Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19
BackgroundMost existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 pati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1194349/full |
| _version_ | 1797818802818252800 |
|---|---|
| author | Yangjie Zhu Boyang Yu Boyang Yu Kang Tang Tongtong Liu Tongtong Liu Dongjun Niu Lulu Zhang |
| author_facet | Yangjie Zhu Boyang Yu Boyang Yu Kang Tang Tongtong Liu Tongtong Liu Dongjun Niu Lulu Zhang |
| author_sort | Yangjie Zhu |
| collection | DOAJ |
| description | BackgroundMost existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission.MethodsWe conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance.ResultsA total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722—0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set.ConclusionAn easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation. |
| first_indexed | 2024-03-13T09:13:26Z |
| format | Article |
| id | doaj.art-bb530150e1994313820a7a9ec42c7e37 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-03-13T09:13:26Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-bb530150e1994313820a7a9ec42c7e372023-05-26T16:18:27ZengFrontiers Media S.A.Frontiers in Public Health2296-25652023-05-011110.3389/fpubh.2023.11943491194349Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19Yangjie Zhu0Boyang Yu1Boyang Yu2Kang Tang3Tongtong Liu4Tongtong Liu5Dongjun Niu6Lulu Zhang7Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaDepartment of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaDepartment of Medical Health Service, General Hospital of Northern Theater Command of PLA, Shenyang, ChinaDepartment of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaDepartment of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaDepartment of Medical Health Service, 969th Hospital of PLA Joint Logistics Support Forces, Hohhot, ChinaDepartment of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaDepartment of Military Health Management, College of Health Service, Naval Medical University, Shanghai, ChinaBackgroundMost existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission.MethodsWe conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance.ResultsA total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722—0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set.ConclusionAn easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.https://www.frontiersin.org/articles/10.3389/fpubh.2023.1194349/fullCOVID-19comorbidityhospitalizationdeathprediction modelretrospective study |
| spellingShingle | Yangjie Zhu Boyang Yu Boyang Yu Kang Tang Tongtong Liu Tongtong Liu Dongjun Niu Lulu Zhang Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 Frontiers in Public Health COVID-19 comorbidity hospitalization death prediction model retrospective study |
| title | Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 |
| title_full | Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 |
| title_fullStr | Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 |
| title_full_unstemmed | Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 |
| title_short | Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19 |
| title_sort | development and validation of a prediction model based on comorbidities to estimate the risk of in hospital death in patients with covid 19 |
| topic | COVID-19 comorbidity hospitalization death prediction model retrospective study |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1194349/full |
| work_keys_str_mv | AT yangjiezhu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT boyangyu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT boyangyu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT kangtang developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT tongtongliu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT tongtongliu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT dongjunniu developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 AT luluzhang developmentandvalidationofapredictionmodelbasedoncomorbiditiestoestimatetheriskofinhospitaldeathinpatientswithcovid19 |