COVID-19 mortality risk assessment: An international multi-center study

Prediction models based on machine learning algorithms for COVID-19 severity risk

BACKGROUND

The World Health Organization has highlighted the risk of Disease X, urging pandemic preparedness. Coronavirus disease 2019 (COVID-19) could be the first Disease X; therefore, understanding the epidemiological experiences of COVID-19 is crucial while preparing for future similar diseases.

METHODS

Prediction models for COVID-19 severity risk in hospitalized patients were constructed based on four machine learning algorithms, namely, logistic regression, Cox regression, support vector machine (SVM), and random forest. These models were evaluated for prediction accuracy, area under the curve (AUC), sensitivity, and specificity as well as were interpreted using SHapley Additive exPlanation.

RESULTS

Data were collected from 1,485 hospitalized patients across 6 centers, comprising 1,184 patients with severe or critical COVID-19 and 301 patients with nonsevere COVID-19. Among the four models, the SVM model achieved the highest prediction accuracy of 98.45%, with an AUC of 0.994, a sensitivity of 0.989, and a specificity of 0.969. Moreover, oxygenation index (OI), confusion, respiratory rate, and age were found to be predictors of COVID-19 severity risk.

CONCLUSIONS

SVM could accurately predict COVID-19 severity risk; thus, it can be prioritized as a prediction model. OI is the most critical predictor of COVID-19 severity risk and can serve as the primary and independent evaluation indicator.

Exploring the Molecular Interplay Between Oxygen Transport, Cellular Oxygen Sensing, and Mitochondrial Respiration

Significance: The mitochondria play a key role in maintaining oxygen homeostasis under normal oxygen tension (normoxia) and during oxygen deprivation (hypoxia). This is a critical balancing act between the oxygen content of the blood, the tissue oxygen sensing mechanisms, and the mitochondria, which ultimately consume most oxygen for energy production. Recent Advances: We describe the well-defined role of the mitochondria in oxygen metabolism with a special focus on the impact on blood physiology and pathophysiology. Critical Issues: Fundamental questions remain regarding the impact of mitochondrial responses to changes in overall blood oxygen content under normoxic and hypoxic states and in the case of impaired oxygen sensing in various cardiovascular and pulmonary complications including blood disorders involving hemolysis and hemoglobin toxicity, ischemia reperfusion, and even in COVID-19 disease. Future Directions: Understanding the nature of the crosstalk among normal homeostatic pathways, oxygen carrying by hemoglobin, utilization of oxygen by the mitochondrial respiratory chain machinery, and oxygen sensing by hypoxia-inducible factor proteins, may provide a target for future therapeutic interventions. Antioxid. Redox Signal. 42, 730-750.

Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome

Background

Two years after the COVID-19 pandemic, it became known that one of the complications of this disease is myocardial injury. Electrocardiography (ECG) and cardiac biomarkers play a vital role in the early detection of cardiovascular complications and risk stratification. The study aimed to investigate the value of a new electrocardiographic metric for detecting minor myocardial injury in patients during COVID-19 treatment.

Methods

The study was conducted in 2021. A group of 26 patients with verified COVID-19 diagnosis admitted to the intensive care unit for infectious diseases was examined. The severity of a patient's condition was calculated using the NEWS score. The digital ECGs were repeatedly recorded (at the beginning and 2-4 times during the treatment). A total of 240 primary and composite ECG parameters were analyzed for each electrocardiogram. Among these patients, 6 patients died during treatment. Cluster analysis was used to identify subgroups of patients that differed significantly in terms of disease severity (NEWS), SрО2 and integral ECG index (an indicator of the state of the cardiovascular system).

Results

Using analysis of variance (ANOVA repeated measures), a statistical assessment of changes of indicators in subgroups at the end of treatment was given. These subgroup differences persisted at the end of the treatment. To identify potential predictors of mortality, critical clinical and ECG parameters of surviving (S) and non-surviving patients (D) were compared using parametric and non-parametric statistical tests. A decision tree model to classify survival in patients with COVID-19 was constructed based on partial ECG parameters and NEWS score.

Conclusion

A comparison of potential mortality predictors showed no significant differences in vital signs between survivors and non-survivors at the beginning of treatment. A set of ECG parameters was identified that were significantly associated with treatment outcomes and may be predictors of COVID-19 mortality: T-wave morphology (SVD), Q-wave amplitude, and R-wave amplitude (lead I).

Estimating the Number of Primary vs Incidental COVID-19 Hospitalizations in Santa Clara County

Background

The goal of this study was to evaluate whether International Classification of Diseases, 10th Revision (ICD-10), discharge data can be used to accurately differentiate primary coronavirus disease 2019 (COVID-19) hospitalizations, which are specifically due to COVID-19, from incidental COVID-19 hospitalizations for monitoring COVID-19 trends in a large county health department. We sought to explore the use of machine learning algorithms for enhancing surveillance capabilities in a local public health setting.

Methods

Discharge data for 5122 Santa Clara County hospitalizations with a positive severe acute respiratory syndrome coronavirus 2 polymerase chain reaction or antigen test occurring between December 15, 2021, and August 15, 2022, were used to train a series of models for classifying primary COVID-19 hospitalizations using chart review as a gold standard. Area under the receiver operating characteristic curve (AUROC) was used as the evaluation metric.

Results

Each model performed well when trained on the full set of available predictors. AUROC values ranged from 0.808 (random forest) to 0.818 (SuperLearner). After evaluating each model, we implemented a reporting process based on Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression, as the performance was comparable with SuperLearner and it had the advantage of being transparent and familiar to health department staff.

Conclusions

In Santa Clara County, ICD-10 discharge data were successfully used to develop a low-burden method for monitoring primary COVID-19 hospitalization, demonstrating one way that predictive algorithms can help local health jurisdictions meet surveillance needs while minimizing manual effort.

Prediction of mortality and prioritisation to tertiary care using the 'OUR-ARCad' risk score gleaned from the second wave of COVID-19 pandemic-A retrospective cohort study from South India

BACKGROUND

Judicious utilisation of tertiary care facilities through appropriate risk stratification assumes priority, in a raging pandemic, of the nature of delta variant-predominated second wave of COVID-19 pandemic in India. Prioritisation of tertiary care, through a scientifically validated risk score, would maximise recovery without compromising individual safety, but importantly without straining the health system.

METHODS

De-identified data of COVID-19 confirmed patients admitted to a tertiary care hospital in South India, between April 1, 2021 and July 31, 2021, corresponding to the peak of COVID-19 second wave, were analysed after segregating into 'survivors' or 'non-survivors' to evaluate the risk factors for COVID-19 mortality at admission and formulate a risk score with easily obtainable but clinically relevant parameters for accurate patient triaging. The predictive ability was ascertained by the area under the receiver operator characteristics (AUROC) and the goodness of fit by the Hosmer-Lemeshow test and validated using the bootstrap method.

RESULTS

Of 617 COVID-19 patients (325 survivors, 292 non-survivors), treated as per prevailing national guidelines, with a slight male predilection (358/617 [58.0%]), fatalities in the age group above and below 50 years were (217/380 [57.1%]) and (75/237 [31.6%]), p<0.001. The relative distribution of the various parameters among survivors and non-survivors including self-reported comorbidities helped to derive the individual risk scores from parameters significant in the multivariable logistic regression. The 'OUR-ARCad' risk score components were-Oxygen saturation SaO2<94%-23, Urea > 40mg/dL-15, Neutrophil/Lymphocytic ratio >3-23, Age > 50 years-8, Pulse Rate >100-8 and Coronary Artery disease-15. A summated score above 50, mandated tertiary care management (sensitivity-90%, specificity-75%; AUC-0.89), validated in 2000 bootstrap dataset.

CONCLUSIONS

The OUR-ARCad risk score, could potentially maximize recovery in a raging COVID-19 pandemic, through prioritisation of tertiary care services, neither straining the health system nor compromising patient's safety, delivering and diverting care to those who needed the most.

Sex differences in pneumonia risk during COVID-19 in Mexico

This study aimed to evaluate the pneumonia risk based on the patient's sex during the COVID-19 pandemic and the early months of the endemic phase of the disease in Mexico. A retrospective cohort study was conducted using a dataset resulting from the epidemiological surveillance of COVID-19 (February 2020 to August 2023). Data from 1.6 million adults with laboratory-positive disease, were analyzed. Risk ratios (RR) and 95% confidence intervals (CI), computed through generalized linear regression models, were used. The overall risk of pneumonia was 9.3% (95% CI 9.2-9.4%), with sex-specific estimates of 7.0% (95% CI 6.9-7.1%) for women and 12.0% (95% CI 11.9-12.1%) for men. This disparity was consistently observed throughout all phases of the pandemic, including the endemic phase of the disease. After adjusting for age, predominant viral genotype at illness onset and preexisting medical conditions, men had a 3.3% higher risk of severe manifestations when compared to women (RR = 1.033, 95% CI 1.032-1.034). Our research highlights the potential role of patients' sex as a factor influencing pneumonia risk during and after the COVID-19 pandemic in Mexico. These findings may provide useful considerations for healthcare planning and policy development focused on addressing the impact of the disease on vulnerable populations.

Development of decision tree classification algorithms in predicting mortality of COVID-19 patients

INTRODUCTION

The accurate prediction of COVID-19 mortality risk, considering influencing factors, is crucial in guiding effective public policies to alleviate the strain on the healthcare system. As such, this study aimed to assess the efficacy of decision tree algorithms (CART, C5.0, and CHAID) in predicting COVID-19 mortality risk and compare their performance with that of the logistic model.

METHODS

This retrospective cohort study examined 5080 cases of COVID-19 in Babol, a city in northern Iran, who tested positive for the virus via PCR from March 2020 to March 2022. In order to check the validity of the findings, the data was randomly divided into an 80% training set and a 20% testing set. The prediction models, such as Logistic regression models and decision tree algorithms, were trained on the 80% training data and tested on the 20% testing data. The accuracy of these methods for the test samples was assessed using measures like ROC curve, sensitivity, specificity, and AUC.

RESULTS

The findings revealed that the mortality rate for COVID-19 patients who were admitted to hospitals was 7.7%. Through cross validation, it was determined that the CHAID algorithm outperformed other decision tree and logistic regression algorithms in specificity, and precision but not sensitivity in predicting the risk of COVID-19 mortality. The CHAID algorithm demonstrated a specificity, precision, accuracy, and F-score of 0.98, 0.70, 0.95, and 0.52 respectively. All models indicated that factors such as ICU hospitalization, intubation, age, kidney disease, BUN, CRP, WBC, NLR, O2 sat, and hemoglobin were among the factors that influenced the mortality rate of COVID-19 patients.

CONCLUSIONS

The CART and C5.0 models had outperformed in sensitivity but CHAID demonstrates a better performance compared to other decision tree algorithms in specificity, precision, accuracy and shows a slight improvement over the logistic regression method in predicting the risk of COVID-19 mortality in the population under study.

The effectiveness of COVID-19 vaccination in preventing hospitalisation and mortality: A nationwide cross-sectional study in Iran

Background

The pandemic of the coronavirus disease 2019 (COVID-19) led to a global health crisis, prompting widespread vaccination efforts to reduce severe outcomes. In this study, we assessed the impact of mass COVID-19 vaccination on hospitalisation and mortality rates in Iran, where over 83% of the vaccinated population received inactivated virus vaccines.

Methods

Using retrospective, cross-sectional analysis, we examined data from the Iran Health Insurance Organisation, covering 41 million individuals from 20 February 2020 to 20 March 2022. We analysed hospital records from 956 Iranian hospitals, focusing on inpatient stays, short-term hospitalisations, and emergency department visits. Study outcomes included COVID-19 hospital admissions and associated mortality. We used negative binomial regression to compare hospital admission rates between periods, while we used a poison regression model with a log link to assess mortality risks before and after vaccination.

Results

Among 806 076 hospital admissions, 57 599 deaths were recorded. COVID-19 hospitalisations increased with age, and women had slightly higher admission rates than men. Advanced age and male sex correlated with higher mortality rates. Hospital admissions rose to 1178.66 per million population per month post-vaccination compared to 459.78 pre-vaccination. The incidence rate ratio was 2.09 (95% confidence interval (CI) = 1.90-2.32, P < 0.001), mainly due to the Delta variant. In contrast, post-vaccination mortality rates decreased from 111.33 to 51.66 per 1000 admissions per month. Post-vaccination, COVID-19 mortality significantly decreased, with a relative risk being 0.61 (95% CI = 0.60-0.62, P < 0.001) across all age groups and sexes.

Conclusions

The Delta variant increased hospital admissions among vaccinated individuals, but widespread vaccination significantly reduced COVID-19-related mortality.

Evolving patterns of COVID-19 mortality in US counties: A longitudinal study of healthcare, socioeconomic, and vaccination associations

The COVID-19 pandemic emphasized the need for pandemic preparedness strategies to mitigate its impacts, particularly in the United States, which experienced multiple waves with varying policies, population response, and vaccination effects. This study explores the relationships between county-level factors and COVID-19 mortality outcomes in the U.S. from 2020 to 2023, focusing on disparities in healthcare access, vaccination coverage, and socioeconomic characteristics. We conduct multi-variable rolling regression analyses to reveal associations between various factors and COVID-19 mortality outcomes, defined as Case Fatality Rate (CFR) and Overall Mortality to Hospitalization Rate (OMHR), at the U.S. county level. Each analysis examines the association between mortality outcomes and one of the three hierarchical levels of the Social Vulnerability Index (SVI), along with other factors such as access to hospital beds, vaccination coverage, and demographic characteristics. Our results reveal persistent and dynamic correlations between various factors and COVID-19 mortality measures. Access to hospital beds and higher vaccination coverage showed persistent protective effects, while higher Social Vulnerability Index was associated with worse outcomes persistently. Socioeconomic status and vulnerable household characteristics within the SVI consistently associated with elevated mortality. Poverty, lower education, unemployment, housing cost burden, single-parent households, and disability population showed significant associations with Case Fatality Rates during different stages of the pandemic. Vulnerable age groups demonstrated varying associations with mortality measures, with worse outcomes predominantly during the Original strain. Rural-Urban Continuum Code exhibited predominantly positive associations with CFR and OMHR, while it starts with a positive OMHR association during the Original strain. This study reveals longitudinal persistent and dynamic factors associated with two mortality rate measures throughout the pandemic, disproportionately affecting marginalized communities. The findings emphasize the urgency of implementing targeted policies and interventions to address disparities in the fight against future pandemics and the pursuit of improved public health outcomes.

Unbiased identification of risk factors for invasive Escherichia coli disease using machine learning

BACKGROUND

Invasive Escherichia coli disease (IED), also known as invasive extraintestinal pathogenic E. coli disease, is a leading cause of sepsis and bacteremia in older adults that can result in hospitalization and sometimes death and is frequently associated with antimicrobial resistance. Moreover, certain patient characteristics may increase the risk of developing IED. This study aimed to validate a machine learning approach for the unbiased identification of potential risk factors that correlate with an increased risk for IED.

METHODS

Using electronic health records from 6.5 million people, an XGBoost model was trained to predict IED from 663 distinct patient features, and the most predictive features were identified as potential risk factors. Using Shapley Additive predictive values, the specific relationships between features and the outcome of developing IED were characterized.

RESULTS

The model independently predicted that older age, a known risk factor for IED, increased the chance of developing IED. The model also predicted that a history of ≥ 1 urinary tract infection, as well as more frequent and/or more recent urinary tract infections, and ≥ 1 emergency department or inpatient visit increased the risk for IED. Outcomes were used to calculate risk ratios in selected subpopulations, demonstrating the impact of individual or combinations of features on the incidence of IED.

CONCLUSION

This study illustrates the viability and validity of using large electronic health records datasets and machine learning to identify correlating features and potential risk factors for infectious diseases, including IED. The next step is the independent validation of potential risk factors using conventional methods.

Interacting particle models on the impact of spatially heterogeneous human behavioral factors on dynamics of infectious diseases

Human behaviors have non-negligible impacts on spread of contagious disease. For instance, large-scale gathering and high mobility of population could lead to accelerated disease transmission, while public behavioral changes in response to pandemics may effectively reduce contacts and suppress the peak of the outbreak. In order to understand how spatial characteristics like population mobility and clustering interplay with epidemic outbreaks, we formulate a stochastic-statistical environment-epidemic dynamic system (SEEDS) via an agent-based biased random walk model on a two-dimensional lattice. The "popularity" and "awareness" variables are taken into consideration to capture human natural and preventive behavioral factors, which are assumed to guide and bias agent movement in a combined way. It is found that the presence of the spatial heterogeneity, like social influence locality and spatial clustering induced by self-aggregation, potentially suppresses the contacts between agents and consequently flats the epidemic curve. Surprisedly, disease responses might not necessarily reduce the susceptibility of informed individuals and even aggravate disease outbreak if each individual responds independently upon their awareness. The disease control is achieved effectively only if there are coordinated public-health interventions and public compliance to these measures. Therefore, our model may be useful for quantitative evaluations of a variety of public-health policies.

Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality

As the world emerges from the COVID-19 pandemic, there is an urgent need to understand patient factors that may be used to predict the occurrence of severe cases and patient mortality. Approximately 20% of SARS-CoV-2 infections lead to acute respiratory distress syndrome caused by the harmful actions of inflammatory mediators. Patients with severe COVID-19 are often afflicted with neurologic symptoms, and individuals with pre-existing neurodegenerative disease have an increased risk of severe COVID-19. Although collectively, these observations point to a bidirectional relationship between severe COVID-19 and neurologic disorders, little is known about the underlying mechanisms. Here, we analyzed the electronic health records of 471 patients with severe COVID-19 to identify clinical characteristics most predictive of mortality. Feature discovery was conducted by training a regularized logistic regression classifier that serves as a machine-learning model with an embedded feature selection capability. SHAP analysis using the trained classifier revealed that a small ensemble of readily observable clinical features, including characteristics associated with cognitive impairment, could predict in-hospital mortality with an accuracy greater than 0.85 (expressed as the area under the ROC curve of the classifier). These findings have important implications for the prioritization of clinical measures used to identify patients with COVID-19 (and, potentially, other forms of acute respiratory distress syndrome) having an elevated risk of death.

Clinical Features Predicting COVID-19 Severity Risk at the Time of Hospitalization

The global spread of COVID-19 has led to significant mortality and morbidity worldwide. Early identification of COVID-19 patients who are at high risk of developing severe disease can help in improved patient management, care, and treatment, as well as in the effective allocation of hospital resources. The severity prediction at the time of hospitalization can be extremely helpful in deciding the treatment of COVID-19 patients. To this end, this study presents an interpretable artificial intelligence (AI) model, named COVID-19 severity predictor (CoSP) that predicts COVID-19 severity using the clinical features at the time of hospital admission. We utilized a dataset comprising 64 demographic and laboratory features of 7,416 confirmed COVID-19 patients that were collected at the time of hospital admission. The proposed hierarchical CoSP model performs four-class COVID severity risk prediction into asymptomatic, mild, moderate, and severe categories. CoSP yielded better performance with good interpretability, as observed via Shapley analysis on COVID severity prediction compared to the other popular ML methods, with an area under the received operating characteristic curve (AUC-ROC) of 0.95, an area under the precision-recall curve (AUPRC) of 0.91, and a weighted F1-score of 0.83. Out of 64 initial features, 19 features were inferred as predictive of the severity of COVID-19 disease by the CoSP model. Therefore, an AI model predicting COVID-19 severity may be helpful for early intervention, optimizing resource allocation, and guiding personalized treatments, potentially enabling healthcare professionals to save lives and allocate resources effectively in the fight against the pandemic.

Prevalence and Predictive Factors of Rhabdomyolysis in COVID-19 Patients: A Cross-sectional Study

Introduction

The aim of the present prospective observational study was to demonstrate the prevalence and predictive factors of rhabdomyolysis in coronavirus disease 2019 (COVID-19) patients.

Methods

The study was performed on reverse transcriptase-polymerase chain reaction (RT-PCR)-confirmed COVID-19 patients admitted to the emergency department between March 2020 and March 2021. Peak creatinine phosphokinase (CPK) levels were used to define rhabdomyolysis. A CPK level equal to or more than 1000 IU/L was defined as the presence of moderate to severe rhabdomyolysis. We developed a COVID-19-related Rhabdomyolysis Prognostic rule (CORP rule) using the independent predictors of rhabdomyolysis in COVID-19 patients.

Results

Five hundred and six confirmed COVID-19 patients (mean age 58.36 ± 17.83 years, 56.32% male) were studied. Rhabdomyolysis occurred in 44 (8.69%) cases throughout their hospitalization. Male gender (odds ratio [OR] = 2.78, 95% confidence interval [CI]: 1.28, 6.00), hyponatremia (OR = 2.46, 95% CI: 1.08, 5.59), myalgia (OR = 3.04, 95% CI: 1.41, 6.61), D-dimer >1000 (OR = 2.84, 95% CI: 1.27, 6.37), and elevated aspartate aminotransferase level (three times higher than normal range) (OR = 3.14, 95% CI: 1.52, 6.47) were the significant preliminary predictors of rhabdomyolysis. The area under the curve of the CORP rule was 0.75 (95% CI: 0.69, 0.81), indicating the fair performance of it in the prognosis of rhabdomyolysis following COVID-19 infection. The best cutoff of the CORP rule was 3, which had a sensitivity of 72.9% and a specificity of 72.7%.

Conclusion

This prospective study showed that 8.69% of patients developed rhabdomyolysis following COVID-19 infection. The CORP rule with optimal cutoff can correctly classify 72.8% of COVID-19 patients at risk of developing rhabdomyolysis.

Characteristics and risk factors associated with mortality during the first cycle of prone secondary to ARDS due to SARS-CoV-2 pneumonia

OBJECTIVE

To analyze characteristics, changes in oxygenation, and pulmonary mechanics, in mechanically ventilated patients with ARDS due to SARS-CoV-2 treated with prone position and evaluate the response to this maneuver.

DESIGN

Cohort study including patients with PaO2/FiO2 <150mmHg requiring prone position over 18 months. We classified patients according to PaO2/FiO2 changes from basal to 24h after the first prone cycle as: 1) no increase 2) increase <25%, 3) 25%-50% increase 4) increase >50%.

SETTING

33-bed medical-surgical Intensive Care Unit (ICU) in Argentina.

PATIENTS

273 patients.

INTERVENTIONS

None.

MAIN VARIABLES OF INTEREST

Epidemiological characteristics, respiratory mechanics and oxygenation were compared between survivors and non-survivors. Independent factors associated with in-hospital mortality were identified.

RESULTS

Baseline PaO2/FiO2 was 116 [97-135]mmHg (115 [94-136] in survivors vs. 117 [98-134] in non-survivors; p=0.50). After prone positioning, 22 patients (8%) had similar PaO2/FiO2 values; 46(16%) increased PaO2/FiO2 ≤25%; 55 (21%) increased it 25%-50%; and 150 (55%), >50%. Mortality was 86%, 87%, 72% and 50% respectively (p<0.001). Baseline PaO2/FiO2, <100mmHg did not imply that patients were refractory to prone position. Factors independently associated with mortality were age, percentage increase in PaO2/FiO2 after 24h being in prone, and number of prone cycles.

CONCLUSIONS

Older patients unable to improve PaO2/FiO2 after 24h in prone position and who require >1 cycle might early receive additional treatments for refractory hypoxemia. After the first 24h in the prone position, a low percentage of PaO2/FiO2 increase over baseline, beyond the initial value, was independently associated with higher mortality.

Identifying prognostic factors for survival in intensive care unit patients with SIRS or sepsis by machine learning analysis on electronic health records

BACKGROUND

Systemic inflammatory response syndrome (SIRS) and sepsis are the most common causes of in-hospital death. However, the characteristics associated with the improvement in the patient conditions during the ICU stay were not fully elucidated for each population as well as the possible differences between the two.

GOAL

The aim of this study is to highlight the differences between the prognostic clinical features for the survival of patients diagnosed with SIRS and those of patients diagnosed with sepsis by using a multi-variable predictive modeling approach with a reduced set of easily available measurements collected at the admission to the intensive care unit (ICU).

METHODS

Data were collected from 1,257 patients (816 non-sepsis SIRS and 441 sepsis) admitted to the ICU. We compared the performance of five machine learning models in predicting patient survival. Matthews correlation coefficient (MCC) was used to evaluate model performances and feature importance, and by applying Monte Carlo stratified Cross-Validation.

RESULTS

Extreme Gradient Boosting (MCC = 0.489) and Logistic Regression (MCC = 0.533) achieved the highest results for SIRS and sepsis cohorts, respectively. In order of importance, APACHE II, mean platelet volume (MPV), eosinophil counts (EoC), and C-reactive protein (CRP) showed higher importance for predicting sepsis patient survival, whereas, SOFA, APACHE II, platelet counts (PLTC), and CRP obtained higher importance in the SIRS cohort.

CONCLUSION

By using complete blood count parameters as predictors of ICU patient survival, machine learning models can accurately predict the survival of SIRS and sepsis ICU patients. Interestingly, feature importance highlights the role of CRP and APACHE II in both SIRS and sepsis populations. In addition, MPV and EoC are shown to be important features for the sepsis population only, whereas SOFA and PLTC have higher importance for SIRS patients.

Patterns of case fatality and hospitalization duration among nearly 1 million hospitalized COVID-19 patients covered by Iran Health Insurance Organization (IHIO) over two years of pandemic: An analysis of associated factors

BACKGROUND

Different populations and areas of the world experienced diverse COVID-19 hospitalization and mortality rates. Claims data is a systematically recorded source of hospitalized patients' information that could be used to evaluate the disease management course and outcomes. We aimed to investigate the hospitalization and mortality patterns and associated factors in a huge sample of hospitalized patients.

METHODS

In this retrospective registry-based study, we utilized claim data from the Iran Health Insurance Organization (IHIO) consisting of approximately one million hospitalized patients across various hospitals in Iran over a 26-month period. All records in the hospitalization dataset with ICD-10 codes U07.1/U07.2 for clinically/laboratory confirmed COVID-19 were included. In this study, a case referred to one instance of a patient being hospitalized. If a patient experienced multiple hospitalizations within 30 days, those were aggregated into a single case. However, if hospitalizations had longer intervals, they were considered independent cases. The primary outcomes of study were general and intensive care unit (ICU) hospitalization periods and case fatality rate (CFR) at the hospital. Besides, various demographic and hospitalization-associated factors were analyzed to derive the associations with study outcomes using accelerated failure time (AFT) and logistic regression models.

RESULTS

A total number of 1 113 678 admissions with COVID-19 diagnosis were recorded by IHIO during the study period, defined as 917 198 cases, including 51.9% females and 48.1% males. The 61-70 age group had the highest number of cases for both sexes. Among defined cases, CFR was 10.36% (95% CI: 10.29-10.42). The >80 age group had the highest CFR (26.01% [95% CI: 25.75-26.27]). The median of overall hospitalization and ICU days were 4 (IQR: 3-7) and 5 (IQR: 2-8), respectively. Male patients had a significantly higher risk for mortality both generally (odds ratio (OR) = 1.36 [1.34-1.37]) and among ICU admitted patients (1.12 [1.09-1.12]). Among various insurance funds, Foreign Citizens had the highest risk of death both generally (adjusted OR = 2.06 [1.91-2.22]) and in ICU (aOR = 1.71 [1.51-1.92]). Increasing age groups was a risk of longer hospitalization, and the >80 age group had the highest risk for overall hospitalization period (median ratio = 1.52 [1.51-1.54]) and at ICU (median ratio = 1.17 [1.16-1.18]). Considering Tehran as the reference province, Sistan and Balcuchestan (aOR = 1.4 [1.32-1.48]), Alborz (aOR = 1.28 [1.22-1.35]), and Khorasan Razavi (aOR = 1.24 [1.20-1.28]) were the provinces with the highest risk of mortality in hospitalized patients.

CONCLUSION

Hospitalization data unveiled mortality and duration associations with variables, highlighting provincial outcome disparities in Iran. Using enhanced registry systems in conjunction with other studies, empowers policymakers with evidence for optimizing resource allocation and fortifying healthcare system resilience against future health challenges.

Blood urea nitrogen and clinical prognosis in patients with COVID-19: A retrospective study

The aim of this study was to estimate the association between blood urea nitrogen (BUN) and clinical prognosis in patients with COVID-19. A multicenter, retrospective study was conducted in adult patients with COVID-19 in 3 hospitals in Zhenjiang from January 2023 to May 2023. Patients were divided into survival and death group based on whether they survived at day 28. The demographic, comorbidities, and laboratory data were independently collected and analyzed, as well as clinical outcomes. Total 141 patients were enrolled and 23 (16.3%) died within 28 days. Patients who died within 28 days had a higher level of BUN compared with survivors. Bivariate logistic regression analysis showed that BUN was a risk factor for 28-day mortality in patients with COVID-19. ROC curve showed that BUN could predict 28-day mortality of COVID-19 patients (AUC = 0.796, 95%CI: 0.654-0.938, P < .001). When the cutoff value of BUN was 7.37 mmol/L, the sensitivity and specificity were 84.62% and 70.31%. Subgroup analysis demonstrated that hyper-BUN (≥7.37 mmol/L) was associated with increased 28-day mortality among COVID-19 patients. Patients with COVID-19 who died within 28 days had a higher level of BUN, and hyper-BUN (≥7.37 mmol/L) was associated with increased 28-day mortality.

International Hepato-Pancreato-Billiary Association (IHPBA) registry study on COVID-19 infections in HPB surgery patients

BACKGROUND

In response to the pandemic, the International Hepato-Pancreato-Biliary Association (IHPBA) developed the IHPBA-COVID Registry to capture data on HPB surgery outcomes in COVID-positive patients prior to mass vaccination programs. The aim was to provide a tool to help members gain a better understanding of the impact of COVID-19 on patient outcomes following HPB surgery worldwide.

METHODS

An online registry updated in real time was disseminated to all IHPBA, E-AHPBA, A-HPBA and A-PHPBA members to assess the effects of the pandemic on the outcomes of HPB procedures, perioperative COVID-19 management and other aspects of surgical care.

RESULTS

One hundred twenty-five patients from 35 centres in 18 countries were included. Seventy-three (58%) patients were diagnosed with COVID-19 preoperatively. Operative mortality after pancreaticoduodenectomy and major hepatectomy was 28% and 15%, respectively, and 2.5% after cholecystectomy. Postoperative complication rates of pancreatic procedures, hepatic interventions and biliary interventions were respectively 80%, 50% and 37%. Respiratory complication rates were 37%, 31% and 10%, respectively.

CONCLUSION

This study reveals a high risk of mortality and complication after HPB surgeries in patient infected with COVID-19. The more extensive the procedure, the higher the risk. Nonetheless, an increased risk was observed across all types of interventions, suggesting that elective HPB surgery should be avoided in COVID positive patients, delaying it at distance from the viral infection.

Combating COVID-19 Crisis using Artificial Intelligence (AI) Based Approach: Systematic Review

BACKGROUND

SARS-CoV-2, the unique coronavirus that causes COVID-19, has wreaked damage around the globe, with victims displaying a wide range of difficulties that have encouraged medical professionals to look for innovative technical solutions and therapeutic approaches. Artificial intelligence-based methods have contributed a significant part in tackling complicated issues, and some institutions have been quick to embrace and tailor these solutions in response to the COVID-19 pandemic's obstacles. Here, in this review article, we have covered a few DL techniques for COVID-19 detection and diagnosis, as well as ML techniques for COVID-19 identification, severity classification, vaccine and drug development, mortality rate prediction, contact tracing, risk assessment, and public distancing. This review illustrates the overall impact of AI/ML tools on tackling and managing the outbreak.

PURPOSE

The focus of this research was to undertake a thorough evaluation of the literature on the part of Artificial Intelligence (AI) as a complete and efficient solution in the battle against the COVID-19 epidemic in the domains of detection and diagnostics of disease, mortality prediction and vaccine as well as drug development.

METHODS

A comprehensive exploration of PubMed, Web of Science, and Science Direct was conducted using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) regulations to find all possibly suitable papers conducted and made publicly available between December 1, 2019, and August 2023. COVID-19, along with AI-specific words, was used to create the query syntax.

RESULTS

During the period covered by the search strategy, 961 articles were published and released online. Out of these, a total of 135 papers were chosen for additional investigation. Mortality rate prediction, early detection and diagnosis, vaccine as well as drug development, and lastly, incorporation of AI for supervising and controlling the COVID-19 pandemic were the four main topics focused entirely on AI applications used to tackle the COVID-19 crisis. Out of 135, 60 research papers focused on the detection and diagnosis of the COVID-19 pandemic. Next, 19 of the 135 studies applied a machine-learning approach for mortality rate prediction. Another 22 research publications emphasized the vaccine as well as drug development. Finally, the remaining studies were concentrated on controlling the COVID-19 pandemic by applying AI AI-based approach to it.

CONCLUSION

We compiled papers from the available COVID-19 literature that used AI-based methodologies to impart insights into various COVID-19 topics in this comprehensive study. Our results suggest crucial characteristics, data types, and COVID-19 tools that can aid in medical and translational research facilitation.

Severe COVID-19 in patients with immune-mediated rheumatic diseases: A stratified analysis from the SORCOM multicentre registry

OBJECTIVES

The aim of this study is to evaluate risk factors for severe coronavirus disease 2019 (COVID-19) in patients with immune-mediated rheumatic diseases, stratified by systemic autoimmune conditions and chronic inflammatory arthritis.

METHODS

An observational, cross-sectional multicentre study was performed. Patients from 10 rheumatology departments in Madrid who presented with severe acute respiratory syndrome coronavirus-2 infection between February 2020 and May 2021 were included. The main outcome was COVID-19 severity (hospital admission or mortality). Risk factors for severity were estimated, adjusting for covariates (socio-demographic, clinical, and treatments), using logistic regression analyses.

RESULTS

In total, 523 patients with COVID-19 were included, among whom 192 (35.6%) patients required hospital admission and 38 (7.3%) died. Male gender, older age, and comorbidities such as diabetes mellitus, hypertension, and obesity were associated with severe COVID-19. Corticosteroid doses >10 mg/day, rituximab, sulfasalazine, and mycophenolate use, were independently associated with worse outcomes. COVID-19 severity decreased over the different pandemic waves. Mortality was higher in the systemic autoimmune conditions (univariate analysis, P < .001), although there were no differences in the overall severity in the multivariate analysis.

CONCLUSIONS

This study confirms and provides new insights regarding the harmful effects of corticosteroids, rituximab, and other therapies (mycophenolate and sulfasalazine) in COVID-19. Methotrexate and anti-tumour necrosis factor therapy were not associated with worse outcomes.

Combining blood glucose and SpO2/FiO2 ratio facilitates prediction of imminent ventilatory needs in emergency room COVID-19 patients

The increasing requirement of mechanical ventilation (MV) due to the novel coronavirus disease (COVID-19) is still a global threat. The aim of this study is to identify markers that can easily stratify the impending use of MV in the emergency room (ER). A total of 106 patients with COVID-19 requiring oxygen support were enrolled. Fifty-nine patients were provided MV 0.5 h (interquartile range: 0.3 to 1.4) post-admission. Clinical and laboratory data before intubation were collected. Using a multivariate logistic regression model, we identified four markers associated with the impending use of MV, including the ratio of peripheral blood oxygen saturation to fraction of inspired oxygen (SpO2/FiO2 ratio), alanine aminotransferase, blood glucose (BG), and lymphocyte counts. Among these markers, SpO2/FiO2 ratio and BG, which can be measured easily and immediately, showed higher accuracy (AUC: 0.88) than SpO2/FiO2 ratio alone (AUC: 0.84), despite no significant difference (DeLong test: P = 0.591). Moreover, even in patients without severe respiratory failure (SpO2/FiO2 ratio > 300), BG (> 138 mg/dL) was predictive of MV use. Measuring BG and SpO2/FiO2 ratio may be a simple and versatile new strategy to accurately identify ER patients with COVID-19 at high risk for the imminent need of MV.

Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19

Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices and clinical questionnaires. The derivation cohort consisted of people diagnosed with COVID-19 between September and December 2021, and the external validation cohort collected between March and June 2022. To develop the model, a total of 50 participants wore the device for an average of 77 h. To evaluate the model, a total of 181 infected participants wore the device for an average of 65 h. We designed machine learning-based models that predict deterioration in patients with mild COVID-19. The prediction model, 10 min in advance, showed an area under the receiver characteristic curve (AUC) of 0.99, and the prediction model, 8 h in advance, showed an AUC of 0.84. We found that certain variables that are important to model vary depending on the point in time to predict. Efficient deterioration monitoring in many patients is possible by utilizing data collected from wearable sensors and symptom self-reports.

Extremely missing numerical data in Electronic Health Records for machine learning can be managed through simple imputation methods considering informative missingness: A comparative of solutions in a COVID-19 mortality case study

BACKGROUND AND OBJECTIVE

Reusing Electronic Health Records (EHRs) for Machine Learning (ML) leads on many occasions to extremely incomplete and sparse tabular datasets, which can hinder the model development processes and limit their performance and generalization. In this study, we aimed to characterize the most effective data imputation techniques and ML models for dealing with highly missing numerical data in EHRs, in the case where only a very limited number of data are complete, as opposed to the usual case of having a reduced number of missing values.

METHODS

We used a case study including full blood count laboratory data, demographic and survival data in the context of COVID-19 hospital admissions and evaluated 30 processing pipelines combining imputation methods with ML classifiers. The imputation methods included missing mask, translation and encoding, mean imputation, k-nearest neighbors' imputation, Bayesian ridge regression imputation and generative adversarial imputation networks. The classifiers included k-nearest neighbors, logistic regression, random forest, gradient boosting and deep multilayer perceptron.

RESULTS

Our results suggest that in the presence of highly missing data, combining translation and encoding imputation-which considers informative missingness-with tree ensemble classifiers-random forest and gradient boosting-is a sensible choice when aiming to maximize performance, in terms of area under curve.

CONCLUSIONS

Based on our findings, we recommend the consideration of this imputer-classifier configuration when constructing models in the presence of extremely incomplete numerical data in EHR.

Early and fair COVID-19 outcome risk assessment using robust feature selection

Personalized medicine plays an important role in treatment optimization for COVID-19 patient management. Early treatment in patients at high risk of severe complications is vital to prevent death and ventilator use. Predicting COVID-19 clinical outcomes using machine learning may provide a fast and data-driven solution for optimizing patient care by estimating the need for early treatment. In addition, it is essential to accurately predict risk across demographic groups, particularly those underrepresented in existing models. Unfortunately, there is a lack of studies demonstrating the equitable performance of machine learning models across patient demographics. To overcome this existing limitation, we generate a robust machine learning model to predict patient-specific risk of death or ventilator use in COVID-19 positive patients using features available at the time of diagnosis. We establish the value of our solution across patient demographics, including gender and race. In addition, we improve clinical trust in our automated predictions by generating interpretable patient clustering, patient-level clinical feature importance, and global clinical feature importance within our large real-world COVID-19 positive patient dataset. We achieved 89.38% area under receiver operating curve (AUROC) performance for severe outcomes prediction and our robust feature ranking approach identified the presence of dementia as a key indicator for worse patient outcomes. We also demonstrated that our deep-learning clustering approach outperforms traditional clustering in separating patients by severity of outcome based on mutual information performance. Finally, we developed an application for automated and fair patient risk assessment with minimal manual data entry using existing data exchange standards.

Impact of decreased levels of total CO2 on in-hospital mortality in patients with COVID-19

Decreased total CO2 (tCO2) is significantly associated with all-cause mortality in critically ill patients. Because of a lack of data to evaluate the impact of tCO2 in patients with COVID-19, we assessed the impact of tCO2 on all-cause mortality in this study. We retrospectively reviewed the data of hospitalized patients with COVID-19 in two Korean referral hospitals between February 2020 and September 2021. The primary outcome was in-hospital mortality. We assessed the impact of tCO2 as a continuous variable on mortality using the Cox-proportional hazard model. In addition, we evaluated the relative factors associated with tCO2 ≤ 22 mmol/L using logistic regression analysis. In 4,423 patients included, the mean tCO2 was 24.8 ± 3.0 mmol/L, and 17.9% of patients with tCO2 ≤ 22 mmol/L. An increase in mmol/L of tCO2 decreased the risk of all-cause mortality by 4.8% after adjustment for age, sex, comorbidities, and laboratory values. Based on 22 mmol/L of tCO2, the risk of mortality was 1.7 times higher than that in patients with lower tCO2. This result was maintained in the analysis using a cutoff value of tCO2 24 mmol/L. Higher white blood cell count; lower hemoglobin, serum calcium, and eGFR; and higher uric acid, and aspartate aminotransferase were significantly associated with a tCO2 value ≤ 22 mmol/L. Decreased tCO2 significantly increased the risk of all-cause mortality in patients with COVID-19. Monitoring of tCO2 could be a good indicator to predict prognosis and it needs to be appropriately managed in patients with specific conditions.

A risk scoring model of COVID-19 at hospital admission

BACKGROUND

The COVID-19 pandemic has been the most serious public health crisis in recent times, a pandemic whose impact was felt across the globe in various groups and populations. Confronted with an urgent problem, people and governments were forced to make decisions without fully understanding the disease. The present work aims to reinforce our ever-growing knowledge of the illness, particularly in modelling the risk of death of a patient admitted to a hospital with a positive COVID-19 test.

METHODS

Given the simplicity of using and programming logistic regression in any national healthcare unit and the ease of interpreting the results, we chose to use this technique over several other. Using scoring techniques, it is possible to associate the various diagnoses with a numerical value (score), making it possible therefore to integrate the patient's multiple medical conditions as a single continuous variable in the model.

RESULTS

It is possible to establish with good discriminatory capacity (ROC AUC Test = 0.8) which COVID patients are at higher risk when admitted to the healthcare unit-people of advanced age with pre-existing conditions, such as diabetes and high blood pressure, or newly acquired conditions, such as pneumonia. Moreover, males and clinical episodes occurring in healthcare units with few available beds (high healthcare unit occupancy) are also at higher risk. The importance of each variable in predicting the target is: age (47%), sum of comorbidity scores (28%), healthcare unit score (12.0%), gender score (7%) and healthcare unit occupancy (6%).

CONCLUSIONS

Using a dataset with more than 52000 people, it was possible to successfully differentiate likelihood of death by COVID using age, comorbidity information, healthcare unit, healthcare unit occupancy and gender. The age and the comorbidities associated with each patient had a joint contribution of about 75% in explaining the COVID related mortality in Portuguese public hospitals in the period between March 2020 and May 2021.

Comparing machine learning algorithms to predict COVID‑19 mortality using a dataset including chest computed tomography severity score data

Since the beginning of the COVID-19 pandemic, new and non-invasive digital technologies such as artificial intelligence (AI) had been introduced for mortality prediction of COVID-19 patients. The prognostic performances of the machine learning (ML)-based models for predicting clinical outcomes of COVID-19 patients had been mainly evaluated using demographics, risk factors, clinical manifestations, and laboratory results. There is a lack of information about the prognostic role of imaging manifestations in combination with demographics, clinical manifestations, and laboratory predictors. The purpose of the present study is to develop an efficient ML prognostic model based on a more comprehensive dataset including chest CT severity score (CT-SS). Fifty-five primary features in six main classes were retrospectively reviewed for 6854 suspected cases. The independence test of Chi-square was used to determine the most important features in the mortality prediction of COVID-19 patients. The most relevant predictors were used to train and test ML algorithms. The predictive models were developed using eight ML algorithms including the J48 decision tree (J48), support vector machine (SVM), multi-layer perceptron (MLP), k-nearest neighbourhood (k-NN), Naïve Bayes (NB), logistic regression (LR), random forest (RF), and eXtreme gradient boosting (XGBoost). The performances of the predictive models were evaluated using accuracy, precision, sensitivity, specificity, and area under the ROC curve (AUC) metrics. After applying the exclusion criteria, a total of 815 positive RT-PCR patients were the final sample size, where 54.85% of the patients were male and the mean age of the study population was 57.22 ± 16.76 years. The RF algorithm with an accuracy of 97.2%, the sensitivity of 100%, a precision of 94.8%, specificity of 94.5%, F1-score of 97.3%, and AUC of 99.9% had the best performance. Other ML algorithms with AUC ranging from 81.2 to 93.9% had also good prediction performances in predicting COVID-19 mortality. Results showed that timely and accurate risk stratification of COVID-19 patients could be performed using ML-based predictive models fed by routine data. The proposed algorithm with the more comprehensive dataset including CT-SS could efficiently predict the mortality of COVID-19 patients. This could lead to promptly targeting high-risk patients on admission, the optimal use of hospital resources, and an increased probability of survival of patients.

Symptoms, Treatment, and Outcomes of COVID-19 Patients Coinfected with Clostridioides difficile: Single-Center Study from NE Romania during the COVID-19 Pandemic

The Coronavirus disease 2019 (COVID-19) pandemic has brought new challenges across medical disciplines, particularly in infectious disease medicine. In Romania, the incidence of SARS-CoV-2 (Severe acute respiratory syndrome coronavirus 2) infection increased dramatically since March 2020 until March 2022. Antibiotic administration for pulmonary superinfections in COVID-19 intensified and, consequently, increased rates of Clostridioides difficile infection (CDI) were hypothesized. We conducted a single-center, retrospective, observational study on patients from North-Eastern Romania to assess clinical characteristics and outcomes of COVID-19 and Clostridioides difficile (CD) coinfection, and to identify risk factors for CDI in COVID-19 patients. The study enrolled eighty-six CDI and COVID-19 coinfected patients admitted during March 2020-February 2021 (mean age 59.14 years, 53.49% men, 67.44% urban residents) and a group of eighty-six COVID-19 patients. On admission, symptoms were more severe in mono-infected patients, while coinfected patients associated a more intense acute inflammatory syndrome. The main risk factors for severe COVID-19 were smoking, diabetes mellitus, and antibiotic administration. Third generation cephalosporins (55%) and carbapenems (24%) were the main antibiotics used, and carbapenems were significantly associated with severe COVID-19 in patients coinfected with CD during hospitalization. Coinfection resulted in longer hospitalization and poorer outcomes. The extensive use of antibiotics in COVID-19, particularly carbapenems, contributed substantially to CD coinfection.

Predicting Mortality in Hospitalized COVID-19 Patients in Zambia: An Application of Machine Learning

The coronavirus disease 2019 (COVID-19) has wreaked havoc globally, resulting in millions of cases and deaths. The objective of this study was to predict mortality in hospitalized COVID-19 patients in Zambia using machine learning (ML) methods based on factors that have been shown to be predictive of mortality and thereby improve pandemic preparedness. This research employed seven powerful ML models that included decision tree (DT), random forest (RF), support vector machines (SVM), logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and XGBoost (XGB). These classifiers were trained on 1,433 hospitalized COVID-19 patients from various health facilities in Zambia. The performances achieved by these models were checked using accuracy, recall, F1-Score, area under the receiver operating characteristic curve (ROC_AUC), area under the precision-recall curve (PRC_AUC), and other metrics. The best-performing model was the XGB which had an accuracy of 92.3%, recall of 94.2%, F1-Score of 92.4%, and ROC_AUC of 97.5%. The pairwise Mann-Whitney U-test analysis showed that the second-best model (GB) and the third-best model (RF) did not perform significantly worse than the best model (XGB) and had the following: GB had an accuracy of 91.7%, recall of 94.2%, F1-Score of 91.9%, and ROC_AUC of 97.1%. RF had an accuracy of 90.8%, recall of 93.6%, F1-Score of 91.0%, and ROC_AUC of 96.8%. Other models showed similar results for the same metrics checked. The study successfully derived and validated the selected ML models and predicted mortality effectively with reasonably high performance in the stated metrics. The feature importance analysis found that knowledge of underlying health conditions about patients' hospital length of stay (LOS), white blood cell count, age, and other factors can help healthcare providers offer lifesaving services on time, improve pandemic preparedness, and decongest health facilities in Zambia and other countries with similar settings.

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).

Prognostic models in COVID-19 infection that predict severity: a systematic review

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

Factors associated with COVID-19 fatality among patients admitted in Mashonaland West Province, Zimbabwe 2020-2022: a secondary data analysis

Introduction

approximately 15% of COVID-19 patients develop symptoms necessitating admission. From 2020 to 2022, Mashonaland West Province had an institutional case fatality rate of 23% against a national rate of 7%. Therefore, we evaluated the COVID-19 admissions in the province to determine the factors associated with COVID-19 mortality.

Methods

we conducted an analytical cross-sectional study based on secondary data from isolation centers across the province using all 672 death audit forms and patient records. We obtained data on patient demographics, signs and symptoms, clinical management and oxygen therapy administered, among other things. Data were entered into an electronic form and imported into Epi-info 7 for analysis bivariate and multivariate conducted. Results: we found that being an older man, aOR 1.04 (1.03-1.05), who had diabetes aOR 6.0 (95% CI: 3.8-9.2) and hypertension aOR 4.5 (95% CI: 2.8-6.5) were independent risk factors. Patients put on dexamethasone aOR 2.4 (95% CI: 1.6-3.4) and heparin/clexane aOR 1.6 (95% CI: 1.1-2.2) had a higher mortality risk. However, vitamin C aOR 0.48 (95% CI: 0.31-0.71) and oxygen therapy aOR 0.14 (95% CI: 0.10-0.19) and being pregnant aOR 0.06 (95% CI: 0.02-0.14) were protective. Conclusion: mortality risk increased in older male patients with comorbidities and with those on dexamethasone and heparin therapy. Oxygen therapy and vitamin C were protective. There is a need to conduct further study of the source of these variations in risk across patients to establish the true impact of differences in individuals' mortality.

A machine learning analysis of correlates of mortality among patients hospitalized with COVID-19

It is vital to determine how patient characteristics that precede COVID-19 illness relate to COVID-19 mortality. This is a retrospective cohort study of patients hospitalized with COVID-19 across 21 healthcare systems in the US. All patients (N = 145,944) had COVID-19 diagnoses and/or positive PCR tests and completed their hospital stays from February 1, 2020 through January 31, 2022. Machine learning analyses revealed that age, hypertension, insurance status, and healthcare system (hospital site) were especially predictive of mortality across the full sample. However, multiple variables were especially predictive in subgroups of patients. The nested effects of risk factors such as age, hypertension, vaccination, site, and race accounted for large differences in mortality likelihood with rates ranging from about 2-30%. Subgroups of patients are at heightened risk of COVID-19 mortality due to combinations of preadmission risk factors; a finding of potential relevance to outreach and preventive actions.

COVID-19 Adverse Outcomes in Immunocompromised Patients

Background: Coronavirus disease 2019 (COVID-19) is a devastating viral pandemic infecting millions of people with a wide range of symptoms from fever to death. It has been suggested that immunocompromised patients are at a higher risk of severe disease, poor clinical outcomes, and mortality. However, these patients’ risk factors and COVID-19-related outcomes are not well characterized. Objectives: We evaluated the COVID-19-related outcomes among immunocompromised patients ranging from solid tumors, hematological malignancies, and HIV to autoimmune disease and transplant recipients who received immunosuppressive agents. We also aimed at finding risk factors related to mortality among immunocompromised patients with COVID-19. Methods: This cross-sectional study was conducted in Khansari Hospital, Iran between March and November 2021. We included immunocompromised patients with nasal swab positive SARS-CoV-2 polymerase chain reaction (PCR) results in the study. Patient outcomes, including hospitalization ward and the mortality rate, were assessed till three months after COVID-19 infection were evaluated in all patients. Moreover, the relation between risk factors and the rate of the mortality rate was analyzed in immunocompromised patients with COVID-19. Results: A total number of 74 immunocompromised patients with solid tumors, hematologic malignancies, autoimmune diseases, acquired immunodeficiencies, and solid-organ transplant recipients were included in the study. Results indicated that the male gender and ICU hospitalization significantly increase the mortality risk. Surprisingly, chemotherapy is associated with a lower risk of mortality. Conclusions: Identifying the risk factors can improve the decision-making on cancer patients’ management during the COVID-19 infection. A further large cohort of patients would be required to identify risk factors relating to poor clinical outcomes and mortality rates in immunocompromised patients with COVID-19.

Descriptive Assessment of Race, Ethnicity, Comorbidities, and SARS-CoV-2 Infection- Fatality in North Carolina

Background

SARS-CoV-2 infection has caused variable clinical outcomes including hospitalization and death. We analyzed state-level data from the North Carolina COVID-19 Surveillance System (NC COVID) to describe demographics of those infected with SARS-CoV-2 and to describe factors associated with infection-fatality in North Carolina.

Methods

This was a retrospective cohort study using surveillance data on positive SARS-CoV-2-infected individuals (N = 214,179) identified between March 1, 2020, and September 30, 2020. We present descriptive statistics and associations among demographics, medical comorbidities, and SARS-CoV-2 infection-fatality.

Results

Median age for residents with reported SARS-CoV-2 was 38 (IQR 23-54). Age was strongly correlated with SARS-CoV-2 infection-fatality. Greater infection-fatality was noted among those who identified as Black across all comorbidities. Coexisting chronic disease was associated with greater infection-fatality, with kidney disease demonstrating the strongest association.

Limitations

A high percentage of missing data for race/ethnicity and comorbidities limits the interpretation of our findings. Data were not available for socioeconomic measures that could aid in better understanding inequities associated with SARS-CoV-2 infection-fatality.

Conclusions

Among North Carolinians identified with SARS-CoV-2 via surveillance efforts, age, race, and comorbidities were associated with infection-fatality; these findings are similar to those of studies using different source populations in the United States. In addition to age and other nonmodifiable variables, systematic differences in social conditions and opportunity may increase the risk of SARS-CoV-2 infection-fatality among Black Americans compared to other races/ethnicities.

Validation of a specialized evaluation system for COVID-19 in Japan: A retrospective, multicenter cohort study

INTRODUCTION

Evaluation of a severity grade (SG) is important to classify patients for efficient use of limited medical resources. This study validates two existing evaluation systems for the prevention of the coronavirus disease 2019 (COVID-19) in Japan: a criterion of SG and a list of 14 specialized underlying diseases (SUDs).

METHODS

A retrospective cohort was created using electronic medical records from 18 research institutes. The cohort includes 6,050 COVID-19 patients with two types of diagnosis information as follows: SG at hospitalization among mild, moderate I, moderate II, and severe and aggravation after hospitalization.

RESULTS

A crude mortality rate and an aggravation rate increased by the worsening of SG in the COVID-19 cohort. The transition of the aggravation rate was notable for COVID-19 patients with SUD. A conditional probability of the mortality given the aggravation in the COVID-19 cohort was 87.4% compared to mild or moderate patients (approximately 21%-45%) who have the possibility of the aggravation. An odds ratio of the mortality and aggravation information about the SUD list was higher than other variables.

CONCLUSIONS

We demonstrated the possibility of improving the criteria of SG by including the SUD list for more effective operation of the criteria of SG. Furthermore, we demonstrated the importance of the prevention of the aggravation based on the conditional probability, and the possibility of predicting the aggravation using the risk factors.

Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset

The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48-71), 46% women]. We also proposed new original population-based meta-features that have not been devised in the literature. Stacking has shown to achieve the best results reported in the literature for the death prediction task, improving over previous state-of-the-art by more than 46% in Recall for predicting death, with AUROC 0.826 and MacroF1 of 65.4%. The newly proposed meta-features were highly discriminative of death, but fell short in producing large improvements in final prediction performance, demonstrating that we are possibly on the limits of the prediction capabilities that can be achieved with the current set of ML techniques and (meta-)features. Finally, we investigated how the trained models perform on different hospitals, showing that there are indeed large differences in classifier performance between different hospitals, further making the case that errors are produced by factors that cannot be modeled with the current predictors.

Impact of days elapsed from the onset of symptoms to hospitalization in COVID-19 in-hospital mortality: time matters

BACKGROUND

COVID-19 shows different clinical and pathophysiological stages over time. The effect of days elapsed from the onset of symptoms (DEOS) to hospitalization on COVID-19 prognostic factors remains uncertain. We analyzed the impact on mortality of DEOS to hospitalization and how other independent prognostic factors perform when taking this time elapsed into account.

METHODS

This retrospective, nationwide cohort study, included patients with confirmed COVID-19 from February 20th and May 6th, 2020. The data was collected in a standardized online data capture registry. Univariate and multivariate COX-regression were performed in the general cohort and the final multivariate model was subjected to a sensitivity analysis in an early presenting (EP; <5 DEOS) and late presenting (LP; ≥5 DEOS) group.

RESULTS

7,915 COVID-19 patients were included in the analysis, 2,324 in the EP and 5,591 in the LP group. DEOS to hospitalization was an independent prognostic factor of in-hospital mortality in the multivariate Cox regression model along with other 9 variables. Each DEOS increment accounted for a 4,3% mortality risk reduction (HR 0.957; 95% CI 0.93 - 0.98). Regarding variations in other mortality predictors in the sensitivity analysis, the Charlson Comorbidity Index only remained significant in the EP group while D-dimer only remained significant in the LP group.

CONCLUSION

When caring for COVID-19 patients, DEOS to hospitalization should be considered as their need for early hospitalization confers a higher risk of mortality. Different prognostic factors vary over time and should be studied within a fixed timeframe of the disease.

Prediction of mortality risk and duration of hospitalization of COVID-19 patients with chronic comorbidities based on machine learning algorithms

Background

The severity of coronavirus (COVID-19) in patients with chronic comorbidities is much higher than in other patients, which can lead to their death. Machine learning (ML) algorithms as a potential solution for rapid and early clinical evaluation of the severity of the disease can help in allocating and prioritizing resources to reduce mortality.

Objective

The objective of this study was to predict the mortality risk and length of stay (LoS) of patients with COVID-19 and history of chronic comorbidities using ML algorithms.

Methods

This retrospective study was conducted by reviewing the medical records of COVID-19 patients with a history of chronic comorbidities from March 2020 to January 2021 in Afzalipour Hospital in Kerman, Iran. The outcome of patients, hospitalization was recorded as discharge or death. The filtering technique used to score the features and well-known ML algorithms were applied to predict the risk of mortality and LoS of patients. Ensemble Learning methods is also used. To evaluate the performance of the models, different measures including F1, precision, recall, and accuracy were calculated. The TRIPOD guideline assessed transparent reporting.

Results

This study was performed on 1291 patients, including 900 alive and 391 dead patients. Shortness of breath (53.6%), fever (30.1%), and cough (25.3%) were the three most common symptoms in patients. Diabetes mellitus(DM) (31.3%), hypertension (HTN) (27.3%), and ischemic heart disease (IHD) (14.2%) were the three most common chronic comorbidities of patients. Twenty-six important factors were extracted from each patient's record. Gradient boosting model with 84.15% accuracy was the best model for predicting mortality risk and multilayer perceptron (MLP) with rectified linear unit function (MSE = 38.96) was the best model for predicting the LoS. The most common chronic comorbidities among these patients were DM (31.3%), HTN (27.3%), and IHD (14.2%). The most important factors in predicting the risk of mortality were hyperlipidemia, diabetes, asthma, and cancer, and in predicting LoS was shortness of breath.

Conclusion

The results of this study showed that the use of ML algorithms can be a good tool to predict the risk of mortality and LoS of patients with COVID-19 and chronic comorbidities based on physiological conditions, symptoms, and demographic information of patients. The Gradient boosting and MLP algorithms can quickly identify patients at risk of death or long-term hospitalization and notify physicians to do appropriate interventions.

Context and Considerations for the Development of Community-Informed Health Communication Messaging to Support Equitable Uptake of COVID-19 Vaccines Among Communities of Color in Washington, DC

BACKGROUND

Communities of color have been disproportionately impacted by COVID-19. We explored barriers and facilitators to COVID-19 vaccine uptake among African American, Latinx, and African immigrant communities in Washington, DC.

METHODS

A total of 76 individuals participated in qualitative interviews and focus groups, and 208 individuals from communities of color participated in an online crowdsourcing contest.

RESULTS

Findings documented a lack of sufficient, accurate information about COVID-19 vaccines and questions about the science. African American and African immigrant participants spoke about the deeply rooted historical underpinnings to their community's vaccine hesitancy, citing the prior and ongoing mistreatment of people of color by the medical community. Latinx and African immigrant participants highlighted how limited accessibility played an important role in the slow uptake of COVID-19 vaccines in their communities. Connectedness and solidarity were found to be key assets that can be drawn upon through community-driven responses to address social-structural challenges to COVID-19 related vaccine uptake.

CONCLUSIONS

The historic and ongoing socio-economic context and realities of communities of color must be understood and respected to inform community-based health communication messaging to support vaccine equity for COVID-19 and other infectious diseases.

Dietary, comorbidity, and geo-economic data fusion for explainable COVID-19 mortality prediction

Many factors significantly influence the outcomes of infectious diseases such as COVID-19. A significant focus needs to be put on dietary habits as environmental factors since it has been deemed that imbalanced diets contribute to chronic diseases. However, not enough effort has been made in order to assess these relations. So far, studies in the field have shown that comorbid conditions influence the severity of COVID-19 symptoms in infected patients. Furthermore, COVID-19 has exhibited seasonal patterns in its spread; therefore, considering weather-related factors in the analysis of the mortality rates might introduce a more relevant explanation of the disease's progression. In this work, we provide an explainable analysis of the global risk factors for COVID-19 mortality on a national scale, considering dietary habits fused with data on past comorbidity prevalence and environmental factors such as seasonally averaged temperature geolocation, economic and development indices, undernourished and obesity rates. The innovation in this paper lies in the explainability of the obtained results and is equally essential in the data fusion methods and the broad context considered in the analysis. Apart from a country's age and gender distribution, which has already been proven to influence COVID-19 mortality rates, our empirical analysis shows that countries with imbalanced dietary habits generally tend to have higher COVID-19 mortality predictions. Ultimately, we show that the fusion of the dietary data set with the geo-economic variables provides more accurate modeling of the country-wise COVID-19 mortality rates with respect to considering only dietary habits, proving the hypothesis that fusing factors from different contexts contribute to a better descriptive analysis of the COVID-19 mortality rates.

Predictive Factors of Death and the Clinical Profile of Hospitalized Covid-19 Patients in Morocco: A One-Year Mixed Cohort Study

Background Since the onset of the Covid-19 pandemic, several studies have been conducted around the world in an attempt to understand this heterogeneous and unpredictable disease and to prevent related death. It was therefore necessary to study the associated risk factors of Covid-19-related mortality. Objectives The aim of this study was to describe the clinical profile and to identify the factors associated with mortality of patients with Covid-19 in Morocco. Methods We performed a mixed cohort study (retrospective and prospective) of 615 in-patients with Covid-19 disease, enrolled between August 2020 and October 2021. We followed the cohort throughout the hospitalization until discharge and 30 days thereafter. Results The median age was 64 years old; 62.1% of the patients were male. The mean time from symptom onset to hospitalization was 8.5 days (±4.67), and 68.1% of patients had comorbidities. On admission, the most common symptoms were dyspnea (82.2%), cough (80.3%), and fever (76.8%). The main follow-up complication was secondary infection (56.9%). Based on univariate analysis, male gender (p<0.008 and brut relative risk {_bRR}=1.57), advanced age (p<0.001), lung involvement (p<0.001), lymphopenia (p<0.001 and _bRR=2.32), D-dimers of >500 µg/l (p<0.007 and _bRR=2.47), C-reactive protein (CRP) of >130 mg/l (p<0.001 and _bRR=2.45), elevated creatinine (p<0.013 and _bRR=1.61), lactate dehydrogenase (LDH) of >500 U/l (p<0.001 and _bRR=7.16), receiving corticosteroids (p<0.001 and _bRR=5.08), invasive ventilation (p<0.001 and _bRR=30.10), the stay in the resuscitation unit (p<0.001 and _bRR=13.37), and acute respiratory distress syndrome (ARDS) (p<0.001 and _bRR=10.98) were associated with a higher risk of death. In the opposite, receiving azithromycin and hydroxychloroquine (p<0.001 and _bRR=0.28) and pre-admission anticoagulants (p<0.005 and _bRR=0.46) was associated with a lower risk of mortality. Multivariate regression analysis showed that age of >60 years (p<0.001 and adjusted odds ratio {aOR}=4.90), the use of invasive ventilation (p<0.001 and aOR=9.60), the stay in the resuscitation unit (p<0.001 and aOR=5.09), and acute respiratory distress syndrome (p<0.001 and aOR=6.49) were independent predictors of Covid-19 mortality. Conclusion In this cohort study focusing on Covid-19 in-patient's mortality, we found that age of >60 years, the use of invasive ventilation, the stay in the resuscitation unit, and acute respiratory distress syndrome were independent predictors of Covid-19 mortality. The results of this study can be used to improve knowledge for better clinical management of Covid-19 in-patients.

Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study

The unprecedented global crisis brought about by the COVID-19 pandemic has sparked numerous efforts to create predictive models for the detection and prognostication of SARS-CoV-2 infections with the goal of helping health systems allocate resources. Machine learning models, in particular, hold promise for their ability to leverage patient clinical information and medical images for prediction. However, most of the published COVID-19 prediction models thus far have little clinical utility due to methodological flaws and lack of appropriate validation. In this paper, we describe our methodology to develop and validate multi-modal models for COVID-19 mortality prediction using multi-center patient data. The models for COVID-19 mortality prediction were developed using retrospective data from Madrid, Spain (N = 2547) and were externally validated in patient cohorts from a community hospital in New Jersey, USA (N = 242) and an academic center in Seoul, Republic of Korea (N = 336). The models we developed performed differently across various clinical settings, underscoring the need for a guided strategy when employing machine learning for clinical decision-making. We demonstrated that using features from both the structured electronic health records and chest X-ray imaging data resulted in better 30-day mortality prediction performance across all three datasets (areas under the receiver operating characteristic curves: 0.85 (95% confidence interval: 0.83-0.87), 0.76 (0.70-0.82), and 0.95 (0.92-0.98)). We discuss the rationale for the decisions made at every step in developing the models and have made our code available to the research community. We employed the best machine learning practices for clinical model development. Our goal is to create a toolkit that would assist investigators and organizations in building multi-modal models for prediction, classification, and/or optimization.

Niakan Kalhori S, Abooei AH, Gholamzadeh M, Ayyoubzadeh SM. Prediction of COVID-19 Patients' Survival by Deep Learning Approaches

Background: Despite many studies done to predict severe coronavirus 2019 (COVID-19) patients, there is no applicable clinical prediction model to predict and distinguish severe patients early. Based on laboratory and demographic data, we have developed and validated a deep learning model to predict survival and assist in the triage of COVID-19 patients in the early stages. Methods: This retrospective study developed a survival prediction model based on the deep learning method using demographic and laboratory data. The database consisted of data from 487 patients with COVID-19 diagnosed by the reverse transcription-polymerase chain reaction test and admitted to Imam Khomeini hospital affiliated to Tehran University of Medical Sciences from February 21, 2020, to June 24, 2020. Results: The developed model achieved an area under the curve (AUC) of 0.96 for survival prediction. The results demonstrated the developed model provided high precision (0.95, 0.93), recall (0.90,0.97), and F1-score (0.93,0.95) for low- and high-risk groups. Conclusion: The developed model is a deep learning-based, data-driven prediction tool that can predict the survival of COVID-19 patients with an AUC of 0.96. This model helps classify admitted patients into low-risk and high-risk groups and helps triage patients in the early stages.

Autoimmune disease and COVID-19: a multicentre observational study in the United Kingdom

OBJECTIVE

To establish the demographic characteristics, laboratory findings and clinical outcomes in patients with autoimmune disease (AD) compared with a propensity-matched cohort of patients without AD admitted with COVID-19 to hospitals in the UK.

METHODS

This is a multicentre observational study across 26 NHS Trusts. Data were collected both retrospectively and prospectively using a predesigned standardized case record form. Adult patients (≥18 years) admitted between 1 April 2020 and 31 July 2020 were included.

RESULTS

Overall, 6288 patients were included to the study. Of these, 394 patients had AD prior to admission with COVID-19. Of 394 patients, 80 patients with SLE, RA or aPL syndrome were classified as severe rheumatologic AD. A higher proportion of those with AD had anaemia [240 (60.91%) vs 206 (52.28%), P = 0.015], elevated LDH [150 (38.08%) vs 43 (10.92%), P < 0.001] and raised creatinine [122 (30.96%) vs 86 (21.83%), P = 0.01], respectively. A significantly higher proportion of patients with severe rheumatologic AD had elevated CRP [77 (96.25%) vs 70 (87.5%), P = 0.044] and LDH [20 (25%) vs 6 (7.5%), P = 0.021]. Patients with severe rheumatologic AD had significantly higher mortality [32/80 (40%)] compared with propensity matched cohort of patients without AD [20/80 (25%), P = 0.043]. However, there was no difference in 180-day mortality between propensity-matched cohorts of patients with or without AD in general (P = 0.47).

CONCLUSIONS

Patients with severe rheumatologic AD had significantly higher mortality. Anaemia, renal impairment and elevated LDH were more frequent in patients with any AD while elevated CRP and LDH were more frequent in patients with severe rheumatologic AD both of which have been shown to associate with increased mortality in patients with COVID-19.

Assessment of SARS-CoV-2 vaccination status in SARS-COV-2 infected patients admitted in Dr Ruth K.M. Pfau, Civil Hospital Karachi

OBJECTIVES

To determine the frequency of vaccination status in patients with SARS-CoV-2 infection.

METHODS

This case-control study was conducted at Dr Ruth KM Pfau Civil Hospital Karachi, Pakistan between September 2021 to October 2021. All patients who had positive PCR on nasopharyngeal swab for SARS-CoV-2 infection were included. Information regarding vaccination status and brand of vaccination administered and duration between the last dose of vaccine and positive PCR was noted. The disease status of patients was classified on admission into severe and non-severe disease.

RESULTS

Study included 143 patients, out of which 58 (40.6%) were males and 85 (59.4%) were females. Majority of our patients (78.3%) were unvaccinated. Frequency of Severe SARS-CoV-2 Infection in fully vaccinated patients was less than in unvaccinated patients. The odds of developing severe COVID infection in unvaccinated patients versus vaccinated was 8.55 times higher (OR = 6.23, 95% CI 2.58-28.35). Proportion of vaccinated females was less as compared to males. Significant differences were found in severity between hypertension (p<.001), diabetes (<.001) and age (p<.001).

CONCLUSION

The frequency of SARS-CoV-2 infection was greater in unvaccinated patients. The odds of developing severe COVID infection in unvaccinated patients versus vaccinated was 8.55 times higher.

Elevated vascular transformation blood biomarkers in Long-COVID indicate angiogenesis as a key pathophysiological mechanism

BACKGROUND

Long-COVID is characterized by prolonged, diffuse symptoms months after acute COVID-19. Accurate diagnosis and targeted therapies for Long-COVID are lacking. We investigated vascular transformation biomarkers in Long-COVID patients.

METHODS

A case-control study utilizing Long-COVID patients, one to six months (median 98.5 days) post-infection, with multiplex immunoassay measurement of sixteen blood biomarkers of vascular transformation, including ANG-1, P-SEL, MMP-1, VE-Cad, Syn-1, Endoglin, PECAM-1, VEGF-A, ICAM-1, VLA-4, E-SEL, thrombomodulin, VEGF-R2, VEGF-R3, VCAM-1 and VEGF-D.

RESULTS

Fourteen vasculature transformation blood biomarkers were significantly elevated in Long-COVID outpatients, versus acutely ill COVID-19 inpatients and healthy controls subjects (P < 0.05). A unique two biomarker profile consisting of ANG-1/P-SEL was developed with machine learning, providing a classification accuracy for Long-COVID status of 96%. Individually, ANG-1 and P-SEL had excellent sensitivity and specificity for Long-COVID status (AUC = 1.00, P < 0.0001; validated in a secondary cohort). Specific to Long-COVID, ANG-1 levels were associated with female sex and a lack of disease interventions at follow-up (P < 0.05).

CONCLUSIONS

Long-COVID patients suffer prolonged, diffuse symptoms and poorer health. Vascular transformation blood biomarkers were significantly elevated in Long-COVID, with angiogenesis markers (ANG-1/P-SEL) providing classification accuracy of 96%. Vascular transformation blood biomarkers hold potential for diagnostics, and modulators of angiogenesis may have therapeutic efficacy.

External Validation of Mortality Scores among High-Risk COVID-19 Patients: A Romanian Retrospective Study in the First Pandemic Year

Background: We aimed to externally validate three prognostic scores for COVID-19: the 4C Mortality Score (4CM Score), the COVID-GRAM Critical Illness Risk Score (COVID-GRAM), and COVIDAnalytics. Methods: We evaluated the scores in a retrospective study on adult patients hospitalized with severe/critical COVID-19 (1 March 2020–1 March 2021), in the Teaching Hospital of Infectious Diseases, Cluj-Napoca, Romania. We assessed all the deceased patients matched with two survivors by age, gender, and at least two comorbidities. The areas under the receiver-operating characteristic curves (AUROCs) were computed for in-hospital mortality. Results: Among 780 severe/critical COVID-19 patients, 178 (22.8%) died. We included 474 patients according to the case definition (158 deceased/316 survivors). The median age was 75 years; diabetes mellitus, malignancies, chronic pulmonary diseases, and chronic kidney and moderate/severe liver diseases were associated with higher risks of death. According to the predefined 4CM Score, the mortality rates were 0% (low), 13% (intermediate), 27% (high), and 61% (very high). The AUROC for the 4CM Score was 0.72 (95% CI: 0.67–0.77) for in-hospital mortality, close to COVID-GRAM, with slightly greater discriminatory ability for COVIDAnalytics: 0.76 (95% CI: 0.71–0.80). Conclusion: All the prognostic scores showed close values compared to their validation cohorts, were fairly accurate in predicting mortality, and can be used to prioritize care and resources.