Multivariable Risk Modelling and Survival Analysis with Machine Learning in SARS-CoV-2 Infection
Ontology highlight
ABSTRACT:
SUBMITTER: Ciarmiello A
PROVIDER: S-EPMC10672177 | biostudies-literature | 2023 Nov
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The role of smoking in the risk of SARS-CoV-2 infection is unclear. We used a retrospective cohort design to study data from veterans' Electronic Medical Record to assess the impact of smoking on the risk of SARS-CoV-2 infection. Veterans tested for the SARS-CoV-2 virus from 02/01/2020 to 02/28/2021 were classified as: Never Smokers (NS), Former Smokers (FS), and Current Smokers (CS). We report the adjusted odds ratios (aOR) for potential confounders obtained from a cascade machine learning algorithm. We found a 19.6% positivity rate among 1,176,306 veterans tested for SARS-CoV-2 infection. The positivity proportion among NS (22.0%) was higher compared with FS (19.2%) and CS (11.5%). The adjusted odds of testing positive for CS (aOR:0.51; 95%CI: 0.50, 0.52) and FS (aOR:0.89; 95%CI:0.88, 0.90) were significantly lower compared with NS. Four pre-existing conditions, including dementia, lower respiratory infections, pneumonia, and septic shock, were associated with a higher risk of testing positive, whereas the use of the decongestant drug phenylephrine or having a history of cancer were associated with a lower risk. CS and FS compared with NS had lower risks of testing positive for SARS-CoV-2. These findings highlight our evolving understanding of the role of smoking status on the risk of SARS-CoV-2 infection.
| S-EPMC9319659 | biostudies-literature
Project description:The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has evolved many high-risk variants, resulting in repeated COVID-19 waves over the past years. Therefore, accurate early warning of high-risk variants is vital for epidemic prevention and control. However, detecting high-risk variants through experimental and epidemiological research is time-consuming and often lags behind the emergence and spread of these variants. In this study, HiRisk-Detector a machine learning algorithm based on haplotype network, is developed for computationally early detecting high-risk SARS-CoV-2 variants. Leveraging over 7.6 million high-quality and complete SARS-CoV-2 genomes and metadata, the effectiveness, robustness, and generalizability of HiRisk-Detector are validated. First, HiRisk-Detector is evaluated on actual empirical data, successfully detecting all 13 high-risk variants, preceding World Health Organization announcements by 27 days on average. Second, its robustness is tested by reducing sequencing intensity to one-fourth, noting only a minimal delay of 3.8 days, demonstrating its effectiveness. Third, HiRisk-Detector is applied to detect risks among SARS-CoV-2 Omicron variant sub-lineages, confirming its broad applicability and high ROC-AUC and PR-AUC performance. Overall, HiRisk-Detector features powerful capacity for early detection of high-risk variants, bearing great utility for any public emergency caused by infectious diseases or viruses.
| S-EPMC11615786 | biostudies-literature
Project description:Asymptomatic COVID-19 has become one of the biggest challenges for controlling the spread of the SARS-CoV-2. Diagnosis of asymptomatic COVID-19 mainly depends on quantitative reverse transcription PCR (qRT-PCR), which is typically time-consuming and requires expensive reagents. The application is limited in countries that lack sufficient resources to handle large-scale assay during the COVID-19 outbreak. Here, we demonstrated a new approach to detect the asymptomatic SARS-CoV-2 infection using serum metabolic patterns combined with ensemble learning. The direct patterns of metabolites and lipids were extracted by matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) within 1 s with simple sample preparation. A new ensemble learning model was developed using stacking strategy with a new voting algorithm. This approach was validated in a large cohort of 274 samples (92 asymptomatic COVID-19 and 182 healthy control), and provided the high accuracy of 93.4%, with only 5% false negative and 7% false positive rates. We also identified a biomarker panel of ten metabolites and lipids, as well as the altered metabolic pathways during asymptomatic SARS-CoV-2 Infection. The proposed rapid and low-cost approach holds promise to apply in the large-scale asymptomatic COVID-19 screening.
| S-EPMC8517325 | biostudies-literature
Project description:The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) induces B and T cell responses, contributing to virus neutralization. In a cohort of 2,911 young adults, we identified 65 individuals who had an asymptomatic or mildly symptomatic SARS-CoV-2 infection and characterized their humoral and T cell responses to the Spike (S), Nucleocapsid (N) and Membrane (M) proteins. We found that previous infection induced CD4 T cells that vigorously responded to pools of peptides derived from the S and N proteins. By using statistical and machine learning models, we observed that the T cell response highly correlated with a compound titer of antibodies against the Receptor Binding Domain (RBD), S and N. However, while serum antibodies decayed over time, the cellular phenotype of these individuals remained stable over four months. Our computational analysis demonstrates that in young adults, asymptomatic and paucisymptomatic SARS-CoV-2 infections can induce robust and long-lasting CD4 T cell responses that exhibit slower decays than antibody titers. These observations imply that next-generation COVID-19 vaccines should be designed to induce stronger cellular responses to sustain the generation of potent neutralizing antibodies.
| S-EPMC10258347 | biostudies-literature
Project description:Interpretable risk assessment of SARS-CoV-2 positive patients can aid clinicians to implement precision medicine. Here we trained a machine learning model to predict mortality within 12 weeks of a first positive SARS-CoV-2 test. By leveraging data on 33,938 confirmed SARS-CoV-2 cases in eastern Denmark, we considered 2723 variables extracted from electronic health records (EHR) including demographics, diagnoses, medications, laboratory test results and vital parameters. A discrete-time framework for survival modelling enabled us to predict personalized survival curves and explain individual risk factors. Performance on the test set was measured with a weighted concordance index of 0.95 and an area under the curve for precision-recall of 0.71. Age, sex, number of medications, previous hospitalizations and lymphocyte counts were identified as top mortality risk factors. Our explainable survival model developed on EHR data also revealed temporal dynamics of the 22 selected risk factors. Upon further validation, this model may allow direct reporting of personalized survival probabilities in routine care.
| S-EPMC9380679 | biostudies-literature
Project description:BackgroundThe COVID-19 pandemic has disrupted the delivery of immunisation services globally. Many countries have postponed vaccination campaigns out of concern about infection risks to the staff delivering vaccination, the children being vaccinated, and their families. The World Health Organization recommends considering both the benefit of preventive campaigns and the risk of SARS-CoV-2 transmission when making decisions about campaigns during COVID-19 outbreaks, but there has been little quantification of the risks.MethodsWe modelled excess SARS-CoV-2 infection risk to vaccinators, vaccinees, and their caregivers resulting from vaccination campaigns delivered during a COVID-19 epidemic. Our model used population age structure and contact patterns from three exemplar countries (Burkina Faso, Ethiopia, and Brazil). It combined an existing compartmental transmission model of an underlying COVID-19 epidemic with a Reed-Frost model of SARS-CoV-2 infection risk to vaccinators and vaccinees. We explored how excess risk depends on key parameters governing SARS-CoV-2 transmissibility, and aspects of campaign delivery such as campaign duration, number of vaccinations, and effectiveness of personal protective equipment (PPE) and symptomatic screening.ResultsInfection risks differ considerably depending on the circumstances in which vaccination campaigns are conducted. A campaign conducted at the peak of a SARS-CoV-2 epidemic with high prevalence and without special infection mitigation measures could increase absolute infection risk by 32 to 45% for vaccinators and 0.3 to 0.5% for vaccinees and caregivers. However, these risks could be reduced to 3.6 to 5.3% and 0.1 to 0.2% respectively by use of PPE that reduces transmission by 90% (as might be achieved with N95 respirators or high-quality surgical masks) and symptomatic screening.ConclusionsSARS-CoV-2 infection risks to vaccinators, vaccinees, and caregivers during vaccination campaigns can be greatly reduced by adequate PPE, symptomatic screening, and appropriate campaign timing. Our results support the use of adequate risk mitigation measures for vaccination campaigns held during SARS-CoV-2 epidemics, rather than cancelling them entirely.
| S-EPMC8359640 | biostudies-literature
Project description:The COVID-19 pandemic has disrupted delivery of immunisation services globally. Many countries have postponed vaccination campaigns out of concern about infection risks to staff delivering vaccination, the children being vaccinated and their families. The World Health Organization recommends considering both the benefit of preventive campaigns and the risk of SARS-CoV-2 transmission when making decisions about campaigns during COVID-19 outbreaks, but there has been little quantification of the risks. We modelled excess SARS-CoV-2 infection risk to vaccinators, vaccinees and their caregivers resulting from vaccination campaigns delivered during a COVID-19 epidemic. Our model used population age-structure and contact patterns from three exemplar countries (Burkina Faso, Ethiopia, and Brazil). It combined an existing compartmental transmission model of an underlying COVID-19 epidemic with a Reed-Frost model of SARS-CoV-2 infection risk to vaccinators and vaccinees. We explored how excess risk depends on key parameters governing SARS-CoV-2 transmissibility, and aspects of campaign delivery such as campaign duration, number of vaccinations, and effectiveness of personal protective equipment (PPE) and symptomatic screening. Infection risks differ considerably depending on the circumstances in which vaccination campaigns are conducted. A campaign conducted at the peak of a SARS-CoV-2 epidemic with high prevalence and without special infection mitigation measures could increase absolute infection risk by 32% to 45% for vaccinators, and 0.3% to 0.5% for vaccinees and caregivers. However, these risks could be reduced to 3.6% to 5.3% and 0.1% to 0.2% respectively by use of PPE that reduces transmission by 90% (as might be achieved with N95 respirators or high-quality surgical masks) and symptomatic screening. SARS-CoV-2 infection risks to vaccinators, vaccinees and caregivers during vaccination campaigns can be greatly reduced by adequate PPE, symptomatic screening, and appropriate campaign timing. Our results support the use of adequate risk mitigation measures for vaccination campaigns held during SARS-CoV-2 epidemics, rather than cancelling them entirely.
| S-EPMC8142667 | biostudies-literature
Project description:The antibiotic catabolic process and myeloid cell homeostasis were activated while the T-cell response were relatively repressed in those with the risk of secondary infection.
2021-09-20 | GSE184401 | GEO
Project description:BackgroundTo determine whether severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2, the cause of COVID-19 disease) exposure in pregnancy, compared to non-exposure, is associated with infection-related obstetric morbidity.MethodsWe conducted a multicentre prospective study in pregnancy based on a universal antenatal screening program for SARS-CoV-2 infection. Throughout Spain 45 hospitals tested all women at admission on delivery ward using polymerase-chain-reaction (PCR) for COVID-19 since late March 2020. The cohort of positive mothers and the concurrent sample of negative mothers was followed up until 6-weeks post-partum. Multivariable logistic regression analysis, adjusting for known confounding variables, determined the adjusted odds ratio (aOR) with 95% confidence intervals (95% CI) of the association of SARS-CoV-2 infection and obstetric outcomes.Main outcome measuresPreterm delivery (primary), premature rupture of membranes and neonatal intensive care unit admissions.ResultsAmong 1009 screened pregnancies, 246 were SARS-CoV-2 positive. Compared to negative mothers (763 cases), SARS-CoV-2 infection increased the odds of preterm birth (34 vs 51, 13.8% vs 6.7%, aOR 2.12, 95% CI 1.32-3.36, p = 0.002); iatrogenic preterm delivery was more frequent in infected women (4.9% vs 1.3%, p = 0.001), while the occurrence of spontaneous preterm deliveries was statistically similar (6.1% vs 4.7%). An increased risk of premature rupture of membranes at term (39 vs 75, 15.8% vs 9.8%, aOR 1.70, 95% CI 1.11-2.57, p = 0.013) and neonatal intensive care unit admissions (23 vs 18, 9.3% vs 2.4%, aOR 4.62, 95% CI 2.43-8.94, p < 0.001) was also observed in positive mothers.ConclusionThis prospective multicentre study demonstrated that pregnant women infected with SARS-CoV-2 have more infection-related obstetric morbidity. This hypothesis merits evaluation of a causal association in further research.
| S-EPMC8016158 | biostudies-literature
Project description:Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has infected millions of individuals worldwide, causing a severe global pandemic. Mice models are wildly used to investigate viral infection pathology, antiviral drugs, and vaccine development. However, since wild-type mice do not express human angiotensin-converting enzyme 2 (hACE2), which mediates SARS-CoV-2 entry into human cells, they are not susceptible to infection with SARS-CoV-2 and are not suitable to simulate symptomatic COVID-19 disease. HACE2 transgenic mice could provide an efficient model, but they are expensive, not always readily available and practically restricted to specific strain(s). Since additional models are needed to study the disease at varying genetic and immune backgrounds, there is a dearth of mouse models for SARS-CoV-2 infection. Here we report the application of lentiviral vectors to generate hACE2 expression in mouse lung epithelial cells (LET1) as well as in interferon receptor knock-out (IFNAR1-/-) mice. Lenti-hACE2 transduction supported SARS-CoV-2 replication both in vitro and in vivo, simulating mild acute lung disease1. Gene expression analysis revealed two modes of immune responses to SARS-CoV-2 infection: one in response to the exposure of mouse lungs to SARS-CoV-2 particles in the absence of productive viral replication, and the second in response to a productive infection. This approach expands our knowledge on the role of type-1 interferon signaling in COVID-19 disease, and can be further implemented for a range of COVID-19 studies and drug development.
2021-12-07 | GSE186167 | GEO