Machine learning-based scoring system to predict in-hospital outcomes in patients hospitalized with COVID-19
Orianne Weizman1, Baptiste Duceau2, Antonin Trimaille3
1Centre Hospitalier Régional Universitaire de Nancy, 54511 Vandoeuvre-lès-Nancy, France; Université de Paris, PARCC, INSERM, 75015 Paris, France.
Insights
A new Critical COVID-19 France (CCF) risk score accurately predicts outcomes for hospitalized coronavirus disease 2019 (COVID-19) patients. This tool aids in early patient triage and healthcare resource allocation during the pandemic.
Area of Science:
- Critical care medicine
- Infectious diseases
- Epidemiology
Background:
- Predicting patient evolution in coronavirus disease 2019 (COVID-19) remains challenging.
- Hospitalized COVID-19 patients exhibit varied clinical trajectories.
Purpose of the Study:
- To develop and validate a predictive score for outcomes in hospitalized COVID-19 patients.
- To enhance early risk stratification and resource allocation for COVID-19 cases.
Main Methods:
- Nationwide observational study of adult COVID-19 patients (February-April 2020).
- Development of a risk score using stacked Least Absolute Shrinkage and Selection Operator (LASSO) on a derivation cohort.
- Validation of the score in a separate cohort, assessing calibration and discrimination.
Main Results:
- The Critical COVID-19 France (CCF) risk score was developed from 11 independent variables (demographics, vitals, biological markers).
- The CCF score demonstrated accurate calibration and discrimination (C-statistic 0.78) in the derivation cohort.
- The CCF score outperformed existing critical care risk scores in predicting primary composite outcomes (ICU transfer or in-hospital death).
Conclusions:
- The CCF risk score, derived from routine admission data, effectively predicts COVID-19 patient outcomes.
- This validated score can improve early triage and optimize healthcare resource management for COVID-19.
- The CCF score offers a valuable tool for clinicians managing hospitalized COVID-19 patients.
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.
More Related Videos
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Related Concept Videos
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
01:18Steps in Outbreak Investigation