Exploration of Sex and Age-Based Associations in Clinical Characteristics, Predictors of Severity, and Duration of Stay among COVID-19 Patients at the University Hospital of Saudi Arabia

Machine learning versus multivariate logistic regression for predicting severe COVID-19 in hospitalized children with Omicron variant infection

With the emergence of the Omicron variant, the number of pediatric Coronavirus Disease 2019 (COVID-19) cases requiring hospitalization and developing severe or critical illness has significantly increased. Machine learning and multivariate logistic regression analysis were used to predict risk factors and develop prognostic models for severe COVID-19 in hospitalized children with the Omicron variant in this study. Of the 544 hospitalized children including 243 and 301 in the mild and severe groups, respectively. Fever (92.3%) was the most common symptom, followed by cough (79.4%), convulsions (36.8%), and vomiting (23.2%). The multivariate logistic regression analysis showed that age (1-3 years old, odds ratio (OR): 3.193, 95% confidence interval (CI): 1.778-5.733], comorbidity (OR: 1.993, 95% CI:1.154-3.443), cough (OR: 0.409, 95% CI:0.236-0.709), and baseline neutrophil-to-lymphocyte ratio (OR: 1.108, 95% CI: 1.023-1.200), lactate dehydrogenase (OR: 1.993, 95% CI: 1.154-3.443), blood urea nitrogen (OR: 1.002, 95% CI: 1.000-1.003) and total bilirubin (OR: 1.178, 95% CI: 1.005-3.381) were independent risk factors for severe COVID-19. The area under the curve (AUC) of the prediction models constructed by multivariate logistic regression analysis and machine learning (RandomForest + TomekLinks) were 0.7770 and 0.8590, respectively. The top 10 most important variables of random forest variables were selected to build a prediction model, with an AUC of 0.8210. Compared with multivariate logistic regression, machine learning models could more accurately predict severe COVID-19 in children with Omicron variant infection.

Characteristics of COVID-19 Patients Admitted to Intensive Care Unit in Multispecialty Hospital of Riyadh, Saudi Arabia: A Retrospective Study

During the early stages of the COVID-19 pandemic, infection rates were high and symptoms were severe. Medical resources, including healthcare experts and hospital facilities, were put to the test to ensure their readiness to deal with this unique event. An intensive care unit (ICU) is expected to be required by many hospitalized patients. Many hospitals worldwide lacked resources during the pandemic's peak stages, particularly in critical care treatment. Because of this, there were issues with capacity, as well as an excessive influx of patients. Additionally, even though the research location provides medical care to a sizable population, there is a paucity of scientific data detailing the situation as it pertains to COVID-19 patients during the height of the outbreak. Therefore, this study aimed to identify and describe the features of COVID-19 patients hospitalized in the ICU of one of the multispecialty hospitals in Riyadh, Saudi Arabia. An observational retrospective study was conducted using a chart review of COVID-19 patients admitted to the ICU between March 2020 and December 2020. To characterize the patients, descriptive statistics were utilized. An exploratory multivariate regression analysis was carried out on the study cohort to investigate the factors that were shown to be predictors of death and intubation. Only 333 (29.33%) of the 1135 samples from the hospital's medical records were used for the final analysis and interpretation. More than 76% of the patients in the study were male, with a mean BMI of 22.07 and an average age of around 49 years. The most frequent chronic condition found among the patients who participated in the study was diabetes (39.34%), followed by hypertension (31.53%). At the time of admission, 63 of the total 333 patients needed to have intubation performed. In total, 22 of the 333 patients died while undergoing therapy. People with both diabetes and hypertension had a 7.85-fold higher risk of death, whereas those with only diabetes or hypertension had a 5.43-fold and 4.21-fold higher risk of death, respectively. At admission, intubation was necessary for many male patients (49 out of 63). Most intubated patients had hypertension, diabetes, or both conditions. Only 13 of the 63 patients who had been intubated died, with the vast majority being extubated. Diabetes and hypertension were significant contributors to the severity of illness experienced by COVID-19 participants. The presence of multiple comorbidities had the highest risk for intubation and mortality among ICU-admitted patients. Although more intubated patients died, the fatality rate was lower than in other countries due to enhanced healthcare management at the ICU of the study center. However, large-scale trials are needed to determine how effective various strategies were in preventing ICU admission, intubation, and death rates.

Factors Affecting Hospitalization Length and in-Hospital Death Due to COVID-19 Infection in Saudi Arabia: A Single-Center Retrospective Analysis

Background

The emerging COVID-19 coronavirus disease has widely spread, causing a serious worldwide pandemic. Disease severity and mortality risk can be predicted using an analysis of COVID-19 clinical characteristics. Finding out what influences patients' hospitalization length and in-hospital mortality is crucial for decision-making and planning for emergencies. The goal of this study is to identify the factors that influence hospital stay length and in-hospital death due to COVID-19 infection.

Methods

This cross-sectional study was conducted from August to October 2020 and included 630 patients with a confirmed diagnosis of COVID-19 infection. Using odds ratios (OR) and 95% confidence intervals (CI), a multivariable logistic regression model was used to assess the variables that are linked to longer hospital stays and in-hospital deaths.

Results

Most patients were male (64.3%), and most were older than 40 years (81.4%). The mean length of hospital stay (LoHS) was 10.4±11.6 days. The overall death rate among these COVID-19 cases was 14.3%. Non-survivors were older, had more comorbidities, had prolonged LoHS with increased ICU admission rates and mechanical ventilation usage, and had a more severe condition than survivors. ICU admission, low serum albumin, and elevated LDH levels were associated with longer LoHS, while ICU admission, DM, and respiratory diseases as comorbidities, total leukocytic count, and serum albumin were predictors of mortality.

Conclusion

Longer LoHS due to COVID-19 infection was linked to ICU admission, low serum albumin, and elevated LDH levels, while the independent predictors of in-hospital death were ICU admission, DM, and respiratory diseases as comorbidities, total leukocytic count, and serum albumin.