Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques
MotivationPatients 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, inc...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-05-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.880999/full |
| _version_ | 1811255525064572928 |
|---|---|
| author | Yacheng Fu Yacheng Fu Weijun Zhong Weijun Zhong Tao Liu Jianmin Li Kui Xiao Xinhua Ma Lihua Xie Junyi Jiang Junyi Jiang Honghao Zhou Honghao Zhou Rong Liu Rong Liu Wei Zhang Wei Zhang |
| author_facet | Yacheng Fu Yacheng Fu Weijun Zhong Weijun Zhong Tao Liu Jianmin Li Kui Xiao Xinhua Ma Lihua Xie Junyi Jiang Junyi Jiang Honghao Zhou Honghao Zhou Rong Liu Rong Liu Wei Zhang Wei Zhang |
| author_sort | Yacheng Fu |
| collection | DOAJ |
| description | MotivationPatients 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.MethodsIn 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.ResultsThe 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).ConclusionA 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. |
| first_indexed | 2024-04-12T17:25:09Z |
| format | Article |
| id | doaj.art-356c8af5c5ff4190a9cb853d1427245d |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-04-12T17:25:09Z |
| publishDate | 2022-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-356c8af5c5ff4190a9cb853d1427245d2022-12-22T03:23:19ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-05-011010.3389/fpubh.2022.880999880999Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning TechniquesYacheng Fu0Yacheng Fu1Weijun Zhong2Weijun Zhong3Tao Liu4Jianmin Li5Kui Xiao6Xinhua Ma7Lihua Xie8Junyi Jiang9Junyi Jiang10Honghao Zhou11Honghao Zhou12Rong Liu13Rong Liu14Wei Zhang15Wei Zhang16Department of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaDepartment of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaShenzhen Center for Chronic Disease Control, Shenzhen, ChinaDepartment of Pulmonary and Critical Care Medicine, Hunan Provincial People's Hospital, The First Affiliated Hospital of Hunan Normal University, Changsha, ChinaDepartment of Pulmonary and Critical Care Medicine, The Second Xiangya Hospital, Central South University, Changsha, ChinaUnion Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaB7 Department, Zhongfa District of Tongji Hospital, Tongji Medical, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaDepartment of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaDepartment of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaDepartment of Clinical Pharmacology, Xiangya Hospital, Central South University, Changsha, ChinaNational Clinical Research Center for Geriatric Disorders, Changsha, ChinaMotivationPatients 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.MethodsIn 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.ResultsThe 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).ConclusionA 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.https://www.frontiersin.org/articles/10.3389/fpubh.2022.880999/fullCOVID-19risk factorscritical illnessmachine learningLASSO regression |
| spellingShingle | Yacheng Fu Yacheng Fu Weijun Zhong Weijun Zhong Tao Liu Jianmin Li Kui Xiao Xinhua Ma Lihua Xie Junyi Jiang Junyi Jiang Honghao Zhou Honghao Zhou Rong Liu Rong Liu Wei Zhang Wei Zhang Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques Frontiers in Public Health COVID-19 risk factors critical illness machine learning LASSO regression |
| title | Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques |
| title_full | Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques |
| title_fullStr | Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques |
| title_full_unstemmed | Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques |
| title_short | Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques |
| title_sort | early prediction model for critical illness of hospitalized covid 19 patients based on machine learning techniques |
| topic | COVID-19 risk factors critical illness machine learning LASSO regression |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.880999/full |
| work_keys_str_mv | AT yachengfu earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT yachengfu earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT weijunzhong earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT weijunzhong earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT taoliu earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT jianminli earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT kuixiao earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT xinhuama earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT lihuaxie earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT junyijiang earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT junyijiang earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT honghaozhou earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT honghaozhou earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT rongliu earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT rongliu earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT weizhang earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques AT weizhang earlypredictionmodelforcriticalillnessofhospitalizedcovid19patientsbasedonmachinelearningtechniques |