COVID-19 Chest CT Quantification: Triage and Prognostic Value in Different Ages.

Objective: We evaluated the triage and prognostic performance of seven proposed computed tomography (CT)-severity score (CTSS) systems in two different age groups.Design: Retrospective study.Setting: COVID-19 pandemic.Participants: Admitted COVID-19, PCR-positive patients were included, excluding patients with heart failure and significant pre-existing pulmonary disease.Methods: Patients were divided into two age groups: ≥65 years and ≤64 years. Clinical data indicating disease severity at presentation and at peak disease severity were recorded. Initial CT images were scored by two radiologists according to seven CTSSs (CTSS1-CTSS7). Receiver operating characteristic (ROC) analysis for the performance of each CTSS in diagnosing severe/critical disease on admission (triage performance) and at peak disease severity (prognostic performance) was done for the whole cohort and each age group separately.Results: Included were 96 patients. Intraclass correlation coefficient (ICC) between the two radiologists scoring the CT scan images were good for all the CTSSs (ICC=0.764-0.837). In the whole cohort, all CTSSs showed an unsatisfactory area under the curve (AUC) in the ROC curve for triage, excluding CTSS2 (AUC=0.700), and all CTSSs showed acceptable AUCs for prognostic usage (0.759-0.781). In the older group (≥65 years; n=55), all CTSSs excluding CTSS6 showed excellent AUCs for triage (0.804-0.830), and CTSS6 was acceptable (AUC=0.796); all CTSSs showed excellent or outstanding AUCs for prognostication (0.859-0.919). In the younger group (≤64 years; n=41), all CTSSs showed unsatisfactory AUCs for triage (AUC=0.487-0.565) and prognostic usage (AUC=0.668-0.694), excluding CTSS6, showing marginally acceptable AUC for prognostic performance (0.700).Conclusion: Those CTSSs requiring more numerous segmentations, namely CTSS2, CTSS7, and CTSS5 showed the best ICCs; therefore, they are the best when comparison between two separate scores is needed. Irrespective of patients' age, CTSSs show minimal value in triage and acceptable prognostic value in COVID-19 patients. CTSS performance is highly variable in different age groups. It is excellent in those aged ≥65 years, but has little if any value in younger patients. Multicenter studies with larger sample size to evaluate results of this study should be conducted.

Machine Learning-Based Identifications of COVID-19 Fake News Using Biomedical Information Extraction

The spread of fake news related to COVID-19 is an infodemic that leads to a public health crisis. Therefore, detecting fake news is crucial for an effective management of the COVID-19 pandemic response. Studies have shown that machine learning models can detect COVID-19 fake news based on the content of news articles. However, the use of biomedical information, which is often featured in COVID-19 news, has not been explored in the development of these models. We present a novel approach for predicting COVID-19 fake news by leveraging biomedical information extraction (BioIE) in combination with machine learning models. We analyzed 1164 COVID-19 news articles and used advanced BioIE algorithms to extract 158 novel features. These features were then used to train 15 machine learning classifiers to predict COVID-19 fake news. Among the 15 classifiers, the random forest model achieved the best performance with an area under the ROC curve (AUC) of 0.882, which is 12.36% to 31.05% higher compared to models trained on traditional features. Furthermore, incorporating BioIE-based features improved the performance of a state-of-the-art multi-modality model (AUC 0.914 vs. 0.887). Our study suggests that incorporating biomedical information into fake news detection models improves their performance, and thus could be a valuable tool in the fight against the COVID-19 infodemic. © 2023 by the authors.

Hematological and biochemical parameters can triage COVID-19 patients

Objectives: To reveal the importance of the laboratory routine determination of some hematological, coagulation and biochemical parameters in the prognosis of COVID-19. Materials and methods: The basic characteristic information such as age, gender, clinical symptoms and the clinical laboratory data of 300 COVID-19 patients that were admitted to the Respiratory Care Unit, Al-lmam Al-Hussein Medical City, Kerbala, Iraq were obtained from the patients' records. The patients were 146 males and 154 females, their ages were between 20 and 50 years (34.3±8.6). Results: According to their clinical status, patients were divided into moderate and severe groups. Among the 300 patients, 177 were considered as moderate cases and 123 were severe cases. Ferritin, D-Dimer, and C-reactive protein (CRP) levels were significantly higher in severe cases (P<0.05), as were lymphocytes and white blood cells (WBC) levels (P=0.0001). Hematocrit and hemoglobin were at almost the same levels in both groups (P>0.05). Platelet counts showed normal values in moderate and severe cases. In severe cases, lactate dehydrogenase (LDH) was significantly increased (P=0.0001). The receiver operating characteristic (ROC) curve exhibited that WBC, D-Dimer and LDH have fair values regarding the discriminative ability between the moderate and severe groups (AUC 0.788, 0.718 and 0.761, respectively, P-value of 0.0001). Conclusion: The laboratory routine determination is of a key importance in the prognosis and handling of the cases of COVID-19, especially those that could develop acute respiratory failure, so further deterioration can be avoided.

Increasing the Level of Neopterin in patients infected with SARS-CoV-2 Indicates Fatal Mortality

Background: The severity of Coronavirus Disease-2019 (COVID-19) cases is associated with hyperinflammation. Patients with critical and severe COVID-19 have been observed to have high amounts of circulating cytokines. Neopterin, a crucial cytokine in the antiviral immune response that is released by macrophages upon stimulation with interferon-gamma, can be utilized to forecast the severity of illness in COVID-19 patients. Methods: The study included 185 patients with COVID-19. The patients with COVID-19 were divided into three groups according to disease severity as critical disease (n=51), severe disease (n=81), and moderate disease (n=53). All basic demographic and clinical data of the patients were recorded and blood samples were collected. Results: Neopterin levels were significantly higher in critical COVID-19 patients compared with severe and moderate COVID-19 patients (p < 0.0001). Further, neopterin showed significantly higher levels in the age group >50 years of patients with COVID-19 than in the age group <50 years. Neopterin levels were correlated with WBCs, Platelet, CRP, D-Dimer, Ferritin, Fibrinogen, IL-6, and Procalcitonin levels positively (ρ= 0.569, 0.474, 0.338, 0.696, 0.605, 0.77, 0.727, and 0.585;p < 0.01 respectively), and correlated with BMI, SpO2, and lymphocyte negatively (ρ= - 0.165;p < 0.05, p= - 0.754, - 0. 548;p < 0.01 respectively). A cutoff value of 23.62 nmol/L for neopterin predicted COVID-19 with a sensitivity of 95.7% and a specificity of 95.5% (AUC: 0.986;p < 0.0001). Conclusion: Neopterin may be a useful prognostic biomarker for assessing the severity of COVID-19.

On summary ROC curve for dichotomous diagnostic studies: an application to meta-analysis of COVID-19.

In a systematic review of a diagnostic performance, summarizing performance metrics is crucial. There are various summary models in the literature, and hence model selection becomes inevitable. However, most existing large-sample-based model selection approaches may not fit in a meta-analysis of diagnostic studies, typically having a rather small sample size. Researchers need to effectively determine the final model for further inference, which motivates this article to investigate existing methods and to suggest a more robust method for this need. We considered models covering several widely-used methods for bivariate summary of sensitivity and specificity. Simulation studies were conducted based on different number of studies and different population sensitivity and specificity. Then final models were selected using several existing criteria, and we compared the summary receiver operating characteristic (sROC) curves to the theoretical ROC curve given the generating model. Even though parametric likelihood-based criteria are often applied in practice for their asymptotic property, they fail to consistently choose appropriate models under the limited number of studies. When the number of studies is as small as 10 or 5, our suggestion is best in different scenarios. An example for summary ROC curves for chemiluminescence immunoassay (CLIA) used in COVID-19 diagnosis is also illustrated.

Identification of DNA methylation change in TCF7L2 gene in the blood of type 2 diabetes mellitus as a predictive biomarker in Iraq Kurdistan region by using methylation-specific PCR.

Objective. Nowadays, type 2 diabetes mellitus (T2D) is the most common chronic endocrine disorder affecting an estimated 5-10% of adults worldwide, and this disease also rapidly increased among the population in the Kurdistan region. This research aims to identify DNA methylation change in the TCF7L2 gene as a possible predictive T2D biomarker. Methods. One hundred and thirteen participants were divided into three groups: diabetic (47), prediabetic (36), and control (30). The study was carried out in patients who visited the private clinical sector between August and December 2021 in Koya city (Iraq Kurdistan region) to determine DNA methylation status using a methylation-specific PCR (MSP) with paired primers for each methylated and non-methylated region. In addition, the X2 Kruskal-Wallis statistical and Wilcoxon signed-rank tests were used, p<0.05 was considered significant. Results. The results showed hypermethylation of DNA in the promoter region in diabetic and prediabetic groups compared to the healthy controls. Different factors affected the DNA methylation level, including body max index, alcohol consumption, family history, and physical activity with the positive Coronavirus. Conclusion. The results obtained indicate that DNA methylation changes in the TCF7L2 promoter region may be used as a potential predictive biomarker of the T2D diagnosis. However, the findings obtained in this study should be supported by additional data.

Real-Time Health Monitoring System Using Predictive Analytics

Medical specialists are primarily interested in researching health care as a potential replacement for conventional healthcare methods nowadays. COVID-19 creates chaos in society regardless of the modern technological evaluation involved in this sector. Due to inadequate medical care and timely, accurate prognoses, many unexpected fatalities occur. As medical applications have expanded in their reaches along with their technical revolution, therefore patient monitoring systems are getting more popular among the medical actors. The Internet of Things (IoT) has met the requirements for the solution to deliver such a vast service globally at any time and in any location. The suggested model shows a wearable sensor node that the patients will wear. Monitoring client metrics like blood pressure, heart rate, temperature, etc., is the responsibility of the sensor nodes, which send the data to the cloud via an intermediary node. The sensor-acquired data are stored in the cloud storage for detailed analysis. Further, the stored data will be normalized and processed across various predictive models. Among the different cloud-based predictive models now being used, the model having the highest accuracy will be treated as the resultant model. This resultant model will be further used for the data dissemination mechanism by which the concerned medical actors will be provided an alert message for a proper medication in a desirable manner. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A rank-based approach to design and analysis of pretest-posttest randomized trials, with application to COVID-19 ordinal scale data.

Randomized controlled trials with a pretest-posttest design frequently yield ordered categorical outcome data. Focusing on the estimation of the win probability that a treated participant would have a better score than (or win over) a control participant, we developed methods for analysis and sample size planning for such trials. We exploited the analysis of covariance framework with the dependent variable being individual participants' win fractions at posttest and the covariate being the win fractions at pretest. The win fractions were obtained using the mid-ranks of the ordinal data. Simulation evaluation based on a recent randomized trial on COVID-19 suggests that the methods perform very well. A sample SAS code for data analysis is presented.

Real-Time Health Monitoring System Using Predictive Analytics

Medical specialists are primarily interested in researching health care as a potential replacement for conventional healthcare methods nowadays. COVID-19 creates chaos in society regardless of the modern technological evaluation involved in this sector. Due to inadequate medical care and timely, accurate prognoses, many unexpected fatalities occur. As medical applications have expanded in their reaches along with their technical revolution, therefore patient monitoring systems are getting more popular among the medical actors. The Internet of Things (IoT) has met the requirements for the solution to deliver such a vast service globally at any time and in any location. The suggested model shows a wearable sensor node that the patients will wear. Monitoring client metrics like blood pressure, heart rate, temperature, etc., is the responsibility of the sensor nodes, which send the data to the cloud via an intermediary node. The sensor-acquired data are stored in the cloud storage for detailed analysis. Further, the stored data will be normalized and processed across various predictive models. Among the different cloud-based predictive models now being used, the model having the highest accuracy will be treated as the resultant model. This resultant model will be further used for the data dissemination mechanism by which the concerned medical actors will be provided an alert message for a proper medication in a desirable manner. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Machine Learning Approach to Predict In-Hospital Mortality in COVID-19 Patients with Underlying Cardiovascular Disease using Artificial Neural Network

Background: Machine learning algorithms, such as artificial neural networks (ANN), provide more accurate predictions by discovering complex patterns within data. Since COVID-19 disease is prevalent, using advanced statistical tools can upgrade clinical decision making by identi-fying high risk patients at the time of admission. Objective(s): This study aims to predict in-hospital mortality in COVID-19 patients with underlying cardiovascular disease (CVD) using the ANN model. Method(s): In the current retrospective cohort study, 880 COVID-19 patients with underlying CVD were enrolled from 26 health centers affiliated with Shiraz University of Medical Sciences and fol-lowed up from 10 June to 26 December 2020. The five-fold cross-validation method was utilized to build the optimal ANN model for predicting in-hospital death. Moreover, the predictive power of the ANN model was assessed with concordance indices and the area under the ROC curve (AUC). Result(s): The median (95% CI) survival time of hospitalization was 16.7 (15.2-18.2) days and the empirical death rate was calculated to be 17.5%. About 81.5% of intubated COVID-19 patients were dead and the majority of the patients were admitted to the hospital with triage level two (54%). According to the ANN model, intubation, blood urea nitrogen, C-reactive protein, lactate dehydro-genase, and serum calcium were the most important prognostic indicators associated with patients' in-hospital mortality. In addition, the accuracy of the ANN model was obtained to be 83.4%, with a sensitivity and specificity of 72.7% and 85.6%, respectively (AUC=0.861). Conclusion(s): In this study, the ANN model demonstrated a good performance in the prediction of in-hospital mortality in COVID-19 patients with a history of CVD. Copyright © 2022 Bentham Science Publishers.

CT severity score in COVID-19 patients, assessment of performance in triage and outcome prediction: a comparative study of different methods

Background: Lung involvement in COVID-19 can be quantified by chest CT scan with some triage and prognostication value. Optimizing initial triage of patients could help decrease adverse health impacts of the disease through better clinical management. At least 6 CT severity score (CTSS) systems have been proposed. We aimed to evaluate triage and prognostication performance of seven different CTSSs, including one proposed by ourselves, in hospitalized COVID-19 patients diagnosed by positive polymerase chain reaction (PCR). Result(s): After exclusion of 14 heart failure and significant preexisting pulmonary disease patients, 96 COVID-19, PCR-positive patients were included into our retrospective study, admitted from February 20, 2020, to July 22. Their mean age was 63.6 +/- 17.4 years (range 21-88, median 67). Fifty-seven (59.4%) were men, and 39 (40.6%) were women. All CTSSs showed good interrater reliability as calculated intraclass correlation coefficients (ICCs) between two radiologists were 0.764-0.837. Those CTSSs with more numerous segmentations showed the best ICCs. As judged by area under curve (AUC) for each receiver operator characteristic (ROC) curve, only three CTSSs showed acceptable AUCs (AUC = 0.7) for triage of severe/critical patients. All CTSSs showed acceptable AUCs for prognostication (AUCs = 0.76-0.79). Calculated AUCs for different CTSSs were not significantly different for triage and for prediction of severe/critical disease, but some difference was shown for prediction of critical disease. Conclusion(s): Men are probably affected more frequently than women by COVID-19. Quantification of lung disease in COVID-19 is a readily available and easy tool to be used in triage and prognostication, but we do not advocate its use in heart failure or chronic respiratory disease patients. The scoring systems with more numerous segmentations are recommended if any future imaging for comparison is contemplated. CTSS performance in triage was much lower than earlier reports, and only three CTSSs showed acceptable AUCs in this regard. CTSS performed better for prognostic purposes than for triage as all 7 CTSSs showed acceptable AUCs in both types of prognostic ROC curves. There is not much difference among performance of different CTSSs. Copyright © 2022, The Author(s).

Face Mask Detection Using Machine Learning Techniques

The year 2020 will be remembered for a major pandemic caused by Covid-19. The studies have shown that the spread of corona virus can be slowed by using face mask and at crowded places where the transmission is high, the use of face mask is important. To determine whether the person is wearing the face mask or not plays a major role which is done using face mask detection. The main objective is to develop a system to detect whether a person is wearing face mask or not wearing the face mask and to test the performance of different CNN models like Vgg16, MobileNetV2 and Densenet121 which can be used for classification. The models were compared with respect to accuracy, AUC curve, confusion matrix and its accuracy of predicting the image if it is with face mask or without face mask. The accuracy of Vgg16, MobileNetV2 and Densenet121 was found to be 93.1%, 99.88% and 99.37% respectively. The area under the ROC curve for the densenet121 was found to be greater as compared to other models. The models were also tested with respect to the confusion matrix and predicting if a person is wearing the face mask or not wearing the face mask. © 2022 IEEE.

Determining the SARS-CoV-2 Anti-Spike Cutoff Level Denoting Neutralizing Activity Using Two Commercial Kits.

BACKGROUND: The viral neutralization assay is the gold standard to estimate the level of immunity against SARS-CoV-2. This study analyzes the correlation between the quantitative Anti-SARS-CoV-2 QuantiVac ELISA (IgG) and the NeutraLISA neutralization assay. METHODS: 650 serum samples were tested for both SARS-CoV-2 anti-spike (anti-S) immunoglobulin G (IgG) and neutralizing antibodies (nAbs) using kits by EUROIMMUN, Germany. RESULTS: There was a significant correlation between levels of anti-S and nAbs (Spearman's rho = 0.913). Among the positive samples for anti-S, 77.0% (n = 345) were positive for nAbs. There was a substantial agreement between anti-S and nAbs (Cohen's kappa coefficient = 0.658; agreement of 83.38%). Considering NeutraLISA as a gold standard, anti-S had a sensitivity of 98.57%, specificity of 65.66%, NPV of 97.5%, and PPV of 77.0%. When the anti-S titer was greater than 18.1 RU/mL (57.9 BAU/mL), nAbs were positive, with a sensitivity of 90.0% and specificity of 91%. CONCLUSIONS: A titer of SARS-CoV-2 anti-S IgG can be correlated with levels of nAbs.

SAPS 3 as a 28-day mortality predictor in critically ill COVID-19 patients

Background: The case fatality rate (CFR) of COVID-19 was 8.7% in Indonesia on April 2020. Simplified Acute Physiology Score 3 (SAPS 3) has been used to predict the hospital mortality based on different variables including acute physiologic derangements, current conditions and interventions, and previous health status assess the severity of condition during the first hour of admission to the ICU. We assessed SAPS 3 to predict the outcome and mortality of critical COVID-19 patients in ICU over a period of 28 days. Methodology: This retrospective cohort study consisted of adult patients admitted to ICU with probable or confirmed COVID-19 in our hospital. We recorded the patients SAPS 3 score from the medical record as well as the 28-day mortality. Validity of the SAPS 3 score was done by the Area Under Curve (AUC) measurement and Hosmer-Lemeshow calibration test. Result(s): The mortality rate of critical COVID-19 patients was 43.8%. The age, intra-hospital location before ICU admission, use of vasoactive drugs (P < 0.0001), focal neurological deficits (P < 0.0001), respiratory failure (P = 0.004), creatinine >= 3.5 mg/dL (P = 0.005), and platelets < 50,000 /microL (P = 0.032) were significantly associated with 28-days mortality in the ICU. SAPS 3 showed good discrimination and predictability. The optimal cut-off point was 39 with 70.3% sensitivity and 74.4% specificity. Conclusion(s): SAPS3 score system was valid in predicting the 28-day mortality of COVID-19 patients in the ICU with good discrimination and calibration value;therefore, it is an important predictor tool for early prognosis screening that will help reduce the strain over the ICU resources. Abbreviations: CFR: Case Fatality Rate;SAPS 3: Simplified Acute Physiology Score 3;COVID-19: The Coronavirus Disease 2019;ICU: Intensive Care Unit;APACHE: Acute Physiology and Chronic Health Evaluation;SPSS: Statistical Package for Social Sciences;GCS: Glasgow Coma Scale;ROC: Receiver Operating Characteristic;PHEIC: Public Health Emergency of International Concern;OR: Odds Ratio Copyright © 2022 Faculty of Anaesthesia, Pain and Intensive Care, AFMS. All rights reserved.

Assessing the Nationwide COVID-19 Risk in Mexico through the Lens of Comorbidity by an XGBoost-Based Logistic Regression Model.

The outbreak of the new COVID-19 disease is a serious health problem that has affected a large part of the world population, especially older adults and people who suffer from a previous comorbidity. In this work, we proposed a classifier model that allows for deciding whether or not a patient might suffer from the COVID-19 disease, considering spatio-temporal variables, physical characteristics of the patients and the presence of previous diseases. We used XGBoost to maximize the likelihood function of the multivariate logistic regression model. The estimated and observed values of percentage occurrence of cases were very similar, and indicated that the proposed model was suitable to predict new cases (AUC = 0.75). The main results revealed that patients without comorbidities are less likely to be COVID-19 positive, unlike people with diabetes, obesity and pneumonia. The distribution function by age group showed that, during the first and second wave of COVID-19, young people aged ≤20 were the least affected by the pandemic, while the most affected were people between 20 and 40 years, followed by adults older than 40 years. In the case of the third and fourth wave, there was an increased risk for young individuals (under 20 years), while older adults over 40 years decreased their chances of infection. Estimates of positive COVID cases with both the XGBoost-LR model and the multivariate logistic regression model were used to create maps to visualize the spatial distribution of positive cases across the country. Spatial analysis was carried out to determine, through the data, the main geographical areas where a greater number of positive cases occurred. The results showed that the areas most affected by COVID-19 were in the central and northern regions of Mexico.

Correlation between In Vitro Neutralization Assay and Serological Tests for Protective Antibodies Detection.

Serological assays are useful in investigating the development of humoral immunity against SARS-CoV-2 in the context of epidemiological studies focusing on the spread of protective immunity. The plaque reduction neutralization test (PRNT) is the gold standard method to assess the titer of protective antibodies in serum samples. However, to provide a result, the PRNT requires several days, skilled operators, and biosafety level 3 laboratories. Therefore, alternative methods are being assessed to establish a relationship between their outcomes and PRNT results. In this work, four different immunoassays (Roche Elecsys® Anti SARS-CoV-2 S, Snibe MAGLUMI® SARS-CoV-2 S-RBD IgG, Snibe MAGLUMI® 2019-nCoV IgG, and EUROIMMUN® SARS-CoV-2 NeutraLISA assays, respectively) have been performed on individuals healed after SARS-CoV-2 infection. The correlation between each assay and the reference method has been explored through linear regression modeling, as well as through the calculation of Pearson's and Spearman's coefficients. Furthermore, the ability of serological tests to discriminate samples with high titers of neutralizing antibodies (>160) has been assessed by ROC curve analyses, Cohen's Kappa coefficient, and positive predictive agreement. The EUROIMMUN® NeutraLISA assay displayed the best correlation with PRNT results (Pearson and Spearman coefficients equal to 0.660 and 0.784, respectively), as well as the ROC curve with the highest accuracy, sensitivity, and specificity (0.857, 0.889, and 0.829, respectively).

Shallow Net for COVID-19 Classification based on Biomarkers

In many cases, especially at the beginning of epidemic disaster, it is very important to be able to determine the severity of illness of a given patient. Picking up the severe status will help in directing the effort in a proper way. At the beginning, the number of classified status and the available data are limited, so, in such situation, one needs a system that can be trained based on limited data to give a trusted result. The current work focuses on the importance of the bioscience in differentiation between recovered patients and mortalities. Even with limited data, the decision trees (DT) was able to distinguish between recovered patients and mortalities with accuracy of 94%. Shallow dense network achieved accuracy of 75%. However, when a 10-fold technique was followed with the same data, the net achieved 99% of accuracy. The used data in this work was collected from King Faisal hospital in Taif city under a formal permission from the health ministry. PCA analysis confirmed that there are two parameters that have the greatest ability to differentiate between recovered patients and mortalities. ROC curve reveals that the parameters that can differentiate between recovered patients and mortalities are calcium and hemoglobin. The shallow net gives an accuracy of 92% when trained using calcium and hemoglobin only. This paper shows that with a suitable choosing of the parameters a small decision tree or shallow net can be trained quickly to decide which patient needs more attention so as to use the hospitals resources in a more reasonable way during the pandemic. All codes and data can be accessed from the following link “codes and data” © 2022. International Journal of Advanced Computer Science and Applications.All Rights Reserved.

[COVID-19 mortality prediction. Comparison between two scales]

Background: The prognosis and mortality in patients with COVID-19 are variable. The NEWS2 (National Early Warning Score) and REMS (Rapid Emergency Medicine Score) scales can be used quickly at hospital admission to predict mortality, no studies have been found that compare their predictive performance in our population. Objective: To compare NEWS2 and REMS to predict mortality in patients with COVID-19. Material and methods: Retrospective cohort with 361 patients. The variables were collected to calculate the NEWS2 and REMS scales and the reason for hospital discharge. The predictive value for mortality was analyzed using the ROC curve, establishing the area under the curve (AUC) with 95% confidence intervals (95% CI). The cut-off point (PC) with the best sensitivity and specificity, positive predictive value (PPV) and negative predictive value (NPV), as well as relative risk (RR) with 95% CI. Results: The AUC of NEWS2 and REMS were 0.929 (95% CI: 0.903-0.956) and 0.913 (95% CI: 0.884-0.943), respectively. The PC of the NEWS2 scale was 8 points, with sensitivity 87.8% and specificity 82.1%, PPV 69.7% and NPV 93.5% and of the REMS scale of 7 points, with sensitivity 83.5% and specificity 83.7%, PPV 70.5% and NPV 91.6%. 8 or more points on the NEWS2 scale presenting a RR of 10.74 (95% CI: 6.4-18.03), and REMS 7 or more points RR 8.36 (95% CI: 5.36-13.02). Conclusion: Both tests presented good discriminative ability to predict mortality, being better according to AUC and RR in the NEWS2 scale.

Prognostic accuracy of inflammatory markers in predicting risk of ICU admission for COVID-19: application of time-dependent receiver operating characteristic curves.

OBJECTIVE: Intensive care unit (ICU) admission occurs at different times during hospitalization among patients with COVID-19. We aimed to evaluate the time-dependent receive operating characteristic (ROC) curve and area under the ROC curve, AUC(t), and accuracy of baseline levels of inflammatory markers C-reactive protein (CRP) and neutrophil-to-lymphocyte ratio (NLR) in predicting time to an ICU admission event in patients with severe COVID-19 infection. METHODS: In this observational study, we evaluated 724 patients with confirmed severe COVID-19 referred to Ayatollah Rohani Hospital, affiliated with Babol University of Medical Sciences, Iran. RESULTS: The AUC(t) of CRP and NLR reached 0.741 (95% confidence interval [CI]: 0.661-0.820) and 0.690 (95% CI: 0.607-0.772), respectively, in the first 3 days after hospital admission. The optimal cutoff values of CRP and NLR for stratification of ICU admission outcomes in patients with severe COVID-19 were 78 mg/L and 5.13, respectively. The risk of ICU admission was significantly greater for patients with these cutoff values (CRP hazard ratio = 2.98; 95% CI: 1.58-5.62; NLR hazard ratio = 2.90; 95% CI: 1.45-5.77). CONCLUSIONS: Using time-dependent ROC curves, CRP and NLR values at hospital admission were important predictors of ICU admission. This approach is more efficient than using standard ROC curves.