A prediction model of outcome of SARS-CoV-2 pneumonia based on laboratory findings

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in thousands of deaths in the world. Information about prediction model of prognosis of SARS-CoV-2 infection is scarce. We used machine learning for processing laboratory findings of 110 patients with SARS-CoV-2 pneumonia...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2020-08, Vol.10 (1), p.14042-14042, Article 14042
Main Authors: Wu, Gang, Zhou, Shuchang, Wang, Yujin, Lv, Wenzhi, Wang, Shili, Wang, Ting, Li, Xiaoming
Format: Article
Language:English
Subjects:
692/699/255
692/699/255/2514
Age
Aged
Algorithms
Artificial intelligence
Betacoronavirus - genetics
Bilirubin - blood
Blood
Blood platelets
Cochlea
Collagen
Coronavirus Infections - blood
Coronavirus Infections - therapy
Coronavirus Infections - virology
Coronaviruses
COVID-19
Cytokines
Data Accuracy
Degradation products
Dehydrogenases
Feasibility Studies
Feature selection
Female
Fibrin Fibrinogen Degradation Products - analysis
Forecasting - methods
Hearing
Hospitals
Humanities and Social Sciences
Humans
Infections
Laboratories
Leukocytes
Machine Learning
Male
Mapping
Models, Statistical
Mortality
multidisciplinary
Myoglobin - blood
Myoglobins
Neutrophils
Pandemics
Patients
Pneumonia
Pneumonia, Viral - blood
Pneumonia, Viral - therapy
Pneumonia, Viral - virology
Prediction models
Prognosis
Prothrombin - analysis
Receptors, Interleukin-2 - blood
Retrospective Studies
SARS-CoV-2
Science
Science (multidisciplinary)
Sensitivity and Specificity
Severe acute respiratory syndrome coronavirus 2
Treatment Outcome
Urea
Urea - blood
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in thousands of deaths in the world. Information about prediction model of prognosis of SARS-CoV-2 infection is scarce. We used machine learning for processing laboratory findings of 110 patients with SARS-CoV-2 pneumonia (including 51 non-survivors and 59 discharged patients). The maximum relevance minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator logistic regression model were used for selection of laboratory features. Seven laboratory features selected in the model were: prothrombin activity, urea, white blood cell, interleukin-2 receptor, indirect bilirubin, myoglobin, and fibrinogen degradation products. The signature constructed using the seven features had 98% [93%, 100%] sensitivity and 91% [84%, 99%] specificity in predicting outcome of SARS-CoV-2 pneumonia. Thus it is feasible to establish an accurate prediction model of outcome of SARS-CoV-2 pneumonia based on laboratory findings.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-71114-7