Immune and cellular damage biomarkers to predict COVID-19 mortality in hospitalized patients
Autor: | Marcello Cottini, Bruno Bertozzi, Alberto Franzin, Carlo Lombardi, Oscar Vivaldi, Elena Roca, Paolo Poggio, Camillo Ferrandina, A. D’Alessio, Gian Marco Conte, Alvise Berti, Barbara Bigni |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Platelets
medicine.medical_specialty LDH Coronavirus disease 2019 (COVID-19) Hospitalized patients Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Population Specialties of internal medicine Disease Article chemistry.chemical_compound Immune system Internal medicine medicine Lymphocytes Electrical and Electronic Engineering education Creatinine education.field_of_study business.industry SARS-CoV-2 COVID-19 In-hospital death Building and Construction Coronavirus chemistry RC581-951 Cohort business CRP |
Zdroj: | Current Research in Immunology, Vol 2, Iss, Pp 155-162 (2021) Current Research in Immunology |
ISSN: | 2590-2555 |
Popis: | Early prediction of COVID-19 in-hospital mortality relies usually on patients’ preexisting comorbidities and is rarely reproducible in independent cohorts. We wanted to compare the role of routinely measured biomarkers of immunity, inflammation, and cellular damage with preexisting comorbidities in eight different machine-learning models to predict mortality, and evaluate their performance in an independent population. We recruited and followed-up consecutive adult patients with SARS-Cov-2 infection in two different Italian hospitals. We predicted 60-day mortality in one cohort (development dataset, n = 299 patients, of which 80% was allocated to the development dataset and 20% to the training set) and retested the models in the second cohort (external validation dataset, n = 402). Demographic, clinical, and laboratory features at admission, treatments and disease outcomes were significantly different between the two cohorts. Notably, significant differences were observed for %lymphocytes (p Graphical abstract Image 1 |
Databáze: | OpenAIRE |
Externí odkaz: |