Mortality Predictors in Severe COVID-19 Patients from an East European Tertiary Center: A Never-Ending Challenge for a No Happy Ending Pandemic

A Retrospective Study on the Outcome of Coronavirus Disease 2019 (COVID-19) Patients Admitted to a District General Hospital and Predictors of High Mortality

BACKGROUND

The clinical features and severity of coronavirus disease 2019 (COVID-19) vary between patients and countries. Patients with certain conditions are predisposed to poor outcomes compared with those without medical conditions, such as diabetes, dementia, and hypertension (HTN).

METHODS

The aim of this retrospective study was to assess factors associated with higher mortality in patients with COVID-19 infections and to identify the reason for hospital admission in these patients. The study was performed on patients admitted between 1 and 31 March 2020. Data collection was done retrospectively from electronic medical records.

RESULTS

There were 269 patient admissions during this period, of which 147 were included in this audit. The mean age of COVID-19-positive patients was 62.8 years and 65.9 years for COVID-19-negative patients during this period. Forty-seven patients requiring hospital admission were COVID-19 positive and 93 were COVID-19 negative. There were no COVID-19 swabs in the seven patients included in the audit. Approximately 50% of the COVID-19-positive patients presented with fever and shortness of breath (sob), followed by dyspnea and cough (seven patients). The most common comorbidity was HTN, followed by type 2 diabetes mellitus (T2DM) and ischemic heart disease (IHD). The survival rate was 72.3% in COVID-19-positive patients and 80% in COVID-19-negative patients. The average length of stay was 14.4 days for COVID-19-positive survivors compared to 7.8 days for COVID-19-negative survivors. Most patients who tested positive for COVID-19 infection received oseltamivir vaccination and antibiotics. The presence of HTN, diabetes mellitus (DM), age, and organ failure was associated with a high mortality risk.

CONCLUSION

Our study supports the findings of previous studies that diabetes, HTN, coronary artery disease, old age, and organ failure were associated with high mortality in patients admitted to hospitals with COVID-19 infections.

Sex hormones and the total testosterone:estradiol ratio as predictors of severe acute respiratory syndrome coronavirus 2 infection in hospitalized men

BACKGROUND

The predictive ability of the early determination of sex steroids and the total testosterone:estradiol ratio for the risk of severe coronavirus disease 2019 or the potential existence of a biological gradient in this relationship has not been evaluated.

OBJECTIVES

To assess the relationship of sex steroid levels and the total testosterone:estradiol ratio with the risk of severe acute respiratory syndrome coronavirus 2 infection in men, defined as the need for intensive care unit admission or death, and the predictive ability of each biomarker.

MATERIALS AND METHODS

This was a prospective observational study. We included all consecutive adult men with severe acute respiratory syndrome coronavirus 2 infections in a single center admitted to a general hospital ward or to the intensive care unit. Sex steroids were evaluated at the centralized laboratory of our hospital.

RESULTS

We recruited 98 patients, 54 (55.1%) of whom developed severe coronavirus disease in 2019. Compared to patients with nonsevere coronavirus disease 2019, patients with severe coronavirus disease 2019 had significantly lower serum levels of total testosterone (111 ± 89 vs. 191 ± 143 ng/dL; p < 0.001), dehydroepiandrosterone (1.69 ± 1.26 vs. 2.96 ± 2.64 ng/mL; p < 0.001), and dehydroepiandrosterone sulfate (91.72 ± 76.20 vs. 134.28 ± 98.261 μg/dL; p = 0.009), significantly higher levels of estradiol (64.61 ± 59.35 vs. 33.78 ± 13.78 pg/mL; p = 0.001), and significantly lower total testosterone:estradiol ratio (0.28 ± 0.31 vs. 0.70 ± 0.75; p < 0.001). The lower the serum level of androgen and the lower the total testosterone:estradiol ratio values, the higher the likelihood of developing severe coronavirus disease 2019, with the linear trend in the adjusted analyses being statistically significant for all parameters except for androstenedione (p = 0.064). In the receiver operating characteristic analysis, better predictive performance was shown by the total testosterone:estradiol ratio, with an area under the curve of 0.77 (95% confidence interval 0.68-0.87; p < 0.001).

DISCUSSION AND CONCLUSION

Our results suggest that men with severe acute respiratory syndrome coronavirus 2 infection, decreased androgen levels and increased estradiol levels have a higher likelihood of developing an unfavorable outcome. The total testosterone:estradiol ratio showed the best predictive ability.

COVID-19 and Laboratory Markers from Romanian Patients-A Narrative Review

COVID-19 has significantly impacted the whole world, and Romania was no exception. Biomarkers play a crucial role in understanding and managing the disease. However, research regarding laboratory analyses for patients with COVID-19 is fairly limited. For detection, PCR testing is still considered the golden standard, while antibodies are still useful for monitoring both patients and their vaccination status. In our country, biomarkers such as CRP, LDH, transaminases, cardiac, and iron markers have been used to assess the status of patients and even predict illness outcome. CRP, IL-6, LDH, FER, fibrinogen, creatinine, and vitamin D levels have been associated with increased severity, risk of ICU admission, and death. Cardiac markers and D-dimers are also good predictors, but their role seems more important in patients with complications. HDL cholesterol and BUN levels were also suggested as potential biomarkers. Hematological issues in SARS-CoV-2 infections include neutrophilia, lymphopenia and their ratio, while PCT, which is a marker of bacterial infections, is better to be used in patients with co- or supra-infections. The current research is a narrative review that focuses on the laboratory results of Romanian COVID-19 patients. The goal of this article is to provide an update on the research on biomarkers and other laboratory tests conducted inside the borders of Romania and identify gaps in this regard. Secondly, options for further research are discussed and encouraged.

Clinical profile of hospitalised moderate category COVID-19 patients: Short study from a Tertiary Care Centre in Delhi

Background

The clinical profile of hospitalized moderate-category COVID-19 patients has been understudied globally and in India.

Aim

The present study was conducted to study the clinical profile and assess the proportions of patients who progressed to severe disease and its predictors among moderate COVID-19 patients.

Materials and Methods

In this single-center observational study, 100 moderate-category COVID-19 patients as per Ministry of Health and Family Welfare (MoHFW) criteria of age ≥18 years of either sex, excluding pregnant females from February to November 2021, were studied by analyzing their clinical profiles and assessing Quick Sequential Organ Failure Assessment (qSOFA), National Early Warning Score 2 (NEWS-2), and chest computed-tomography severity score (CTSS) to predict progression to severe disease. Severe disease was defined as per MoHFW criteria.

Results

Out of 100 moderate-category COVID-19 patients, progression to severe disease was seen in 11 patients (11%), among which eight patients had expired, three patients were discharged, and the rest of the 89 patients (89%) who did not progress to severe disease were discharged. A higher age (62.2± 19.5 vs 54.8 ± 14.6 years), along with multivariate analysis revealing male sex (1.25 times), chronic kidney disease (2.86 times), leukocytosis (6.10 times), thrombocytopenia (1.04 times), anemia (9.3 times), a higher qSOFA score (3.6 times), and a higher NEWS-2 score on admission (1.56 times) had higher odds of progression to severe disease. A significant correlation (P < .05) of qSOFA score with serum LDH, ferritin, and hs-CRP levels; CT severity score with the serum ferritin, IL-6, and LDH levels; and NEWS-2 with serum LDH, hs-CRP, and ferritin levels were found. Moreover, the NEWS-2 score was found slightly better than qSOFA on receiver operating characteristic (ROC) curve analysis, with an area under the curve of 85.8% and 83.2%, respectively, predicting progression to severe disease.

Conclusion

Our study revealed male gender, chronic kidney disease, leukocytosis, anemia, thrombocytopenia, a higher qSOFA and NEWS-2 score on admission, and further, NEWS-2 score better than qSOFA on ROC curve analysis, with an area under the curve of 85.8% and 83.2%, respectively, in predicting severe disease among hospitalized moderate COVID-19 patients.

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.

The Clash of the Titans: COVID-19, Carbapenem-Resistant Enterobacterales, and First mcr-1-Mediated Colistin Resistance in Humans in Romania

(1) Background: Antibiotic resistance and coronavirus disease-19 (COVID-19) represent a dual challenge in daily clinical practice, inducing a high burden on public health systems. Hence, we aimed to dynamically evaluate the impact of COVID-19 on patients with carbapenem-resistant Enterobacterales (CRE) urinary tract infections (UTIs), as well as the antibiotic resistance trends after the onset of the pandemic. (2) Methods: We conducted a prospective study including patients with CRE UTIs who were enrolled both pre- and during the pandemic from 2019 to 2022. We further performed a standardized and comparative clinical, paraclinical, and microbiological assessment between patients with and without COVID-19. (3) Results: A total of 87 patients with CRE UTIs were included in this study (46 pre-pandemic and 41 during the pandemic, of which 21 had associated Severe Acute Respiratory Syndrome Coronavirus-2 infection). Klebsiella pneumoniae was the main etiological agent of the UTIs, with the majority of strains (82.7%) being carbapenemase producers (mainly OXA-48 producers), while five of the 34 colistin-resistant isolates were harboring the mobile colistin resistance-1 (mcr-1) gene. COVID-19 patients presented a significantly worse outcome with higher rates of intensive care unit (ICU) admissions (66.7% for COVID patients vs. 18.2% for non-COVID patients, p < 0.001), while the fatality rates were also considerably higher among patients with concomitant viral infection (33.3% vs. 12.1%, p < 0.001). Besides COVID-19, additional risk factors associated with increased mortality were urinary catheterization, sepsis with K. pneumoniae, impaired liver and kidney function, and an inappropriate initial empiric antibiotic therapy. (4) Conclusions: COVID-19 showed a pronounced negative impact on patients with CRE UTIs, with significantly longer hospitalizations and higher ICU admissions and mortality rates.

An Overview of the Impact of Bacterial Infections and the Associated Mortality Predictors in Patients with COVID-19 Admitted to a Tertiary Center from Eastern Europe

1.

BACKGROUND

Literature data on bacterial infections and their impact on the mortality rates of COVID-19 patients from Romania are scarce, while worldwide reports are contrasting. 2.

MATERIALS AND METHODS

We conducted a unicentric retrospective observational study that included 280 patients with SARS-CoV-2 infection, on whom we performed various microbiological determinations. Based on the administration or not of the antibiotic treatment, we divided the patients into two groups. First, we sought to investigate the rates and predictors of bacterial infections, the causative microbial strains, and the prescribed antibiotic treatment. Secondly, the study aimed to identify the risk factors associated with in-hospital death and evaluate the biomarkers' performance for predicting short-term mortality. 3.

RESULTS

Bacterial co-infections or secondary infections were confirmed in 23 (8.2%) patients. Acinetobacter baumannii was the pathogen responsible for most of the confirmed bacterial infections. Almost three quarters of the patients (72.8%) received empiric antibiotic therapy. Multivariate logistic regression has shown leukocytosis and intensive care unit admission as risk factors for bacterial infections and C-reactive protein, together with the length of hospital stay, as mortality predictors. The ROC curves revealed an acceptable performance for the erythrocyte sedimentation rate (AUC: 0.781), and C-reactive protein (AUC: 0.797), but a poor performance for fibrinogen (AUC: 0.664) in predicting fatal events. 4.

CONCLUSIONS

This study highlighted the somewhat paradoxical association of a low rate of confirmed infections with a high rate of empiric antibiotic therapy. A thorough assessment of the risk factors for bacterial infections, in addition to the acknowledgment of various mortality predictors, is crucial for identifying high-risk patients, thus allowing a timely therapeutic intervention, with a direct impact on improving patients' prognosis.

Cytokines and Chemokines in Breastmilk of SARS-CoV-2 Infected or COVID-19 Vaccinated Mothers

INTRODUCTION

The COVID-19 disease and anti-SARS-CoV-2 vaccination were accompanied by alterations in several inflammatory markers. The aim of our research was to check to what extent such cytokines are transferred to infants via the breastmilk of SARS-CoV-2-infected or vaccinated mothers. Thus, we wanted to check if breastfeeding is safe during SARS-CoV-2 infection or after COVID-19 mRNA-vaccination.

MATERIAL AND METHOD

The Luminex Multiplexing Assay was used for quantifying 10 cytokine in the human breastmilk of SARS-CoV-2-infected or COVID-19-vaccinated mothers, compared with anti-SARS-CoV-2 IgG naïve mothers. Two milk samples were collected at 30 and 60 days either after the booster dose or afterthe onset of symptoms. A single milk sample was collected from the mothers within the control group.

RESULTS

The cytokine concentrations were mostly found within the reference intervals for all mothers. The status of the vaccinated/infected mother, the age of the breastfed child, the parity of the mother and the maternal age were variation factors of the above-mentioned cytokine concentrations. The type of birth and the presence of IgG in the milk had no influence on these cytokine concentrations in milk. Furthermore, no statistically significant differences were recorded between the cytokine concentrations of the two milk samples.

CONCLUSION

Our study provides data that support the safety of breastfeeding in the case of mild COVID-19 infection or after Pfizer or Moderna vaccinations.

A Rising Star of the Multimarker Panel: Growth Differentiation Factor-15 Levels Are an Independent Predictor of Mortality in Acute Heart Failure Patients Admitted to an Emergency Clinical Hospital from Eastern Europe

(1) Background: Acute heart failure (HF) represents one of the most common yet extremely severe presentations in emergency services worldwide, requiring prompt diagnosis, followed by an adequate therapeutic approach, and a thorough risk stratification. Natriuretic peptides (NPs) are currently the most widely implemented biomarkers in acute HF, but due to their lack of specificity, they are mainly used as ruling-out criteria. Growth differentiation factor-15 (GDF-15) is a novel molecule expressing different pathophysiological pathways in HF, such as fibrosis, remodeling, and oxidative stress. It is also considered a very promising predictor of mortality and poor outcome. In this study, we aimed to investigate the GDF-15’s expression and particularities in patients with acute HF, focusing mainly on its role as a prognosis biomarker, either per se or as part of a multimarker panel. (2) Methods: This unicentric prospective study included a total of 173 subjects, divided into 2 subgroups: 120 patients presented in emergency with acute HF, while 53 were ambulatory-evaluated controls with chronic HF. At admission, all patients were evaluated according to standard clinical echocardiography and laboratory panel, including the assessment of GDF-15. (3) Results: The levels of GDF-15 were significantly higher in patients with acute HF, compared to controls [596 (305−904) vs. 216 (139−305) ng/L, p < 0.01]. GDF-15 also exhibited an adequate diagnostic performance in acute HF, expressed as an area under the curve (AUC) of 0.883 [confidence interval (CI) 95%: 0.828−0.938], similar to that of NT-proBNP (AUC: 0.976, CI 95%: 0.952−1.000), or troponin (AUC: 0.839, CI 95%: 0.733−0.944). High concentrations of GDF-15 were significantly correlated with mortality risk. In a multivariate regression model, GDF-15 was the most important predictor of a poor outcome, superior to NT-proBNP or troponin. (4) Conclusions: GDF-15 proved to be a reliable tool in the multimarker assessment of patients with acute HF. Compared to the gold standard NT-proBNP, GDF-15 presented a similar diagnostic performance, doubled by a significantly superior prognostic value, making it worth being included in a standardized multimarker panel.

A Real Pandora's Box in Pandemic Times: A Narrative Review on the Acute Cardiac Injury Due to COVID-19

The intricate relationship between severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the cardiovascular system is an extensively studied pandemic topic, as there is an ever-increasing amount of evidence that reports a high prevalence of acute cardiac injury in the context of viral infection. In patients with Coronavirus disease 2019, COVID-19, a significant increase in serum levels of cardiac troponin or other various biomarkers was observed, suggesting acute cardiac injury, thus predicting both a severe course of the disease and a poor outcome. Pathogenesis of acute cardiac injury is not yet completely elucidated, though several mechanisms are allegedly involved, such as a direct cardiomyocyte injury, oxygen supply-demand inequity caused by hypoxia, several active myocardial depressant factors during sepsis, and endothelial dysfunction due to the hyperinflammatory status. Moreover, the increased levels of plasma cytokines and catecholamines and a significantly enhanced prothrombotic environment may lead to the destabilization and rupture of atheroma plaques, subsequently triggering an acute coronary syndrome. In the present review, we focus on describing the epidemiology, pathogenesis, and role of biomarkers in the diagnosis and prognosis of patients with acute cardiac injury in the setting of the COVID-19 pandemic. We also explore some novel therapeutic strategies involving immunomodulatory therapy, as well as their role in preventing a severe form of the disease, with both the short-term outcome and the long-term cardiovascular sequelae being equally important in patients with SARS-CoV-2 induced acute cardiac injury.

Patient care in rapid-expansion intensive care units during the COVID-19 pandemic crisis

Background

The coronavirus-2019 (COVID-19) pandemic highlighted the unfortunate reality that many hospitals have insufficient intensive care unit (ICU) capacity to meet massive, unanticipated increases in demand. To drastically increase ICU capacity, NewYork-Presbyterian/Weill Cornell Medical Center modified its existing operating rooms and post-anaesthesia care units during the initial expansion phase to accommodate the surge of critically ill patients.

Methods

This retrospective chart review examined patient care in non-standard Expansion ICUs as compared to standard ICUs. We compared clinical data between the two settings to determine whether the expeditious development and deployment of critical care resources during an evolving medical crisis could provide appropriate care.

Results

Sixty-six patients were admitted to Expansion ICUs from March 1^st to April 30^th, 2020 and 343 were admitted to standard ICUs. Most patients were male (70%), White (30%), 45–64 years old (35%), non-smokers (73%), had hypertension (58%), and were hospitalized for a median of 40 days. For patients that died, there was no difference in treatment management, but the Expansion cohort had a higher median ICU length of stay (q = 0.037) and ventilatory length (q = 0.015). The cohorts had similar rates of discharge to home, but the Expansion ICU cohort had higher rates of discharge to a rehabilitation facility and overall lower mortality.

Conclusions

We found no significantly worse outcomes for the Expansion ICU cohort compared to the standard ICU cohort at our institution during the COVID-19 pandemic, which demonstrates the feasibility of providing safe and effective care for patients in an Expansion ICU.

What Doesn’t Kill Them Makes Them Stronger: The Impact of the Resistance Patterns of Urinary Enterobacterales Isolates in Patients from a Tertiary Hospital in Eastern Europe

(1) Background: The evolution of bacterial resistance to antibiotics is one of the factors that make infectious pathology an extremely dynamic field, also inducing a significant burden on public health systems; therefore, continuous updates on the bacterial resistance to antibiotics and their particular regional patterns is crucial for the adequate approach of various infectious diseases. (2) Methods: We retrospectively analyzed 354 patients with Enterobacterales urinary tract infections (UTIs), determined their antibiotic resistance pattern, thus aiming to correlate them with the outcome and other specific markers of poor prognosis. (3) Results: The most frequent causative agent was Escherichia coli, representing 64.6% of all UTIs. We identified 154 patients resistant to multiple antibiotic classes, of which 126 were multidrug-resistant (MDR), 17 were extensive drug-resistant (XDR) and 11 were pandrug-resistant (PDR). Moreover, 25 isolates were resistant to carbapenems (CRE), 25 were difficult-to-treat (DTR), and 84 were extended-spectrum cephalosporin-resistant (ESC), with only 95 isolates susceptible to all tested antibiotics. Mortality ranged from 1% for UTIs caused by isolates susceptible to all tested antibiotics, to 24% for the ones caused by DTR or CRE isolates. Other significant risk factors associated with mortality were: prolonged hospital stay (p = 0.0001), Charlson comorbidity index ≥ 3 (p = 0.02), urinary catheterization (p = 0.001), associated respiratory pathologies (p = 0.004), obesity (p = 0.047), a history of previous hospitalizations (p = 0.007), inappropriate empiric antibiotic regimen (p = 0.001), or hyper inflammatory status (p = 0.006). Basically, we observed that a multiple regression model comprising urinary catheterization, inappropriate empiric anti-biotherapy, obesity, and respiratory comorbidities exhibits the best correlation with mortality rate in patients with UTI (R = 0.347, R² = 0.12). (4) Conclusions: By focusing on the novel resistance patterns, our study provides complementary evidence concerning the resistance profiles found in an Eastern European region, as well as their prognostic implications in patients with UTI.

The Utility of Laboratory Parameters for Cardiac Inflammation in Heart Failure Patients Hospitalized with SARS-CoV-2 Infection

COVID-19 has been associated with cardiovascular consequences, including myocardial infarction, thromboembolic events, arrhythmia, and heart failure. Numerous overlapping mechanisms, such as the IL-6 dependent cytokine storm and unopposed angiotensin II stimulation, could be responsible for these consequences. Cardiac damage is hypothesized to be a consequence of the direct viral infection of cardiomyocytes, resulting in increased metabolic demand, immunological activation, and microvascular dysfunction. Patients with pre-existing chronic heart failure are therefore at increased risk of decompensation, further heart damage, and significant health deterioration. Based on the aforementioned assumptions, we developed a study aiming to provide a detailed description of changes in biological parameters and cardiac injury markers of patients with heart failure and SARS-CoV-2 infection by correlating them with the clinical presentation and COVID-19 vaccination status, to predict the probability of ICU admission based on their initial hospital presentation. A two-year retrospective study was performed on heart failure patients with a history of SARS-CoV-2 infection and detailed records of biological biomarkers; a total of 124 eligible patients with COVID-19 and 236 without COVID-19 were recruited. Patients with heart failure and SARS-CoV-2 infection had significantly elevated baseline biological parameters and cardiac markers compared to those without COVID-19. Several cardiac injury markers were identified as significant independent risk factors for ICU admission: CK-MB (HR = 4.1, CI[2.2–6.9]), myoglobin (HR = 5.0, CI[2.3–7.8]), troponin-I (HR = 7.1[4.4–9.6]) troponin-T (HR = 4.9, CI[1.7–7.4]). The elevation of a basic panel of acute inflammation markers (CRP, IL-6, fibrinogen), D-dimers, and BNP was also a significant risk factor. The follow-up of survivors at four weeks after viral clearance determined a worsened clinical picture by NYHA classification, worsened cardiac ultrasound findings, and a mild improvement in cardiac and inflammatory markers. Increased levels of myocardial damage parameters in association with cardiac ultrasound findings and basic inflammatory markers may enable early risk assessment and triage in hospitalized heart failure patients infected with SARS-CoV-2.

Explainable Artificial Intelligence Approach for the Early Prediction of Ventilator Support and Mortality in COVID-19 Patients

Early prediction of mortality and risk of deterioration in COVID-19 patients can reduce mortality and increase the opportunity for better and more timely treatment. In the current study, the DL model and explainable artificial intelligence (EAI) were combined to identify the impact of certain attributes on the prediction of mortality and ventilatory support in COVID-19 patients. Nevertheless, the DL model does not suffer from the curse of dimensionality, but in order to identify significant attributes, the EAI feature importance method was used. The DL model produced significant results; however, it lacks interpretability. The study was performed using COVID-19-hospitalized patients in King Abdulaziz Medical City, Riyadh. The dataset contains the patients’ demographic information, laboratory investigations, and chest X-ray (CXR) findings. The dataset used suffers from an imbalance; therefore, balanced accuracy, sensitivity, specificity, Youden index, and AUC measures were used to investigate the effectiveness of the proposed model. Furthermore, the experiments were conducted using original and SMOTE (over and under sampled) datasets. The proposed model outperforms the baseline study, with a balanced accuracy of 0.98 and an AUC of 0.998 for predicting mortality using the full-feature set. Meanwhile, for predicting ventilator support a highest balanced accuracy of 0.979 and an AUC of 0.981 was achieved. The proposed explainable prediction model will assist doctors in the early prediction of COVID-19 patients that are at risk of mortality or ventilatory support and improve the management of hospital resources.