Related Experiment Videos
Predicting COVID-19 severity using machine learning: the role of clinical parameters, blood groups, and vaccination
Laila A Damiati1, Mohammed A Baghdadi2,3, Safa A Damiati4
1Department of Biological Sciences, College of Science, University of Jeddah, Jeddah, Saudi Arabia.
Insights
Machine learning identified key predictors of COVID-19 severity, revealing differential biomarker regulation across age groups and a link between symptoms and pneumococcal vaccination status. These insights aid in better risk assessment for COVID-19 patients.
Area of Science:
- Medical Research
- Biostatistics
- Epidemiology
Background:
- COVID-19 significantly impacts global health and economies, necessitating a deeper understanding of disease severity and progression.
- Clinical factors, laboratory parameters, and patient age are crucial variables in assessing COVID-19 severity.
Purpose of the Study:
- To investigate the link between clinical factors, laboratory parameters, age, and COVID-19 severity.
- To explore relationships between variables and disease progression using machine learning (ML).
Main Methods:
- Analyzed data from 177 hospitalized COVID-19 patients across five age groups.
- Assessed various biomarkers (hematological, electrolytes, liver/renal function) for sensitivity, specificity, and cut-off levels.
- Employed ML techniques (Random Forest, Mutual Information) to identify key predictors and interactions.
Main Results:
- Differential regulation of biomarkers observed across different age groups in COVID-19 patients.
- Significant association found between symptom presence and pneumococcal vaccination status.
- ML identified crucial features influencing COVID-19 severity.
Conclusions:
- While blood group and pneumococcal vaccine showed minor influence, ML identified key predictors of COVID-19 severity.
- Findings offer valuable insights for improved risk assessment in COVID-19 patients.
- Understanding biomarker variations and predictor importance can guide clinical management.
Objectives:
COVID-19 has had strong impacts on both global health systems and economies. Therefore, understanding disease severity and progression is crucial. This cross-sectional study aims to investigate possible link between clinical factors, laboratory parameters, and age on COVID-19 severity. Machine-learning (ML) methods were used to analyze a dataset to explore the relationships between these variables and disease progression.
Methods:
In this study, 177 hospitalized COVID-19 patients were divided into five age groups. A range of biomarkers, including hematological parameters, electrolytes, and liver and renal function tests, were analyzed. Several parameters had acceptable sensitivity and specificity and indicated cut-off levels between patient age groups. Furthermore, ML was used to find an interaction between blood group, pneumococcal vaccine status, and COVID-19 symptoms to explore potential relationships.
Results:
The main findings were that various biomarkers were differentially regulated in COVID-19 patients across different age groups. Furthermore, the interpretation of the obtained results indicated a significant association between the presence of symptoms during the course of the illness and pneumococcal vaccination status. Additionally, feature selection analysis employing machine learning techniques, specifically Random Forest and Mutual Information, identified the most important features within the analyzed dataset.
Conclusions:
Although blood group and Pneumococcal vaccine showed weak influence on the presence of COVID-19 symptoms, our findings shed light on the relative importance of the most influencing predictors on COVID-19 severity, which may provide valuable-insights for better risk assessment.
