Association of blood group with COVID-19 disease susceptibility and severity in Saudi Arabia.

BACKGROUND: Novel SARS-CoV-2 (COVID-19) virus has rapidly spread worldwide and was declared a pandemic, making identifying and prioritizing individuals most at risk a critical challenge. The literature describes an association between blood groups and the susceptibility to various viral infections and their severity. Knowing if a specific blood group has more susceptibility to COVID-19 may help improve understanding the pathogenesis and severity of the disease. We aimed to assess the association between ABO/RhD and COVID-19 susceptibility and severity, and to compare results with similar studies in Saudi Arabia. STUDY DESIGN AND METHODS: This study was conducted between March and October 2021 on 600 patients confirmed positive for COVID-19 infection. Patients' data were collected and analyzed. As a control, 8423 healthy blood donors were enrolled as a sample representative of the population for blood group distribution. RESULTS: More individuals had blood group B in the COVID-19 group in comparison with the control group (24.2% vs. 18%), The opposite was observed among individuals of group O (39.5% vs. 47.3%). The B blood group was predictive of higher risk of mortality. No significant difference in the distribution of RhD was observed between the COVID-19 and the control groups. Neither ABO nor RhD was significantly associated with the severity of COVID-19. DISCUSSION: Although there was no significant association with the disease severity, the B blood group may be associated with a higher risk for COVID-19 infection. Further studies with a larger sample size are necessary to evaluate this correlation.

Machine Learning-Based Prediction of COVID-19 Prognosis Using Clinical and Hematologic Data.

The coronavirus disease 2019 (COVID-19) pandemic is challenging healthcare systems worldwide. The prediction of disease prognosis has a critical role in confronting the burden of COVID-19. We aimed to investigate the feasibility of predicting COVID-19 patient outcomes and disease severity based on clinical and hematological parameters using machine learning techniques. This multicenter retrospective study analyzed records of 485 patients with COVID-19, including demographic information, symptoms, hematological variables, treatment information, and clinical outcomes. Different machine learning approaches, including random forest, multilayer perceptron, and support vector machine, were examined in this study. All models showed a comparable performance, yielding the best area under the curve of 0.96, in predicting the severity of disease and clinical outcome. We also identified the most relevant features in predicting COVID-19 patient outcomes, and we concluded that hematological parameters (neutrophils, lymphocytes, D-dimer, and monocytes) are the most predictive features of severity and patient outcome.