Dataset Information

A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers.

ABSTRACT: Novel coronavirus disease 2019 (COVID-19) is an emerging, rapidly evolving crisis, and the ability to predict prognosis for individual COVID-19 patient is important for guiding treatment. Laboratory examinations were repeatedly measured during hospitalization for COVID-19 patients, which provide the possibility for the individualized early prediction of prognosis. However, previous studies mainly focused on risk prediction based on laboratory measurements at one time point, ignoring disease progression and changes of biomarkers over time. By using historical regression trees (HTREEs), a novel machine learning method, and joint modeling technique, we modeled the longitudinal trajectories of laboratory biomarkers and made dynamically predictions on individual prognosis for 1997 COVID-19 patients. In the discovery phase, based on 358 COVID-19 patients admitted between 10 January and 18 February 2020 from Tongji Hospital, HTREE model identified a set of important variables including 14 prognostic biomarkers. With the trajectories of those biomarkers through 5-day, 10-day and 15-day, the joint model had a good performance in discriminating the survived and deceased COVID-19 patients (mean AUCs of 88.81, 84.81 and 85.62% for the discovery set). The predictive model was successfully validated in two independent datasets (mean AUCs of 87.61, 87.55 and 87.03% for validation the first dataset including 112 patients, 94.97, 95.78 and 94.63% for the second validation dataset including 1527 patients, respectively). In conclusion, our study identified important biomarkers associated with the prognosis of COVID-19 patients, characterized the time-to-event process and obtained dynamic predictions at the individual level.

SUBMITTER: Chen X

PROVIDER: S-EPMC8195146 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Host microRNAs can influence the cytokine storm associated SARS-CoV-2 infection and proposed as biomarkers for COVID-19 disease. In the present study, serum MiRNA-106a and miRNA-20a were quantified by real time-PCR in 50 COVID-19 patients hospitalized at Minia university hospital and 30 healthy volunteers. Profiles of serum inflammatory cytokines (TNF-α, IFN-γ, and IL-10) and TLR4 were analyzed by Eliza in patients and controls. A highly significant decrease (P value = 0.0001) in the expressions of miRNA-106a and miRNA-20a was reported in COVID-19 patients compared to controls. A significant decrease in the levels of miRNA-20a was also reported in patients with lymphopenia, patients having chest CT severity score (CSS) > 19 and in patients having O2 saturation less than 90%. Significantly higher levels of TNF-α, IFN-γ, IL-10 and TLR4 were reported in patients compared to controls. IL-10 and TLR4 levels were significantly higher in patients having lymphopenia. TLR-4 level was higher in patients with CSS > 19 and in patients with hypoxia. Using univariate logistic regression analysis, miRNA-106a, miRNA-20a, TNF-α, IFN-γ, IL-10 and TLR4 were identified as good predictors of disease. Receiver operating curve showed that the downregulation of miRNA-20a in patients having lymphopenia, patients with CSS > 19 and patients with hypoxia could be a potential biomarker with AUC = 0.68 ± 0.08, AUC = 0.73 ± 0.07 and AUC = 0.68 ± 0.07 respectively. Also, ROC curve showed accurate association between the increase of serum IL-10 and TLR-4 and lymphopenia among COVID-19 patients with AUC = 0.66 ± 0.08 and AUC = 0.73 ± 0.07 respectively. ROC curve showed also that serum TLR-4 could be a potential marker for high CSS with AUC = 0.78 ± 0.06. A negative correlation was detected between miRNA-20a with TLR-4 (r = - 0.30, P value = 0.03). We concluded that, miR-20a, is a potential biomarker of COVID-19 severity and blockade of IL-10 and TLR4 may constitute a novel therapy for COVID-19 patients.

Dataset Information

A predictive paradigm for COVID-19 prognosis based on the longitudinal measure of biomarkers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets