tetano
Editor, Senior Moderator
Arch Cardiovasc Dis
. 2022 Oct 22;S1875-2136(22)00194-2.
doi: 10.1016/j.acvd.2022.08.003. Online ahead of print.
Machine learning-based scoring system to predict in-hospital outcomes in patients hospitalized with COVID-19
Orianne Weizman[SUP] 1 [/SUP], Baptiste Duceau[SUP] 2 [/SUP], Antonin Trimaille[SUP] 3 [/SUP], Thibaut Pommier[SUP] 4 [/SUP], Joffrey Cellier[SUP] 5 [/SUP], Laura Geneste[SUP] 6 [/SUP], Vassili Panagides[SUP] 7 [/SUP], Wassima Marsou[SUP] 8 [/SUP], Antoine Deney[SUP] 9 [/SUP], Sabir Attou[SUP] 10 [/SUP], Thomas Delmotte[SUP] 11 [/SUP], Sophie Ribeyrolles[SUP] 12 [/SUP], Pascale Chemaly[SUP] 13 [/SUP], Clément Karsenty[SUP] 9 [/SUP], Gauthier Giordano[SUP] 14 [/SUP], Alexandre Gautier[SUP] 13 [/SUP], Corentin Chaumont[SUP] 15 [/SUP], Pierre Guilleminot[SUP] 4 [/SUP], Audrey Sagnard[SUP] 4 [/SUP], Julie Pastier[SUP] 4 [/SUP], Nacim Ezzouhairi[SUP] 16 [/SUP], Benjamin Perin[SUP] 14 [/SUP], Cyril Zakine[SUP] 17 [/SUP], Thomas Levasseur[SUP] 18 [/SUP], Iris Ma[SUP] 5 [/SUP], Diane Chavignier[SUP] 19 [/SUP], Nathalie Noirclerc[SUP] 20 [/SUP], Arthur Darmon[SUP] 21 [/SUP], Marine Mevelec[SUP] 19 [/SUP], Willy Sutter[SUP] 2 [/SUP], Delphine Mika[SUP] 22 [/SUP], Charles Fauvel[SUP] 15 [/SUP], Théo Pezel[SUP] 23 [/SUP], Victor Waldmann[SUP] 24 [/SUP], Ariel Cohen[SUP] 25 [/SUP], Guillaume Bonnet[SUP] 24 [/SUP], Critical COVID-19 France investigators
Affiliations
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.
Keywords: COVID-19; Prediction; Prognosis; Risk score; SARS-CoV-2.
. 2022 Oct 22;S1875-2136(22)00194-2.
doi: 10.1016/j.acvd.2022.08.003. Online ahead of print.
Machine learning-based scoring system to predict in-hospital outcomes in patients hospitalized with COVID-19
Orianne Weizman[SUP] 1 [/SUP], Baptiste Duceau[SUP] 2 [/SUP], Antonin Trimaille[SUP] 3 [/SUP], Thibaut Pommier[SUP] 4 [/SUP], Joffrey Cellier[SUP] 5 [/SUP], Laura Geneste[SUP] 6 [/SUP], Vassili Panagides[SUP] 7 [/SUP], Wassima Marsou[SUP] 8 [/SUP], Antoine Deney[SUP] 9 [/SUP], Sabir Attou[SUP] 10 [/SUP], Thomas Delmotte[SUP] 11 [/SUP], Sophie Ribeyrolles[SUP] 12 [/SUP], Pascale Chemaly[SUP] 13 [/SUP], Clément Karsenty[SUP] 9 [/SUP], Gauthier Giordano[SUP] 14 [/SUP], Alexandre Gautier[SUP] 13 [/SUP], Corentin Chaumont[SUP] 15 [/SUP], Pierre Guilleminot[SUP] 4 [/SUP], Audrey Sagnard[SUP] 4 [/SUP], Julie Pastier[SUP] 4 [/SUP], Nacim Ezzouhairi[SUP] 16 [/SUP], Benjamin Perin[SUP] 14 [/SUP], Cyril Zakine[SUP] 17 [/SUP], Thomas Levasseur[SUP] 18 [/SUP], Iris Ma[SUP] 5 [/SUP], Diane Chavignier[SUP] 19 [/SUP], Nathalie Noirclerc[SUP] 20 [/SUP], Arthur Darmon[SUP] 21 [/SUP], Marine Mevelec[SUP] 19 [/SUP], Willy Sutter[SUP] 2 [/SUP], Delphine Mika[SUP] 22 [/SUP], Charles Fauvel[SUP] 15 [/SUP], Théo Pezel[SUP] 23 [/SUP], Victor Waldmann[SUP] 24 [/SUP], Ariel Cohen[SUP] 25 [/SUP], Guillaume Bonnet[SUP] 24 [/SUP], Critical COVID-19 France investigators
Affiliations
- PMID: 36376208
- DOI: 10.1016/j.acvd.2022.08.003
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.
Keywords: COVID-19; Prediction; Prognosis; Risk score; SARS-CoV-2.