Machine learning-based scoring system to predict in-hospital outcomes in patients hospitalized with COVID-19 - 10/12/22
, Guillaume Bonnet b, e, 1for the Critical COVID-19 France investigators
Bienvenue sur EM-consulte, la référence des professionnels de santé.
Article gratuit.
Connectez-vous pour en bénéficier!
Highlights |
• | Using machine learning techniques, the CCF risk score was developed to predict in-hospital outcomes in COVID-19. |
• | All hospitalized COVID-19 patients from a nationwide multicentre observational study were included. |
• | The CCF risk score aimed to estimate the risk of transfer to an intensive care unit or in-hospital death. |
• | Eleven clinical and biological variables were selected with good calibration and discrimination. |
• | The CCF risk score performed significantly better than the usual critical care risk scores. |
Abstract |
Background |
The evolution of patients hospitalized with coronavirus disease 2019 (COVID-19) is still hard to predict, even after several months of dealing with the pandemic.
Aims |
To develop and validate a score to predict outcomes in patients hospitalized with COVID-19.
Methods |
All consecutive adults hospitalized for COVID-19 from February to April 2020 were included in a nationwide observational study. Primary composite outcome was transfer to an intensive care unit from an emergency department or conventional ward, or in-hospital death. A score that estimates the risk of experiencing the primary outcome was constructed from a derivation cohort using stacked LASSO (Least Absolute Shrinkage and Selection Operator), and was tested in a validation cohort.
Results |
Among 2873 patients analysed (57.9% men; 66.6±17.0 years), the primary outcome occurred in 838 (29.2%) patients: 551 (19.2%) were transferred to an intensive care unit; and 287 (10.0%) died in-hospital without transfer to an intensive care unit. Using stacked LASSO, we identified 11 variables independently associated with the primary outcome in multivariable analysis in the derivation cohort (n=2313), including demographics (sex), triage vitals (body temperature, dyspnoea, respiratory rate, fraction of inspired oxygen, blood oxygen saturation) and biological variables (pH, platelets, C-reactive protein, aspartate aminotransferase, estimated glomerular filtration rate). The Critical COVID-19 France (CCF) risk score was then developed, and displayed accurate calibration and discrimination in the derivation cohort, with C-statistics of 0.78 (95% confidence interval 0.75–0.80). The CCF risk score performed significantly better (i.e. higher C-statistics) than the usual critical care risk scores.
Conclusions |
The CCF risk score was built using data collected routinely at hospital admission to predict outcomes in patients with COVID-19. This score holds promise to improve early triage of patients and allocation of healthcare resources.
Le texte complet de cet article est disponible en PDF.Keywords : COVID-19, SARS-CoV-2, Risk score, Prediction, Prognosis
Abbreviations : CCF, CI, COVID-19, CURB-65, ICU, IQR, LASSO, PREDICO, qSOFA, SARS-CoV-2, SOFA
Plan
| ☆ | Tweet: A new machine learning-based risk score to predict in-hospital outcomes in patients hospitalized with COVID-19. The CCF risk score, based on 11 simple variables, can help predict outcomes, with an online calculator available. |
Vol 115 - N° 12
P. 617-626 - décembre 2022 Retour au numéro
Article précédent
- Calcific mitral valve disease: The next challenging disease
- David Messika-Zeitoun, Nadav Willner, Ian G. Burwash
- Clustering of patients with inconclusive non-invasive stress testing referred for vasodilator stress cardiovascular magnetic resonance
- Théo Pezel, Guillaume Bonnet, Marine Kinnel, Anouk Asselin, Thomas Hovasse, Thierry Unterseeh, Stéphane Champagne, Francesca Sanguineti, Solenn Toupin, Philippe Garot, Jérôme Garot
Bienvenue sur EM-consulte, la référence des professionnels de santé.