SARS-CoV-2 Genetic Variants and Patient Factors Associated with Hospitalization Risk
Korves, T.; Stein, D.; Walburger, D.; Adamusiak, T.; Roberts, S.
Show abstract
Variants of SARS-CoV-2 have been associated with different transmissibilities and disease severities. The present study examines SARS-CoV-2 genetic variants and their relationship to risk for hospitalization, using data from 12,538 patients from a large, multisite observational cohort study. The association of viral genomic variants and hospitalization is examined with clinical covariates, including COVID-19 vaccination status, outpatient monoclonal antibody treatment status, and underlying risk for poor clinical outcome. Modeling approaches include XGBoost with SHapley Additive exPlanations (SHAP) analysis and generalized linear mixed models. The results indicate that several SARS-CoV-2 lineages are associated with increased hospitalization risk, including B.1.1.7, AY.44, and AY.54. As found in prior studies, Omicron is associated with lower hospitalization risk compared to prior WHO variants. In addition, the results suggest that variants at specific amino acid locations, including locations within Spike protein N-terminal domain and in non-structural protein 14, are associated with hospitalization risk.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Performance of Existing and Novel Symptom- and Antigen Testing-Based COVID-19 Case Definitions in a Community Setting 92%
- Adjusting COVID-19 seroprevalence survey results to account for test sensitivity and specificity 91%
- Misclassification of yellow fever vaccination status revealed through hierarchical Bayesian modeling 91%
Similar papers in this journal
- Development of a prediction model for 30-day COVID-19 hospitalization and death in a national cohort of Veterans Health Administration patients – March 2022 - April 2023 94%
- SARS-CoV-2 Omicron subvariant genomic variation associations with immune evasion in Northern California: A retrospective cohort study 93%
- Predicting Clinical Outcomes of SARS-CoV-2 Infection During the Omicron Wave Using Machine Learning 93%
Similar papers in this journal
- SARS-CoV-2 variants associated with vaccine breakthrough in the Delaware Valley through summer 2021 95%
- Molecular Architecture of Early Dissemination and Evolution of the SARS-CoV-2 Virus in Metropolitan Houston, Texas 94%
- Enhanced virus detection and metagenomic sequencing in patients with meningitis and encephalitis 92%
Similar papers in this journal
- MOATAI-VIR - an AI algorithm that predicts severe adverse events and molecular features for COVID-19’s complications 93%
- PACIFIC: A lightweight deep-learning classifier of SARS-CoV-2 and co-infecting RNA viruses 93%
- A comparative recombination analysis of human coronaviruses and implications for the SARS-CoV-2 pandemic 93%
Similar papers in this journal
- Sensible Long-lead Forecast of COVID-19 Epidemic Outcomes 93%
- Learning patterns of HIV-1 co-resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning 93%
- Genome-wide association study between SARS-CoV-2 single nucleotide polymorphisms and virus copies during infections 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.