Related Experiment Video
Updated: Aug 28, 2025
Dried Blood Spot Collection of Health Biomarkers to Maximize Participation in Population Studies
Published on: January 28, 2014
Identification of High Death Risk Coronavirus Disease-19 Patients using Blood Tests
Elaheh Zadeh Hosseingholi1, Saeede Maddahi2,1, Sajjad Jabbari3,1
1Department of Biology, Faculty of Basic Sciences, Azarbaijan Shahid Madani University, Tabriz, Iran.
Insights
Early prediction of COVID-19 mortality is crucial for resource allocation. Aspartate aminotransferase (AST) and blood urea nitrogen (BUN) levels are key biomarkers for identifying high-risk patients.
Area of Science:
- Medical Informatics
- Biomarkers
- Epidemiology
Background:
- The COVID-19 pandemic significantly impacted healthcare services globally.
- Effective prognosis of disease severity aids in prioritizing hospital resources and reducing mortality.
- Early identification of mortality risk factors is essential for patient management.
Purpose of the Study:
- To identify paramount biomarkers for early mortality prediction in COVID-19 patients.
- To develop a reliable model for assessing COVID-19 patient mortality risk.
- To aid physicians in timely detection and management of high-risk individuals.
Main Methods:
- Retrospective analysis of 205 hospitalized COVID-19 patients (June 2020 - March 2021).
- Utilized machine learning (Random Forests) and statistical tools to analyze demographic data and blood biomarkers.
- Identified key features associated with patient mortality.
Main Results:
- Random Forests model identified Aspartate Aminotransferase (AST) and Blood Urea Nitrogen (BUN) as significant mortality predictors (MCC=0.514).
- Decision tree analysis established BUN >47 mg/dL and AST >44 U/L as mortality risk thresholds.
- Statistical analysis confirmed AST and BUN as highly significant (P < 1.6 × 10⁻⁶), alongside age, thrombocytopenia, elevated white blood cell count, and creatinine.
Conclusions:
- Identified key biomarkers (AST, BUN) and clinical factors for predicting COVID-19 mortality.
- Findings support timely risk stratification for improved patient outcomes.
- Results facilitate better allocation of hospital resources during pandemics.
Background:
The coronavirus disease (COVID-19) pandemic has made a great impact on health-care services. The prognosis of the severity of the disease help reduces mortality by prioritizing the allocation of hospital resources. Early mortality prediction of this disease through paramount biomarkers is the main aim of this study.
Materials And Methods:
In this retrospective study, a total of 205 confirmed COVID-19 patients hospitalized from June 2020 to March 2021 were included. Demographic data, important blood biomarkers levels, and patient outcomes were investigated using the machine learning and statistical tools.
Results:
Random forests, as the best model of mortality prediction, (Matthews correlation coefficient = 0.514), were employed to find the most relevant dataset feature associated with mortality. Aspartate aminotransferase (AST) and blood urea nitrogen (BUN) were identified as important death-related features. The decision tree method was identified the cutoff value of BUN >47 mg/dL and AST >44 U/L as decision boundaries of mortality (sensitivity = 0.4). Data mining results were compared with those obtained through the statistical tests. Statistical analyses were also determined these two factors as the most significant ones with P values of 4.4 × 10-7 and 1.6 × 10-6, respectively. The demographic trait of age and some hematological (thrombocytopenia, increased white blood cell count, neutrophils [%], RDW-CV and RDW-SD), and blood serum changes (increased creatinine, potassium, and alanine aminotransferase) were also specified as mortality-related features (P < 0.05).
Conclusions:
These results could be useful to physicians for the timely detection of COVID-19 patients with a higher risk of mortality and better management of hospital resources.
More Related Videos
10:35A Blood-based Test for the Detection of ROS1 and RET Fusion Transcripts from Circulating Ribonucleic Acid Using Digital Polymerase Chain Reaction
Published on: April 5, 2018
05:58Evaluation of a Point-of-Care Testing Analyzer for Measuring Peripheral Blood Leukocytes
Published on: March 22, 2022