Predictors Of COVID-19 Mortality Research Articles

Risk factors associated with COVID-19 mortality in Mexico.

On December 31, 2019, one of the most serious pandemics in recent times made its appearance. Certain health conditions, such as obesity and diabetes mellitus, have been described to be related to COVID-19 unfavorable outcomes. To identify factors associated with mortality in patients with COVID-19. Retrospective cohort of 998,639 patients. Patient sociodemographic and clinical characteristics were analyzed, with survivors being compared with the deceased individuals. Cox proportional hazards model was used to identify variables predictive of COVID-19-associated mortality. Among the deceased patients, men accounted for 64.3%, and women, for 35.7%, with the difference being statistically significant. Subjects older than 80 years had a 13-fold higher risk of dying from COVID-19 (95% CI = 12,469, 13,586), while chronic kidney disease entailed a risk 1.5 times higher (95% CI = 1,341, 1,798), and diabetes mellitus involved a risk 1.25 times higher (95% CI = 1.238,1.276). Age, sex, diabetes mellitus and obesity were found to be predictors of COVID-19 mortality. Further research related to chronic obstructive pulmonary disease, cardiovascular diseases, smoking and pregnancy is suggested.

Evaluation of MSCT severity scoring for prediction of mortality among patients with COVID-19

BackgroundLung CT imaging may reveal COVID-19 abnormalities earlier than RTPCR. CT may be more sensitive than RT-PCR for diagnosing COVID-19-related pneumonia.AimThis study assesses the accuracy of multi-slice computed tomography (MSCT) grading in predicting COVID-19 mortality.MethodsCOVID-19 RT-PCR. For severity scores, all patients’ clinical examinations, history, and chest MSCT data were collected.ResultsAccording to the chest MSCT score, 102 (51.5%), 70 (35%), and 28 (14%) patients had mild, moderate, and severe illness. Out of the patients, 62 (31%) died, and 69% survived. Patients with severe MSCT scores showed a considerably greater mean age than other groups (P < 0.001). Moreover, this group had a considerably higher mean BMI (P < 0.001), and a majority (57.1%) were obese (P < 0.001). Compared to the mild group, the moderate and severe groups had significantly increased rates of diabetes, hypertension, and liver disease (P < 0.001). The moderate group had a greater rate of no comorbidities (P < 0.001). A severe MSCT score was linked to increased leucocytes, C-reactive protein, ESR, ferritin, d-dimer, HbA1c, and fasting blood sugar, as well as decreased mean lymphocytes (P < 0.001). Severe MSCT scores were linked to increased ICU admissions (P < 0.001) and increased demand for advanced mechanical ventilation and oxygen assistance (P < 0.001). A severe MSCT score was associated with the highest death rate, followed by a moderate MSCT score. Low mortality rates were observed in mild MSCT-scored patients (P < 0.001).ConclusionMSC T score severity is a reliable and noninvasive way to predict COVID-19 mortality

Evaluating methods for risk prediction of Covid-19 mortality in nursing home residents before and after vaccine availability: a retrospective cohort study

BackgroundSARS-CoV-2 vaccines are effective in reducing hospitalization, COVID-19 symptoms, and COVID-19 mortality for nursing home (NH) residents. We sought to compare the accuracy of various machine learning models, examine changes to model performance, and identify resident characteristics that have the strongest associations with 30-day COVID-19 mortality, before and after vaccine availability.MethodsWe conducted a population-based retrospective cohort study analyzing data from all NH facilities across Ontario, Canada. We included all residents diagnosed with SARS-CoV-2 and living in NHs between March 2020 and July 2021. We employed five machine learning algorithms to predict COVID-19 mortality, including logistic regression, LASSO regression, classification and regression trees (CART), random forests, and gradient boosted trees. The discriminative performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) for each model using 10-fold cross-validation. Model calibration was determined through evaluation of calibration slopes. Variable importance was calculated by repeatedly and randomly permutating the values of each predictor in the dataset and re-evaluating the model’s performance.ResultsA total of 14,977 NH residents and 20 resident characteristics were included in the model. The cross-validated AUCs were similar across algorithms and ranged from 0.64 to 0.67. Gradient boosted trees and logistic regression had an AUC of 0.67 pre- and post-vaccine availability. CART had the lowest discrimination ability with an AUC of 0.64 pre-vaccine availability, and 0.65 post-vaccine availability. The most influential resident characteristics, irrespective of vaccine availability, included advanced age (≥ 75 years), health instability, functional and cognitive status, sex (male), and polypharmacy.ConclusionsThe predictive accuracy and discrimination exhibited by all five examined machine learning algorithms were similar. Both logistic regression and gradient boosted trees exhibit comparable performance and display slight superiority over other machine learning algorithms. We observed consistent model performance both before and after vaccine availability. The influence of resident characteristics on COVID-19 mortality remained consistent across time periods, suggesting that changes to pre-vaccination screening practices for high-risk individuals are effective in the post-vaccination era.

Evaluating Mortality Predictors in COVID-19 Intensive Care Unit Patients: Insights into Age, Procalcitonin, Neutrophil-to-Lymphocyte Ratio, Platelet-to-Lymphocyte Ratio, and Ferritin Lactate Index.

Numerous studies suggest that alterations in blood parameters, such as changes in platelet, lymphocyte, hemoglobin, eosinophil, and basophil counts; increased neutrophil counts; and elevated neutrophil/lymphocyte and platelet/lymphocyte ratios, signal COVID-19 infection and predict worse outcomes. Leveraging these insights, our study seeks to create a predictive mortality model by assessing age and crucial laboratory markers. Patients were categorized into two groups based on their hospital outcomes: 130 survivors who recovered from their Intensive Care Unit (ICU) stay (Group 1) and 74 who died (Group 2). We then developed a predictive mortality model using patients' age, neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), procalcitonin levels, and ferritin lactate (FL) index results. A total of 204 patients were included. Patients in Group 2 had a notably higher mean age compared to those in Group 1 (76 ± 11 vs. 66 ± 15 years) (p < 0.001). Using specific cut-off values, our analysis revealed varying effectiveness in predicting COVID-19 mortality: Those aged over 73 years showed 74% sensitivity and 60% specificity, with an area under the curve (AUC) of 0.701. Procalcitonin levels above 0.35 ng/mL balanced true-positive and -negative identifications well, achieving an AUC of 0.752. The FL index, with a threshold of 1228 mg/dL, had 68% sensitivity and 65% specificity with an AUC of 0.707. A PLR higher than 212 resulted in 48% sensitivity and 69% specificity, with an AUC of 0.582. An NLR higher than 5.8 resulted in 55% sensitivity and 63% specificity, with an AUC of 0.640, showcasing diverse predictive accuracies across parameters. The statistical analysis evaluated the effects of age (>73), procalcitonin levels (>0.35), FL > 1228, PLR > 212, and NLR > 5.8 on mortality variables using logistic regression. Ages over 73 significantly increased event odds by 2.1 times (p = 0.05), procalcitonin levels above 0.35 nearly quintupled the odds (OR = 5.6, p < 0.001), high FL index levels more than tripled the odds (OR = 3.5, p = 0.003), a PLR > 212 significantly increased event odds by 3.5 (p = 0.030), and an NLR > 5.8 significantly increased event odds by 1.6 (p = 0.043). Our study highlights significant predictors of mortality in COVID-19 ICU patients, including advanced age, elevated procalcitonin, FL index levels, the PLR, and the NLR.

Predicting COVID-19 Mortality and Identifying Clinical Symptom Patterns in Hospitalized Patients: A Machine-learning Study

Background and Purpose: Identifying effective symptoms, demographic information, and underlying diseases to predict COVID-19 mortality is essential. We aimed to study the effective clinical and symptomatic characteristics of COVID-19 mortality in hospitalized patients with positive polymerase chain reaction (PCR) test results. Materials and Methods: For this study, we prospectively collected complete data on 26867 hospitalized individuals who tested PCR positive for COVID-19 from February 20, 2020, to September 12, 2021, in the Khorasan Razavi Province, Iran. We analyzed the data using artificial neural networks (ANN) and logistic regression (LR) models. Results: The accuracy of the ANN model was higher than the LR (90.27% versus 90.15%). The ten most important predictors that contributed to the prediction of death were decreasing consciousness level, cough, PO2 level, age, chronic kidney disease, fever, headache, smoking status, chronic blood diseases, and diarrhea using the ANN model. Conclusion: In conclusion, individuals suffering from chronic diseases such as cancer, kidney and blood diseases, as well as immunodeficiency are at a higher risk of mortality. This important finding can help decision-makers and medical professionals in their efforts to consider these conditions and provide effective preventative measures to reduce the risk of death.

Searching for New Biomarkers to Assess COVID-19 Patients: A Pilot Study.

During the initial diagnosis of urgent medical conditions, which include acute infectious diseases, it is important to assess the severity of the patient's clinical state as quickly as possible. Unlike individual biochemical or physiological indicators, derived indices make it possible to better characterize a complex syndrome as a set of symptoms, and therefore quickly take a set of adequate measures. Recently, we reported on novel diagnostic indices containing butyrylcholinesterase (BChE) activity, which is decreased in COVID-19 patients. Also, in these patients, the secretion of von Willebrand factor (vWF) increases, which leads to thrombosis in the microvascular bed. The objective of this study was the determination of the concentration and activity of vWF in patients with COVID-19, and the search for new diagnostic indices. One of the main objectives was to compare the prognostic values of some individual and newly derived indices. Patients with COVID-19 were retrospectively divided into two groups: survivors (n = 77) and deceased (n = 24). According to clinical symptoms and computed tomography (CT) results, the course of disease was predominantly moderate in severity. The first blood sample (first point) was taken upon admission to the hospital, the second sample (second point)-within 4-6 days after admission. Along with the standard spectrum of biochemical indicators, BChE activity (BChEa or BChEb for acetylthiocholin or butyrylthiocholin, respectively), malondialdehyde (MDA), and vWF analysis (its antigen level, AGFW, and its activity, ActWF) were determined and new diagnostic indices were derived. The pooled sensitivity, specificity, and area under the receiver operating curve (AUC), as well as Likelihood ratio (LR) and Odds ratio (OR) were calculated. The level of vWF antigen in the deceased group was 1.5-fold higher than the level in the group of survivors. Indices that include vWF antigen levels are superior to indices using vWF activity. It was found that the index [Urea] × [AGWF] × 1000/(BChEb × [ALB]) had the best discriminatory power to predict COVID-19 mortality (AUC = 0.91 [0.83, 1.00], p < 0.0001; OR = 72.0 [7.5, 689], p = 0.0002). In addition, [Urea] × 1000/(BChEb × [ALB]) was a good predictor of mortality (AUC = 0.95 [0.89, 1.00], p < 0.0001; OR = 31.5 [3.4, 293], p = 0.0024). The index [Urea] × [AGWF] × 1000/(BChEb × [ALB]) was the best predictor of mortality associated with COVID-19 infection, followed by [Urea] × 1000/(BChEb × [ALB]). After validation in a subsequent cohort, these two indices could be recommended for diagnostic laboratories.

A time-course prediction model of global COVID-19 mortality.

The COVID-19 pandemic has caused over 6 million deaths worldwide and is a significant cause of mortality. Mortality dynamics vary significantly by country due to pathogen, host, social and environmental factors, in addition to vaccination and treatments. However, there is limited data on the relative contribution of different explanatory variables, which may explain changes in mortality over time. We, therefore, created a predictive model using orthogonal machine learning techniques to attempt to quantify the contribution of static and dynamic variables over time. A model was created using Partial Least Squares Regression trained on data from 2020 to rank order the significance and effect size of static variables on mortality per country. This model enables the prediction of mortality levels for countries based on demographics alone. Partial Least Squares Regression was then used to quantify how dynamic variables, including weather and non-pharmaceutical interventions, contributed to the overall mortality in 2020. Finally, mortality levels for the first 60 days of 2021 were predicted using rolling-window Elastic Net regression. This model allowed prediction of deaths per day and quantification of the degree of influence of included variables, accounting for timing of occurrence or implementation. We found that the most parsimonious model could be reduced to six variables; three policy-related variables - COVID-19 testing policy, canceled public events policy, workplace closing policy; in addition to three environmental variables - maximum temperature per day, minimum temperature per day, and the dewpoint temperature per day. Country and population-level static and dynamic variables can be used to predict COVID-19 mortality, providing an example of how broad temporal data can inform a preparation and mitigation strategy for both COVID-19 and future pandemics and assist decision-makers by identifying population-level contributors, including interventions, that have the greatest influence in mitigating mortality, and optimizing the health and safety of populations.

Variation in presepsin and thrombomodulin levels for predicting COVID-19 mortality

Coronavirus disease (COVID-19) has caused extensive mortality globally; therefore, biomarkers predicting the severity and prognosis of COVID-19 are essential. This study aimed to evaluate the application of presepsin (P-SEP) and thrombomodulin (TM), which are biomarkers of sepsis and endothelial dysfunction, respectively, in the prognosis of COVID-19. Serum P-SEP and TM levels from COVID-19 patients (n = 183) were measured. Disease severity was classified as mild, moderate I, moderate II, or severe based on hemoglobin oxygen saturation and the history of intensive care unit transfer or use of ventilation at admission. Patients in the severe group were further divided into survivors and non-survivors. P-SEP and TM levels were significantly higher in the severe group than those in the mild group, even after adjusting for creatinine values. In addition, TM levels were significantly higher in non-survivors than in survivors. Changes in the P-SEP levels at two time points with an interval of 4.1 ± 2.2 days were significantly different between the survivors and non-survivors. In conclusion, TM and continuous P-SEP measurements may be useful for predicting mortality in patients with COVID-19. Moreover, our data indicate that P-SEP and TM values after creatinine adjustment could be independent predictive markers, apart from renal function.

Machine learning algorithms for predicting determinants of COVID-19 mortality in South Africa.

COVID-19 has strained healthcare resources, necessitating efficient prognostication to triage patients effectively. This study quantified COVID-19 risk factors and predicted COVID-19 intensive care unit (ICU) mortality in South Africa based on machine learning algorithms. Data for this study were obtained from 392 COVID-19 ICU patients enrolled between 26 March 2020 and 10 February 2021. We used an artificial neural network (ANN) and random forest (RF) to predict mortality among ICU patients and a semi-parametric logistic regression with nine covariates, including a grouping variable based on K-means clustering. Further evaluation of the algorithms was performed using sensitivity, accuracy, specificity, and Cohen's K statistics. From the semi-parametric logistic regression and ANN variable importance, age, gender, cluster, presence of severe symptoms, being on the ventilator, and comorbidities of asthma significantly contributed to ICU death. In particular, the odds of mortality were six times higher among asthmatic patients than non-asthmatic patients. In univariable and multivariate regression, advanced age, PF1 and 2, FiO2, severe symptoms, asthma, oxygen saturation, and cluster 4 were strongly predictive of mortality. The RF model revealed that intubation status, age, cluster, diabetes, and hypertension were the top five significant predictors of mortality. The ANN performed well with an accuracy of 71%, a precision of 83%, an F1 score of 100%, Matthew's correlation coefficient (MCC) score of 100%, and a recall of 88%. In addition, Cohen's k-value of 0.75 verified the most extreme discriminative power of the ANN. In comparison, the RF model provided a 76% recall, an 87% precision, and a 65% MCC. Based on the findings, we can conclude that both ANN and RF can predict COVID-19 mortality in the ICU with accuracy. The proposed models accurately predict the prognosis of COVID-19 patients after diagnosis. The models can be used to prioritize COVID-19 patients with a high mortality risk in resource-constrained ICUs.

Can artificial intelligence predict COVID-19 mortality?

COVID-19 infection rapidly spread across the globe and evolved into a pandemic. Artificial intelligence (AI) has been used to predict the spread of the virus and diagnose and treat the disease. In this study, we aimed to predict whether patients admitted to the intensive care unit (ICU) due to COVID-19 infection will result in mortality. Ninety parameters were used for each 589 ICU patient. The nine parameters with the highest effect on mortality were determined. Four hundred seventy-one patients were used to train the AI with these nine parameters. AI was tested with 118 patient data. AI estimated mortality with 83% sensitivity, 84% specificity, 84% accuracy, and 0.81 F1 score. Therefore, the area under the curve was calculated as 0.91. The results indicate that mortality among COVID-19 patients admitted to the ICU can be predicted based on their laboratory parameters on the first day. These findings underscore the potential benefits of utilizing AI in managing pandemics.

A-136 Usefulness of Presepsin and Thrombomodulin Measurements for Predicting COVID-19 Mortality

Abstract Background Coronavirus disease (COVID-19) is a novel infectious disease developed into a pandemic since early 2020, resulting in extensive morbidity and mortality globally. Therefore, it is important to identify biomarkers for predicting the severity and mortality of COVID-19. We focused on presepsin (P-SEP) and thrombomodulin (TM), which are biomarkers of sepsis and endothelial dysfunction, respectively. Some reports have already suggested that these biomarkers can be associated with COVID-19, however, most of them assessed blood P-SEP and TM levels using only a single day measurement. In addition, since both P-SEP and TM are excreted by the kidney, renal dysfunction should be considered when evaluating these levels. In this study, to evaluate the usefulness of P-SEP and TM for the prognosis and prediction of COVID-19 severity, we investigated the changes in these levels after admission with or without adjustment for creatinine (CRE) level in COVID-19 patients. Methods Samples were residual sera obtained from COVID-19 patients (n = 674) admitted to the TMDU Hospital. Serum P-SEP and TM levels were measured using the STACIA clinical assay system. Disease severity was classified as mild, moderate, or severe based on hemoglobin oxygen saturation and the history of intensive care unit transfer or use of ventilation at admission. Patients in the severe group were further classified into survivors and non-survivors. This study was approved by the institutional research ethics committee (No. M2020-110). Results Since patients who received recombinant human TM treatment had abnormally high TM levels (&amp;gt; 1000 U/mL), data after administration were excluded from the analysis. P-SEP and TM levels during hospitalization were significantly correlated with CRE levels. In the correlation between P-SEP and CRE, the slope of the severe group was different from that of the non-severe group. When compared the data extracted within 5 days after admission (n = 183) among the three severity groups, CRE levels showed no significant difference among them. On the other hand, P-SEP and TM levels at admission were significantly higher in the severe group than those in the mild group, even after adjusting for CRE levels. In addition, there was no significant difference in the P-SEP levels between survivors and non-survivors, whereas TM levels were significantly higher in non-survivors than in survivors. Changes in the P-SEP levels at two time points (interval: 4.1 ± 2.2 days) were significantly different between survivors and non-survivors. The second measurement of TM levels were elevated in both groups from the first measurement at admission. Conclusion This study suggested that the elevation of P-SEP and TM levels in severe COVID-19 patients might not only fluctuate with renal dysfunction, but might reflect severity. TM and continuous P-SEP measurements are available for predicting mortality in patients with COVID-19. Moreover, P-SEP and TM values after CRE adjustment would be independent predictive markers, apart from renal function.

Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality

BackgroundCoronavirus disease 2019 (COVID-19) is a rapidly developing and sometimes lethal pulmonary disease. Accurately predicting COVID-19 mortality will facilitate optimal patient treatment and medical resource deployment, but the clinical practice still needs to address it. Both complete blood counts and cytokine levels were observed to be modified by COVID-19 infection. This study aimed to use inexpensive and easily accessible complete blood counts to build an accurate COVID-19 mortality prediction model. The cytokine fluctuations reflect the inflammatory storm induced by COVID-19, but their levels are not as commonly accessible as complete blood counts. Therefore, this study explored the possibility of predicting cytokine levels based on complete blood counts.MethodsWe used complete blood counts to predict cytokine levels. The predictive model includes an autoencoder, principal component analysis, and linear regression models. We used classifiers such as support vector machine and feature selection models such as adaptive boost to predict the mortality of COVID-19 patients.ResultsComplete blood counts and original cytokine levels reached the COVID-19 mortality classification area under the curve (AUC) values of 0.9678 and 0.9111, respectively, and the cytokine levels predicted by the feature set alone reached the classification AUC value of 0.9844. The predicted cytokine levels were more significantly associated with COVID-19 mortality than the original values.ConclusionsIntegrating the predicted cytokine levels and complete blood counts improved a COVID-19 mortality prediction model using complete blood counts only. Both the cytokine level prediction models and the COVID-19 mortality prediction models are publicly available at http://www.healthinformaticslab.org/supp/resources.php.

Machine and Deep Learning Algorithms for COVID-19 Mortality Prediction Using Clinical and Radiomic Features

Aim: Machine learning (ML) and deep learning (DL) predictive models have been employed widely in clinical settings. Their potential support and aid to the clinician of providing an objective measure that can be shared among different centers enables the possibility of building more robust multicentric studies. This study aimed to propose a user-friendly and low-cost tool for COVID-19 mortality prediction using both an ML and a DL approach. Method: We enrolled 2348 patients from several hospitals in the Province of Reggio Emilia. Overall, 19 clinical features were provided by the Radiology Units of Azienda USL-IRCCS of Reggio Emilia, and 5892 radiomic features were extracted from each COVID-19 patient’s high-resolution computed tomography. We built and trained two classifiers to predict COVID-19 mortality: a machine learning algorithm, or support vector machine (SVM), and a deep learning model, or feedforward neural network (FNN). In order to evaluate the impact of the different feature sets on the final performance of the classifiers, we repeated the training session three times, first using only clinical features, then employing only radiomic features, and finally combining both information. Results: We obtained similar performances for both the machine learning and deep learning algorithms, with the best area under the receiver operating characteristic (ROC) curve, or AUC, obtained exploiting both clinical and radiomic information: 0.803 for the machine learning model and 0.864 for the deep learning model. Conclusions: Our work, performed on large and heterogeneous datasets (i.e., data from different CT scanners), confirms the results obtained in the recent literature. Such algorithms have the potential to be included in a clinical practice framework since they can not only be applied to COVID-19 mortality prediction but also to other classification problems such as diabetic prediction, asthma prediction, and cancer metastases prediction. Our study proves that the lesion’s inhomogeneity depicted by radiomic features combined with clinical information is relevant for COVID-19 mortality prediction.

Hemodynamic, Oxygenation and Lymphocyte Parameters Predict COVID-19 Mortality.

The mortality of COVID-19 patients has left the world devastated. Many scoring systems have been developed to predict the mortality of COVID-19 patients, but several scoring components cannot be carried out in limited health facilities. Herein, the authors attempted to create a new and easy scoring system involving mean arterial pressure (MAP), PF Ratio, or SF ratio-respiration rate (SF Ratio-R), and lymphocyte absolute, which were abbreviated as MPL or MSLR functioning, as a predictive scoring system for mortality within 30 days for COVID-19 patients. Of 132 patients with COVID-19 hospitalized between March and November 2021, we followed up on 96 patients. We present bivariate and multivariate analyses as well as the area under the curve (AUC) and Kaplan-Meier charts. From 96 patients, we obtained an MPL score of 3 points: MAP < 75 mmHg, PF Ratio < 200, and lymphocyte absolute < 1500/µL, whereas the MSLR score was 6 points: MAP < 75 mmHg, SF Ratio < 200, lymphocyte absolute < 1500/µL, and respiration rate 24/min. The MPL cut-off point is 2, while the MSLR is 4. MPL and MSLR have the same sensitivity (79.1%) and specificity (75.5%). The AUC value of MPL vs. MSLR was 0.802 vs. 0.807. The MPL ≥ 2 and MSLR ≥ 4 revealed similar predictions for survival within 30 days (p < 0.05). Conclusion: MPL and MSLR scores are potential predictors of mortality in COVID-19 patients within 30 days in a resource-limited country.

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.

Risk Factor Analysis and Multiple Predictive Machine Learning Models for Mortality in COVID-19: A Multicenter and Multi-Ethnic Cohort Study

BackgroundThe COVID-19 pandemic presents a significant challenge to the global health care system. Implementing timely, accurate, and cost-effective screening approaches is crucial in preventing infections and saving lives by guiding disease management. ObjectivesThe study aimed to use machine learning algorithms to analyze clinical features from routine clinical data to identify risk factors and predict the mortality of COVID-19. MethodsThe data used in this research were originally collected for the study titled “Neurologic Syndromes Predict Higher In-Hospital Mortality in COVID-19.” A total of 4711 patients with confirmed COVID-19 were enrolled consecutively from four hospitals. Three machine learning models, including random forest (RF), partial least squares discriminant analysis (PLS-DA), and support vector machine (SVM), were used to find risk factors and predict COVID-19 mortality. ResultsThe predictive models were developed based on three machine learning algorithms. The RF model was trained with 20 variables and had a receiver operating characteristic (ROC) value of 0.859 (95% confidence interval [CI] 0.804–0.920). The PLS-DA model was trained with 20 variables and had a ROC value of 0.775 (95% CI 0.694–0.833). The SVM model was trained with 10 variables and had a ROC value of 0.828 (95% CI 0.785–0.865). The nine variables that were present in all three models were age, procalcitonin, ferritin, C-reactive protein, troponin, blood urea nitrogen, mean arterial pressure, aspartate transaminase, and alanine transaminase. ConclusionThis study developed and validated three machine learning prediction models for COVID-19 mortality based on accessible clinical features. The RF model showed the best performance among the three models. The nine variables identified in the models may warrant further investigation as potential prognostic indicators of severe COVID-19.

Red cell distribution width, platelet distribution width, and plateletcrit as indicators of prognosis in COVID-19 patients - A single-center study

Background: COVID-19 is still present in the world, though the extent varies by region and country. According to the World Health Organization, there have been over 617 million confirmed cases of COVID-19 and over 13 million deaths worldwide since the pandemic began on March 10, 2023. Aims and Objectives: This is a study conducted with the aim of providing biomarkers to predict COVID-19 disease progression and mortality based on red cell indices and platelet indices which are commonly measured as part of a complete blood count (CBC). Materials and Methods: A prospective study was conducted during the peak of the second wave of COVID-19 from March 2021 to June 2021. The study included 540 patients who were admitted to the Government General Hospital, Nizamabad, and had tested positive for COVID-19 by RT-PCR. Red Blood Cell (RBC), Hematocrit (HCT), Red cell indices like Mean Corpuscular Volume (MCV), Mean Corpuscular Hemoglobin (MCH), Mean Corpuscular Haemoglobin Concentration (MCHC), Red Cell Distribution width (RDW) and Platelet indices like Mean Platelet Volume (MPV), Platelet Distribution Width (PDW), Plateletcrit (PCT), Platelet–Large Cell Ratio were taken from CBC analyzer Sysmex XN-1000 and analyzed statistically. The patients were then followed up for a period of 14 days to track their outcomes. Results: In the data, majority were male n=334 (62%) and n=280 (38%) were female. 70.37% (n=380) were survivors and 29.63% (n=160) were non-survivors. Red blood cell, red cell indices such as RDW-CV and RDW-SD, and platelet indices such as PCT and PDW were significantly higher in non-survivors compared to survivors with P&lt;0.05. Conclusion: Non-survivors had significantly higher levels of RDW-CV, RDW-SD, PCT, and PDW compared to survivors. These parameters in combination can be useful for predicting COVID-19 mortality at early stage in forthcoming waves.

Rapid Assessment of COVID-19 Mortality Risk with GASS Classifiers.

Risk prediction models are fundamental to effectively triage incoming COVID-19 patients. However, current triaging methods often have poor predictive performance, are based on variables that are expensive to measure, and often lead to hard-to-interpret decisions. We introduce two new classification methods that can predict COVID-19 mortality risk from the automatic analysis of routine clinical variables with high accuracy and interpretability. SVM22-GASS and Clinical-GASS classifiers leverage machine learning methods and clinical expertise, respectively. Both were developed using a derivation cohort of 499 patients from the first wave of the pandemic and were validated with an independent validation cohort of 250 patients from the second pandemic phase. The Clinical-GASS classifier is a threshold-based classifier that leverages the General Assessment of SARS-CoV-2 Severity (GASS) score, a COVID-19-specific clinical score that recently showed its effectiveness in predicting the COVID-19 mortality risk. The SVM22-GASS model is a binary classifier that non-linearly processes clinical data using a Support Vector Machine (SVM). In this study, we show that SMV22-GASS was able to predict the mortality risk of the validation cohort with an AUC of 0.87 and an accuracy of 0.88, better than most scores previously developed. Similarly, the Clinical-GASS classifier predicted the mortality risk of the validation cohort with an AUC of 0.77 and an accuracy of 0.78, on par with other established and emerging machine-learning-based methods. Our results demonstrate the feasibility of accurate COVID-19 mortality risk prediction using only routine clinical variables, readily collected in the early stages of hospital admission.

Effect of ferritin, INR, and D-dimer immunological parameters levels as predictors of COVID-19 mortality: A strong prediction with the decision trees

Background and objectiveA hyperinflammatory environment is thought to be the distinctive characteristic of COVID-19 infection and an important mediator of morbidity. This study aimed to determine the effect of other immunological parameter levels, especially ferritin, as a predictor of COVID-19 mortality via decision-trees analysis. Material and methodThis is a retrospective study evaluating a total of 2568 patients who died (n = 232) and recovered (n = 2336) from COVID-19 in August and December 2021. Immunological laboratory data were compared between two groups that died and recovered from patients with COVID-19. In addition, decision trees from machine learning models were used to evaluate the performance of immunological parameters in the mortality of the COVID-19 disease. ResultsNon-surviving from COVID-19 had 1.75 times higher ferritin, 10.7 times higher CRP, 2.4 times higher D-dimer, 1.14 times higher international-normalized-ratio (INR), 1.1 times higher Fibrinogen, 22.9 times higher procalcitonin, 3.35 times higher troponin, 2.77 mm/h times higher erythrocyte-sedimentation-rate (ESR), 1.13sec times longer prothrombin time (PT) when compared surviving patients. In addition, our interpretable decision tree, which was constructed with only the cut-off values of ferritin, INR, and D-dimer, correctly predicted 99.7% of surviving patients and 92.7% of non-surviving patients. ConclusionsThis study perfectly predicted the mortality of COVID-19 with our interpretable decision tree constructed with INR and D-dimer, especially ferritin. For this reason, we think that it may be important to include ferritin, INR, and D-dimer parameters and their cut-off values in the scoring systems to be planned for COVID-19 mortality.

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.