Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
1.
Eur Respir J ; 56(2)2020 08.
Article in English | MEDLINE | ID: covidwho-744960

ABSTRACT

BACKGROUND: The outbreak of coronavirus disease 2019 (COVID-19) has globally strained medical resources and caused significant mortality. OBJECTIVE: To develop and validate a machine-learning model based on clinical features for severity risk assessment and triage for COVID-19 patients at hospital admission. METHOD: 725 patients were used to train and validate the model. This included a retrospective cohort from Wuhan, China of 299 hospitalised COVID-19 patients from 23 December 2019 to 13 February 2020, and five cohorts with 426 patients from eight centres in China, Italy and Belgium from 20 February 2020 to 21 March 2020. The main outcome was the onset of severe or critical illness during hospitalisation. Model performances were quantified using the area under the receiver operating characteristic curve (AUC) and metrics derived from the confusion matrix. RESULTS: In the retrospective cohort, the median age was 50 years and 137 (45.8%) were male. In the five test cohorts, the median age was 62 years and 236 (55.4%) were male. The model was prospectively validated on five cohorts yielding AUCs ranging from 0.84 to 0.93, with accuracies ranging from 74.4% to 87.5%, sensitivities ranging from 75.0% to 96.9%, and specificities ranging from 55.0% to 88.0%, most of which performed better than the pneumonia severity index. The cut-off values of the low-, medium- and high-risk probabilities were 0.21 and 0.80. The online calculators can be found at www.covid19risk.ai. CONCLUSION: The machine-learning model, nomogram and online calculator might be useful to access the onset of severe and critical illness among COVID-19 patients and triage at hospital admission.


Subject(s)
Coronavirus Infections/diagnosis , Hospital Mortality/trends , Machine Learning , Pneumonia, Viral/diagnosis , Triage/methods , Adult , Age Factors , Aged , Area Under Curve , Belgium , COVID-19 , COVID-19 Testing , China , Clinical Laboratory Techniques , Cohort Studies , Coronavirus Infections/epidemiology , Decision Support Systems, Clinical , Female , Hospitalization/statistics & numerical data , Humans , Internationality , Italy , Male , Middle Aged , Pandemics/statistics & numerical data , Pneumonia, Viral/epidemiology , Predictive Value of Tests , ROC Curve , Reproducibility of Results , Retrospective Studies , Risk Assessment , Severity of Illness Index , Sex Factors , Survival Analysis
2.
Clin Imaging ; 69: 33-36, 2021 Jan.
Article in English | MEDLINE | ID: covidwho-653904

ABSTRACT

The coronavirus disease 2019 (COVID-19) outbreak, first reported in Wuhan, China, is gradually spreading worldwide. For diagnosis, chest computed tomography is a conventional, noninvasive imaging modality that is very accurate for detection and evaluation of pneumonia and is an important adjunct to real-time reverse transcription polymerase chain reaction diagnosis of the virus. Previous studies have reported typical computed tomography imaging features indicative of COVID-19, such as multifocal ground-glass opacities with or without consolidation. With the sharply increasing demand for computed tomography examination during the outbreak, ensuring appropriate infection control in radiology departments is challenging. Thus, advanced training and education in standardized infection control and prevention practice are essential. The purpose of this brief review is to summarize such training and education for clinical management of this outbreak for radiology department personnel. We will describe standard transmission-based precautions, workflow for computed tomography examination of fever patients, and decontamination management of a radiology department.


Subject(s)
Betacoronavirus , COVID-19 , Coronavirus Infections , Pneumonia, Viral , Radiology , China/epidemiology , Coronavirus Infections/diagnostic imaging , Coronavirus Infections/epidemiology , Coronavirus Infections/prevention & control , Humans , Infection Control , Pandemics , Pneumonia, Viral/epidemiology , SARS-CoV-2
SELECTION OF CITATIONS
SEARCH DETAIL