TY - JOUR
T1 - Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients
AU - Montomoli, Jonathan
AU - Romeo, Luca
AU - Moccia, Sara
AU - Bernardini, Michele
AU - Migliorelli, Lucia
AU - Berardini, Daniele
AU - Donati, Abele
AU - Carsetti, Andrea
AU - Bocci, Maria Grazia
AU - Wendel Garcia, Pedro David
AU - Fumeaux, Thierry
AU - Guerci, Philippe
AU - Schüpbach, Reto Andreas
AU - Ince, Can
AU - Frontoni, Emanuele
AU - Hilty, Matthias Peter
AU - RISC-19-ICU Investigators
AU - Alfaro-Farias, Mario
AU - Vizmanos-Lamotte, Gerardo
AU - Tschoellitsch, Thomas
AU - Meier, Jens
AU - Aguirre-Bermeo, Hernán
AU - Apolo, Janina
AU - Martínez, Alberto
AU - Jurkolow, Geoffrey
AU - Delahaye, Gauthier
AU - Novy, Emmanuel
AU - Losser, Marie-Reine
AU - Wengenmayer, Tobias
AU - Rilinger, Jonathan
AU - Staudacher, Dawid L.
AU - David, Sascha
AU - Welte, Tobias
AU - Stahl, Klaus
AU - Pavlos”, “Agios
AU - Aslanidis, Theodoros
AU - Korsos, Anita
AU - Babik, Barna
AU - Nikandish, Reza
AU - Rezoagli, Emanuele
AU - Giacomini, Matteo
AU - Nova, Alice
AU - Fogagnolo, Alberto
AU - Spadaro, Savino
AU - Ceriani, Roberto
AU - Murrone, Martina
AU - Wu, Maddalena A.
AU - Cogliati, Chiara
AU - Colombo, Riccardo
AU - Catena, Emanuele
AU - Turrini, Fabrizio
PY - 2021/10/1
Y1 - 2021/10/1
N2 - Background: Accurate risk stratification of critically ill patients with coronavirus disease 2019 (COVID-19) is essential for optimizing resource allocation, delivering targeted interventions, and maximizing patient survival probability. Machine learning (ML) techniques are attracting increased interest for the development of prediction models as they excel in the analysis of complex signals in data-rich environments such as critical care. Methods: We retrieved data on patients with COVID-19 admitted to an intensive care unit (ICU) between March and October 2020 from the RIsk Stratification in COVID-19 patients in the Intensive Care Unit (RISC-19-ICU) registry. We applied the Extreme Gradient Boosting (XGBoost) algorithm to the data to predict as a binary outcome the increase or decrease in patients’ Sequential Organ Failure Assessment (SOFA) score on day 5 after ICU admission. The model was iteratively cross-validated in different subsets of the study cohort. Results: The final study population consisted of 675 patients. The XGBoost model correctly predicted a decrease in SOFA score in 320/385 (83%) critically ill COVID-19 patients, and an increase in the score in 210/290 (72%) patients. The area under the mean receiver operating characteristic curve for XGBoost was significantly higher than that for the logistic regression model (0.86 vs. 0.69, P < 0.01 [paired t-test with 95% confidence interval]). Conclusions: The XGBoost model predicted the change in SOFA score in critically ill COVID-19 patients admitted to the ICU and can guide clinical decision support systems (CDSSs) aimed at optimizing available resources.
AB - Background: Accurate risk stratification of critically ill patients with coronavirus disease 2019 (COVID-19) is essential for optimizing resource allocation, delivering targeted interventions, and maximizing patient survival probability. Machine learning (ML) techniques are attracting increased interest for the development of prediction models as they excel in the analysis of complex signals in data-rich environments such as critical care. Methods: We retrieved data on patients with COVID-19 admitted to an intensive care unit (ICU) between March and October 2020 from the RIsk Stratification in COVID-19 patients in the Intensive Care Unit (RISC-19-ICU) registry. We applied the Extreme Gradient Boosting (XGBoost) algorithm to the data to predict as a binary outcome the increase or decrease in patients’ Sequential Organ Failure Assessment (SOFA) score on day 5 after ICU admission. The model was iteratively cross-validated in different subsets of the study cohort. Results: The final study population consisted of 675 patients. The XGBoost model correctly predicted a decrease in SOFA score in 320/385 (83%) critically ill COVID-19 patients, and an increase in the score in 210/290 (72%) patients. The area under the mean receiver operating characteristic curve for XGBoost was significantly higher than that for the logistic regression model (0.86 vs. 0.69, P < 0.01 [paired t-test with 95% confidence interval]). Conclusions: The XGBoost model predicted the change in SOFA score in critically ill COVID-19 patients admitted to the ICU and can guide clinical decision support systems (CDSSs) aimed at optimizing available resources.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85127528872&origin=inward
U2 - https://doi.org/10.1016/j.jointm.2021.09.002
DO - https://doi.org/10.1016/j.jointm.2021.09.002
M3 - Article
SN - 2097-0250
VL - 1
SP - 110
EP - 116
JO - Journal of Intensive Medicine
JF - Journal of Intensive Medicine
IS - 2
ER -