AUTHOR=Fu Yacheng , Zhong Weijun , Liu Tao , Li Jianmin , Xiao Kui , Ma Xinhua , Xie Lihua , Jiang Junyi , Zhou Honghao , Liu Rong , Zhang Wei 

TITLE=Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.880999

DOI=10.3389/fpubh.2022.880999

ISSN=2296-2565

ABSTRACT=Motivation: Patients with novel coronavirus disease 2019 (COVID-19) worsen into critical illness suddenly is a matter of great concern. Early identification and effective triaging of patients with high risk of developing of critical illness COVID-19 upon admission can be aid in improving patient care, increasing the cure rate and mitigating the burden on the medical care system.The present study  proposed and extended classical Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression to objectively identify clinical determination and risk factors for early identification of patients at high risk of progression to critical illness at the time of hospital admission.
Methods: In this retrospective multicenter study, data of 1929 COVID-19 patients were assessed. The association between laboratory characteristics measured at admission and critical illness were screened with logistic regression. LASSO logistic regression was utilized to construct predictive models for estimating the risk that a patient with COVID-19 will develop critical illness. 
Results: The development cohort consisted of 1363 COVID-19 patients with 133 (9.7%) patients developed critical illness. Univariate logistic regression analysis revealed 28 variables were prognosis factors for critical illness COVID-19  (p<0.05). Elevated CK-MB, neutrophils, PCT, α-HBDH, d-dimer, LDH, glucose, PT, APTT, RDW (SD and CV), fibrinogen, AST were predictors for early identification of patients at high risk of progression to critical illness. Lymphopenia, a low rate of basophils, eosinophils, thrombopenia, red blood cell, hematokrit, hemoglobin concentration, blood platelet count, and decreased levels of K, Na, albumin, albumin to globulin ratio and uric acid were clinical determinations associated with development of critical illness at the time of hospital admission. The risk score accurately predicted critical illness in the development cohort (area under the curve [AUC]=0.83, 95% CI: 0.78-0.86), also in the external validation cohort (n=566, AUC=0.84). 
Conclusions: A risk prediction model based on laboratory findings of COVID-19 patients was developed for early identification of patients at high risk of progression to critical illness. This cohort study identified 28 indicators be associated with critical illness of COVID-19 patients. The risk model might contribute to the treatment of critical illness disease as early as possible and allow for optimize use of medical resources.