Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study
AbstractObjectives To appraise effective predictors for COVID-19 mortality in a retrospective cohort study.Methods A total of 1270 COVID-19 patients, including 984 admitted in Sino French New City Branch (training and internal validation sets randomly split at 7:3 ratio) and 286 admitted in Optical...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-01-01
|
| Series: | Annals of Medicine |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/07853890.2020.1868564 |
| _version_ | 1797385677880426496 |
|---|---|
| author | Xin Guan Bo Zhang Ming Fu Mengying Li Xu Yuan Yaowu Zhu Jing Peng Huan Guo Yanjun Lu |
| author_facet | Xin Guan Bo Zhang Ming Fu Mengying Li Xu Yuan Yaowu Zhu Jing Peng Huan Guo Yanjun Lu |
| author_sort | Xin Guan |
| collection | DOAJ |
| description | AbstractObjectives To appraise effective predictors for COVID-19 mortality in a retrospective cohort study.Methods A total of 1270 COVID-19 patients, including 984 admitted in Sino French New City Branch (training and internal validation sets randomly split at 7:3 ratio) and 286 admitted in Optical Valley Branch (external validation set) of Wuhan Tongji hospital, were included in this study. Forty-eight clinical and laboratory features were screened with LASSO method. Further multi-tree extreme gradient boosting (XGBoost) machine learning-based model was used to rank importance of features selected from LASSO and subsequently constructed death risk prediction model with simple-tree XGBoost model. Performances of models were evaluated by AUC, prediction accuracy, precision, and F1 scores.Results Six features, including disease severity, age, levels of high-sensitivity C-reactive protein (hs-CRP), lactate dehydrogenase (LDH), ferritin, and interleukin-10 (IL-10), were selected as predictors for COVID-19 mortality. Simple-tree XGBoost model conducted by these features can predict death risk accurately with >90% precision and >85% sensitivity, as well as F1 scores >0.90 in training and validation sets.Conclusion We proposed the disease severity, age, serum levels of hs-CRP, LDH, ferritin, and IL-10 as significant predictors for death risk of COVID-19, which may help to identify the high-risk COVID-19 cases.KEY MESSAGESA machine learning method is used to build death risk model for COVID-19 patients.Disease severity, age, hs-CRP, LDH, ferritin, and IL-10 are death risk factors.These findings may help to identify the high-risk COVID-19 cases. |
| first_indexed | 2024-03-08T21:57:45Z |
| format | Article |
| id | doaj.art-18b5424167794314879fb94f09136bf2 |
| institution | Directory Open Access Journal |
| issn | 0785-3890 1365-2060 |
| language | English |
| last_indexed | 2024-03-08T21:57:45Z |
| publishDate | 2021-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Annals of Medicine |
| spelling | doaj.art-18b5424167794314879fb94f09136bf22023-12-19T16:46:27ZengTaylor & Francis GroupAnnals of Medicine0785-38901365-20602021-01-0153125726610.1080/07853890.2020.1868564Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort studyXin Guan0Bo Zhang1Ming Fu2Mengying Li3Xu Yuan4Yaowu Zhu5Jing Peng6Huan Guo7Yanjun Lu8Department of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Occupational and Environmental Health, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Occupational and Environmental Health, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Occupational and Environmental Health, State Key Laboratory of Environmental Health (Incubating), School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Laboratory Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaAbstractObjectives To appraise effective predictors for COVID-19 mortality in a retrospective cohort study.Methods A total of 1270 COVID-19 patients, including 984 admitted in Sino French New City Branch (training and internal validation sets randomly split at 7:3 ratio) and 286 admitted in Optical Valley Branch (external validation set) of Wuhan Tongji hospital, were included in this study. Forty-eight clinical and laboratory features were screened with LASSO method. Further multi-tree extreme gradient boosting (XGBoost) machine learning-based model was used to rank importance of features selected from LASSO and subsequently constructed death risk prediction model with simple-tree XGBoost model. Performances of models were evaluated by AUC, prediction accuracy, precision, and F1 scores.Results Six features, including disease severity, age, levels of high-sensitivity C-reactive protein (hs-CRP), lactate dehydrogenase (LDH), ferritin, and interleukin-10 (IL-10), were selected as predictors for COVID-19 mortality. Simple-tree XGBoost model conducted by these features can predict death risk accurately with >90% precision and >85% sensitivity, as well as F1 scores >0.90 in training and validation sets.Conclusion We proposed the disease severity, age, serum levels of hs-CRP, LDH, ferritin, and IL-10 as significant predictors for death risk of COVID-19, which may help to identify the high-risk COVID-19 cases.KEY MESSAGESA machine learning method is used to build death risk model for COVID-19 patients.Disease severity, age, hs-CRP, LDH, ferritin, and IL-10 are death risk factors.These findings may help to identify the high-risk COVID-19 cases.https://www.tandfonline.com/doi/10.1080/07853890.2020.1868564COVID-19machine learningfatal riskextreme gradient boosting |
| spellingShingle | Xin Guan Bo Zhang Ming Fu Mengying Li Xu Yuan Yaowu Zhu Jing Peng Huan Guo Yanjun Lu Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study Annals of Medicine COVID-19 machine learning fatal risk extreme gradient boosting |
| title | Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study |
| title_full | Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study |
| title_fullStr | Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study |
| title_full_unstemmed | Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study |
| title_short | Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study |
| title_sort | clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized covid 19 patients results from a retrospective cohort study |
| topic | COVID-19 machine learning fatal risk extreme gradient boosting |
| url | https://www.tandfonline.com/doi/10.1080/07853890.2020.1868564 |
| work_keys_str_mv | AT xinguan clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT bozhang clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT mingfu clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT mengyingli clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT xuyuan clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT yaowuzhu clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT jingpeng clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT huanguo clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy AT yanjunlu clinicalandinflammatoryfeaturesbasedmachinelearningmodelforfatalriskpredictionofhospitalizedcovid19patientsresultsfromaretrospectivecohortstudy |