Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques
Yacheng Fu1,2, Weijun Zhong1,2, Tao Liu3
1Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, China.
Insights
This study identified 28 clinical indicators to predict severe COVID-19 progression. A risk model using these factors accurately identifies high-risk patients for early intervention.
Area of Science:
- Medical Research
- Clinical Medicine
- Infectious Diseases
Background:
- Sudden worsening to critical illness in novel coronavirus disease 2019 (COVID-19) patients is a significant concern.
- Early identification and triage of high-risk COVID-19 patients can improve outcomes and reduce healthcare system burden.
Purpose of the Study:
- To identify clinical and laboratory risk factors for predicting critical illness in COVID-19 patients upon hospital admission.
- To develop and validate a predictive model for early identification of patients at high risk of COVID-19 progression to critical illness.
Main Methods:
- Retrospective multicenter study involving 1,929 COVID-19 patients.
- Utilized logistic regression and least absolute shrinkage and selection operator (LASSO) logistic regression to identify predictors and construct a risk model.
- Validated the model on an external cohort of 566 patients.
Main Results:
- Identified 28 prognostic variables associated with critical illness in COVID-19.
- Key predictors included elevated levels of CK-MB, neutrophils, D-dimer, LDH, glucose, and decreased lymphocyte counts.
- The risk model demonstrated strong predictive accuracy with an area under the curve (AUC) of 0.83 in the development cohort and 0.84 in the validation cohort.
Conclusions:
- A risk prediction model based on laboratory findings can effectively identify COVID-19 patients at high risk of critical illness.
- The identified 28 indicators and the developed risk model can aid in early treatment and optimized resource allocation for critical COVID-19 cases.
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 a high risk of developing critical illness COVID-19 upon admission can aid in improving patient care, increasing the cure rate, and mitigating the burden on the medical care system. This study proposed and extended classical least absolute shrinkage and selection operator (LASSO) logistic regression to objectively identify clinical determination and risk factors for the 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 1,929 patients with COVID-19 were assessed. The association between laboratory characteristics measured at admission and critical illness was 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 a critical illness.
Results:
The development cohort consisted of 1,363 patients with COVID-19 with 133 (9.7%) patients developing the 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, and AST were predictors for the early identification of patients at high risk of progression to critical illness. Lymphopenia, a low rate of basophils, eosinophils, thrombopenia, red blood cell, hematocrit, hemoglobin concentration, blood platelet count, and decreased levels of K, Na, albumin, albumin to globulin ratio, and uric acid were clinical determinations associated with the 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).
Conclusion:
A risk prediction model based on laboratory findings of patients with COVID-19 was developed for the early identification of patients at high risk of progression to critical illness. This cohort study identified 28 indicators associated with critical illness of patients with COVID-19. The risk model might contribute to the treatment of critical illness disease as early as possible and allow for optimized use of medical resources.
