2022
DOI: 10.2459/jcm.0000000000001329
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning for prediction of in-hospital mortality in coronavirus disease 2019 patients: results from an Italian multicenter study

Abstract: BackgroundSeveral risk factors have been identified to predict worse outcomes in patients affected by SARS-CoV-2 infection. Machine learning algorithms represent a novel approach to identifying a prediction model with a good discriminatory capacity to be easily used in clinical practice. The aim of this study was to obtain a risk score for in-hospital mortality in patients with coronavirus disease infection (COVID-19) based on a limited number of features collected at hospital admission.Methods and resultsWe s… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

3
2

Authors

Journals

citations
Cited by 6 publications
(7 citation statements)
references
References 35 publications
0
7
0
Order By: Relevance
“…Spearman correlations (ρ s ) between couples of quantitative variables were visualized by means of a correlation plot since this is the best way to show relationships between the data. Blue and red circles correspond to positive and negative correlations, respectively [24][25][26][27]. The circle diameters and the color intensities are proportional to the magnitude of Spearman indexes; moreover, the black crosses on them identify correlations not significantly different from zero (in other terms, p-values > 0.05).…”
Section: Discussionmentioning
confidence: 99%
“…Spearman correlations (ρ s ) between couples of quantitative variables were visualized by means of a correlation plot since this is the best way to show relationships between the data. Blue and red circles correspond to positive and negative correlations, respectively [24][25][26][27]. The circle diameters and the color intensities are proportional to the magnitude of Spearman indexes; moreover, the black crosses on them identify correlations not significantly different from zero (in other terms, p-values > 0.05).…”
Section: Discussionmentioning
confidence: 99%
“…SARS-CoV-2 infection may also trigger endothelial and microvascular dysfunction that, combined with systemic inflammation, can lead to multiorgan involvement and to a prothrombotic state, with frequent thromboembolic events 29,31–34 . Of note, the severity of the disease can be influenced by multiple factors 35,36 . Among patients hospitalized with laboratory confirmed COVID-19, machine learning algorithms identified age, oxygen saturation, PaO 2 /FiO 2 , creatinine clearance and troponin levels as the most relevant variables that predicted outcome 36 …”
Section: Coronavirus Disease 2019: Clinical Coursementioning
confidence: 99%
“…29,[31][32][33][34] Of note, the severity of the disease can be influenced by multiple factors. 35,36 Among patients hospitalized with laboratory confirmed COVID-19, machine learning algorithms identified age, oxygen saturation, PaO 2 /FiO 2 , creatinine clearance and troponin levels as the most relevant variables that predicted outcome. 36…”
Section: Coronavirus Disease 2019: Clinical Coursementioning
confidence: 99%
“…COVID-19, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), rapidly spread worldwide, becoming a pandemic. Whereas most clinical manifestations of COVID-19 are related to respiratory distress, cardiovascular involvement has been reported, showing an association with worse outcomes 32,33 . Point-of-care cardiac ultrasound abnormalities have been described, including LV hypertrophy, mild pericardial effusion and RV dilatation, with mostly preserved LV and RV systolic functions.…”
mentioning
confidence: 99%
“…Whereas most clinical manifestations of COVID-19 are related to respiratory distress, cardiovascular involvement has been reported, showing an association with worse outcomes. 32,33 Point-of-care cardiac ultrasound abnormalities have been described, including LV hypertrophy, mild pericardial effusion and RV dilatation, with mostly preserved LV and RV systolic functions. LV hypertrophy was independently associated with severe respiratory distress; RV dilatation was associated with longer length of hospitalization, without association with in-hospital mortality.…”
mentioning
confidence: 99%