUC values. The predictive accuracy of the model was 0.996 (95% CI: 0.989 to 1.000) with an optimal cut-off risk score of 3 from among 6 biomarkers including five lab findings (D-dimer, ferritin, neutrophil counts, Hp, and sTfR) and one metabolite (cytosine). The model is of high predictive power, needs a small number of variables that can be acquired at minimal cost and effort, and can be applied independent of non-empirical clinical data. The metabolomics profiling data and the modeling work stemming from it, as presented here, could further explain the cause of COVID-19 disease prognosis and patient management.

Risk factors for disease severity among children with Covid-19: a clinical prediction model

BACKGROUND

Children account for a significant proportion of COVID-19 hospitalizations, but data on the predictors of disease severity in children are limited. We aimed to identify risk factors associated with moderate/severe COVID-19 and develop a nomogram for predicting children with moderate/severe COVID-19.

METHODS

We identified children ≤ 12 years old hospitalized for COVID-19 across five hospitals in Negeri Sembilan, Malaysia, from 1 January 2021 to 31 December 2021 from the state's pediatric COVID-19 case registration system. The primary outcome was the development of moderate/severe COVID-19 during hospitalization. Multivariate logistic regression was performed to identify independent risk factors for moderate/severe COVID-19. A nomogram was constructed to predict moderate/severe disease. The model performance was evaluated using the area under the curve (AUC), sensitivity, specificity, and accuracy.

RESULTS

A total of 1,717 patients were included. After excluding the asymptomatic cases, 1,234 patients (1,023 mild cases and 211 moderate/severe cases) were used to develop the prediction model. Nine independent risk factors were identified, including the presence of at least one comorbidity, shortness of breath, vomiting, diarrhea, rash, seizures, temperature on arrival, chest recessions, and abnormal breath sounds. The nomogram's sensitivity, specificity, accuracy, and AUC for predicting moderate/severe COVID-19 were 58·1%, 80·5%, 76·8%, and 0·86 (95% CI, 0·79 - 0·92) respectively.

CONCLUSION

Our nomogram, which incorporated readily available clinical parameters, would be useful to facilitate individualized clinical decisions.

Hemogram-based decision tree models for discriminating COVID-19 from RSV in infants

OBJECTIVE

Decision trees are efficient and reliable decision-making algorithms, and medicine has reached its peak of interest in these methods during the current pandemic. Herein, we reported several decision tree algorithms for a rapid discrimination between coronavirus disease (COVID-19) and respiratory syncytial virus (RSV) infection in infants.

METHODS

A cross-sectional study was conducted on 77 infants: 33 infants with novel betacoronavirus (SARS-CoV-2) infection and 44 infants with RSV infection. In total, 23 hemogram-based instances were used to construct the decision tree models via 10-fold cross-validation method.

RESULTS

The Random forest model showed the highest accuracy (81.8%), while in terms of sensitivity (72.7%), specificity (88.6%), positive predictive value (82.8%), and negative predictive value (81.3%), the optimized forest model was the most superior one.

CONCLUSION

Random forest and optimized forest models might have significant clinical applications, helping to speed up decision-making when SARS-CoV-2 and RSV are suspected, prior to molecular genome sequencing and/or antigen testing.

Machine learning models to predict the maximum severity of COVID-19 based on initial hospitalization record

Background

As the worldwide spread of coronavirus disease 2019 (COVID-19) continues for a long time, early prediction of the maximum severity is required for effective treatment of each patient.

Objective

This study aimed to develop predictive models for the maximum severity of hospitalized COVID-19 patients using artificial intelligence (AI)/machine learning (ML) algorithms.

Methods

The medical records of 2,263 COVID-19 patients admitted to 10 hospitals in Daegu, Korea, from February 18, 2020, to May 19, 2020, were comprehensively reviewed. The maximum severity during hospitalization was divided into four groups according to the severity level: mild, moderate, severe, and critical. The patient's initial hospitalization records were used as predictors. The total dataset was randomly split into a training set and a testing set in a 2:1 ratio, taking into account the four maximum severity groups. Predictive models were developed using the training set and were evaluated using the testing set. Two approaches were performed: using four groups based on original severity levels groups (i.e., 4-group classification) and using two groups after regrouping the four severity level into two (i.e., binary classification). Three variable selection methods including randomForestSRC were performed. As AI/ML algorithms for 4-group classification, GUIDE and proportional odds model were used. For binary classification, we used five AI/ML algorithms, including deep neural network and GUIDE.

Results

Of the four maximum severity groups, the moderate group had the highest percentage (1,115 patients; 49.5%). As factors contributing to exacerbation of maximum severity, there were 25 statistically significant predictors through simple analysis of linear trends. As a result of model development, the following three models based on binary classification showed high predictive performance: (1) Mild vs. Above Moderate, (2) Below Moderate vs. Above Severe, and (3) Below Severe vs. Critical. The performance of these three binary models was evaluated using AUC values 0.883, 0.879, and, 0.887, respectively. Based on results for each of the three predictive models, we developed web-based nomograms for clinical use (http://statgen.snu.ac.kr/software/nomogramDaeguCovid/).

Conclusions

We successfully developed web-based nomograms predicting the maximum severity. These nomograms are expected to help plan an effective treatment for each patient in the clinical field.

Sex-Based Differences in Outcomes of Coronavirus Disease 2019 (COVID-19) in Korea

PURPOSE

This study examined the factors affecting mortality and clinical severity score (CSS) of male and female patients with Coronavirus Disease 2019 (COVID-19) using clinical epidemiological information provided by the Korea Disease Control and Prevention Agency.

METHODS

This is a retrospective observational cohort study. From January 21 to April 30, 2020, 5624 subjects who were released from quarantine or died were analyzed.

RESULTS

The factors influencing relsease or death that differed by sex were high heart rate and malignancy in males and chronic kidney disease in females. In addition, the factors influencing progression to severe CSS were high BMI (severe obesity) and rheumatic disease in males and high temperature, sputum production, absence of sore throat and headache, chronic kidney disease, malignancy, and chronic liver disease in females. Older age, low lymphocyte count and platelets, dyspnea, diabetes mellitus, dementia, and intensive care unit (ICU) admission affected mortality in all the patients, and older age, low lymphocyte count and platelets, fever, dyspnea, diabetes mellitus, dementia, and ICU admission affected progression to severe stage of CSS.

CONCLUSIONS

This study is expected to contribute to the general results by analyzing nationally representative data. The results of this study present an important basis for development of differentiated nursing and medical management strategies in consideration of factors that influence treatment effects and outcomes according to sex of COVID-19 patients.

The risk profile of patients with COVID-19 as predictors of lung lesions severity and mortality—Development and validation of a prediction model

Objective

We developed and validated a prediction model based on individuals' risk profiles to predict the severity of lung involvement and death in patients hospitalized with coronavirus disease 2019 (COVID-19) infection.

Methods

In this retrospective study, we studied hospitalized COVID-19 patients with data on chest CT scans performed during hospital stay (February 2020-April 2021) in a training dataset (TD) (n = 2,251) and an external validation dataset (eVD) (n = 993). We used the most relevant demographical, clinical, and laboratory variables (n = 25) as potential predictors of COVID-19-related outcomes. The primary and secondary endpoints were the severity of lung involvement quantified as mild (≤25%), moderate (26–50%), severe (>50%), and in-hospital death, respectively. We applied random forest (RF) classifier, a machine learning technique, and multivariable logistic regression analysis to study our objectives.

Results

In the TD and the eVD, respectively, the mean [standard deviation (SD)] age was 57.9 (18.0) and 52.4 (17.6) years; patients with severe lung involvement [n (%):185 (8.2) and 116 (11.7)] were significantly older [mean (SD) age: 64.2 (16.9), and 56.2 (18.9)] than the other two groups (mild and moderate). The mortality rate was higher in patients with severe (64.9 and 38.8%) compared to moderate (5.5 and 12.4%) and mild (2.3 and 7.1%) lung involvement. The RF analysis showed age, C reactive protein (CRP) levels, and duration of hospitalizations as the three most important predictors of lung involvement severity at the time of the first CT examination. Multivariable logistic regression analysis showed a significant strong association between the extent of the severity of lung involvement (continuous variable) and death; adjusted odds ratio (OR): 9.3; 95% CI: 7.1–12.1 in the TD and 2.6 (1.8–3.5) in the eVD.

Conclusion

In hospitalized patients with COVID-19, the severity of lung involvement is a strong predictor of death. Age, CRP levels, and duration of hospitalizations are the most important predictors of severe lung involvement. A simple prediction model based on available clinical and imaging data provides a validated tool that predicts the severity of lung involvement and death probability among hospitalized patients with COVID-19.

Validation of Machine Learning Models to Predict Adverse Outcomes in Patients with COVID-19: A Prospective Pilot Study

PURPOSE

We previously developed learning models for predicting the need for intensive care and oxygen among patients with coronavirus disease (COVID-19). Here, we aimed to prospectively validate the accuracy of these models.

MATERIALS AND METHODS

Probabilities of the need for intensive care [intensive care unit (ICU) score] and oxygen (oxygen score) were calculated from information provided by hospitalized COVID-19 patients (n=44) via a web-based application. The performance of baseline scores to predict 30-day outcomes was assessed.

RESULTS

Among 44 patients, 5 and 15 patients needed intensive care and oxygen, respectively. The area under the curve of ICU score and oxygen score to predict 30-day outcomes were 0.774 [95% confidence interval (CI): 0.614-0.934] and 0.728 (95% CI: 0.559-0.898), respectively. The ICU scores of patients needing intensive care increased daily by 0.71 points (95% CI: 0.20-1.22) after hospitalization and by 0.85 points (95% CI: 0.36-1.35) after symptom onset, which were significantly different from those in individuals not needing intensive care (p=0.002 and <0.001, respectively). Trends in daily oxygen scores overall were not markedly different; however, when the scores were evaluated within <7 days after symptom onset, the patients needing oxygen showed a higher daily increase in oxygen scores [1.81 (95% CI: 0.48-3.14) vs. -0.28 (95% CI: 1.00-0.43), p=0.007].

CONCLUSION

Our machine learning models showed good performance for predicting the outcomes of COVID-19 patients and could thus be useful for patient triage and monitoring.

Severe Outcomes Associated With SARS-CoV-2 Infection in Children: A Systematic Review and Meta-Analysis

OBJECTIVE

To estimate the proportion of SARS-CoV-2 infected children experiencing hospitalization, intensive care unit (ICU) admission, severe outcomes, and death.

DATA SOURCES

PubMed, Embase, and MedRxiv were searched for studies published between December 1, 2019 and May 28, 2021. References of relevant systematic reviews were also screened.

STUDY SELECTION

We included cohort or cross-sectional studies reporting on at least one outcome measure (i.e., hospitalization, ICU admission, severe outcomes, death) for ≥100 children ≤21 years old within 28 days of SARS-CoV-2 positivity; no language restrictions were applied.

DATA EXTRACTION AND SYNTHESIS

Two independent reviewers performed data extraction and risk of bias assessment. Estimates were pooled using random effects models. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines.

MAIN OUTCOMES AND MEASURES

Percentage of SARS-CoV-2 positive children experiencing hospitalization, ICU admission, severe outcome, and death.

RESULTS

118 studies representing 3,324,851 SARS-CoV-2 infected children from 68 countries were included. Community-based studies (N = 48) reported that 3.3% (95%CI: 2.7-4.0%) of children were hospitalized, 0.3% (95%CI: 0.2-0.6%) were admitted to the ICU, 0.1% (95%CI: 0.0-2.2%) experienced a "severe" outcome and 0.02% (95%CI: 0.001-0.05%) died. Hospital-based screening studies (N = 39) reported that 23.9% (95%CI: 19.0-29.2%) of children were hospitalized, 2.9% (95%CI: 2.1-3.8%) were admitted to the ICU, 1.3% (95%CI: 0.5-2.3%) experienced a severe outcome, and 0.2% (95%CI: 0.02-0.5%) died. Studies of hospitalized children (N = 31) reported that 10.1% (95%CI: 6.1-14.9%) of children required ICU admission, 4.2% (95%CI: 0.0-13.8%) had a severe outcome and 1.1% (95%CI: 0.2-2.3%) died. Low risk of bias studies, those from high-income countries, and those reporting outcomes later in the pandemic presented lower estimates. However, studies reporting outcomes after May 31, 2020, compared to earlier publications, had higher proportions of hospitalized patients requiring ICU admission and experiencing severe outcomes.

CONCLUSION AND RELEVANCE

Among children tested positive for SARS-CoV-2, 3.3% were hospitalized, with rates being higher early in the pandemic. Severe outcomes, ICU admission and death were uncommon, however estimates vary by study population, pandemic timing, study risk of bias, and economic status of the country.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO, identifier [CRD42021260164].

Does COVID-19 Clinical Status Associate with Outcome Severity? An Unsupervised Machine Learning Approach for Knowledge Extraction

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial intelligence (AI) and machine learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classifications which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying a principal component analysis (PCA) on the numerical part of the dataset and a multiple correspondence analysis (MCA) on the categorical part of the dataset. Then, the Bayesian information criterion (BIC) was applied to Gaussian mixture models (GMM) in order to identify the optimal number of clusters under which the best grouping of patients occurs. The proposed methodology identified four clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and the patient's mortality.

Development of an Early Warning Model for Predicting the Death Risk of Coronavirus Disease 2019 Based on Data Immediately Available on Admission

Introduction: COVID-19 has overloaded worldwide medical facilities, leaving some potentially high-risk patients trapped in outpatient clinics without sufficient treatment. However, there is still a lack of a simple and effective tool to identify these patients early.

Methods: A retrospective cohort study was conducted to develop an early warning model for predicting the death risk of COVID-19. Seventy-five percent of the cases were used to construct the prediction model, and the remaining 25% were used to verify the prediction model based on data immediately available on admission.

Results: From March 1, 2020, to April 16, 2020, a total of 4,711 COVID-19 patients were included in our study. The average age was 63.37 ± 16.70 years, of which 1,148 (24.37%) died. Finally, age, SpO2, body temperature (T), and mean arterial pressure (MAP) were selected for constructing the model by univariate analysis, multivariate analysis, and a review of the literature. We used five common methods for constructing the model and finally found that the full model had the best specificity and higher accuracy. The area under the ROC curve (AUC), specificity, sensitivity, and accuracy of full model in train cohort were, respectively, 0.798 (0.779, 0.816), 0.804, 0.656, and 0.768, and in the validation cohort were, respectively, 0.783 (0.751, 0.815), 0.800, 0.616, and 0.755. Visualization tools of the prediction model included a nomogram and an online dynamic nomogram (https://wanghai.shinyapps.io/dynnomapp/).

Conclusion: We developed a prediction model that might aid in the early identification of COVID-19 patients with a high probability of mortality on admission. However, further research is required to determine whether this tool can be applied for outpatient or home-based COVID-19 patients.