AUTHOR=Yu Zhixiang , Li Xiayin , Zhao Jin , Sun Shiren 

TITLE=Identification of hospitalized mortality of patients with COVID-19 by machine learning models based on blood inflammatory cytokines

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.1001340

DOI=10.3389/fpubh.2022.1001340

ISSN=2296-2565

ABSTRACT=COVID-19 spread worldwide and presented a significant threat to people's health. Inappropriate disease assessment and treatment strategies present a heavy burden on healthcare systems. Our study aimed to construct predictive models to assess COVID-19 patients who may have poor prognoses early and accurately. This research performed a retrospective analysis on two cohorts of COVID-19 patients. Data from the Barcelona cohort were used as the training set, and data from the Rotterdam cohort were used as the validation set. Logistic regression, randomforest (RF) and decision tree (DT) were used to construct COVID-19 death prognostic models. Based on multiple clinical characters and blood inflammatory cytokines during the first day of hospitalization for the 138 COVID-19 patients, we constructed various models to predict COVID-19 patients' prognoses. All the models showed outstanding performance in identifying low-risk and high-risk COVID-19 patients. The accuracy of the logistic regression, randomforest and decision tree models is 86.96%, 80.43%, and 85.51%, respectively. The models we developed can assist doctors in developing appropriate COVID-19 treatment strategies.