Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study
BackgroundLimited information is available about the present characteristics and dynamic clinical changes that occur in patients with COVID-19 during the early phase of the illness. ObjectiveThis study aimed to develop and validate machine learning models based on clinical features to as...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2021-04-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2021/4/e25852 |
| _version_ | 1819281741436682240 |
|---|---|
| author | Oh, Bumjo Hwangbo, Suhyun Jung, Taeyeong Min, Kyungha Lee, Chanhee Apio, Catherine Lee, Hyejin Lee, Seungyeoun Moon, Min Kyong Kim, Shin-Woo Park, Taesung |
| author_facet | Oh, Bumjo Hwangbo, Suhyun Jung, Taeyeong Min, Kyungha Lee, Chanhee Apio, Catherine Lee, Hyejin Lee, Seungyeoun Moon, Min Kyong Kim, Shin-Woo Park, Taesung |
| author_sort | Oh, Bumjo |
| collection | DOAJ |
| description | BackgroundLimited information is available about the present characteristics and dynamic clinical changes that occur in patients with COVID-19 during the early phase of the illness.
ObjectiveThis study aimed to develop and validate machine learning models based on clinical features to assess the risk of severe disease and triage for COVID-19 patients upon hospital admission.
MethodsThis retrospective multicenter cohort study included patients with COVID-19 who were released from quarantine until April 30, 2020, in Korea. A total of 5628 patients were included in the training and testing cohorts to train and validate the models that predict clinical severity and the duration of hospitalization, and the clinical severity score was defined at four levels: mild, moderate, severe, and critical.
ResultsOut of a total of 5601 patients, 4455 (79.5%), 330 (5.9%), 512 (9.1%), and 301 (5.4%) were included in the mild, moderate, severe, and critical levels, respectively. As risk factors for predicting critical patients, we selected older age, shortness of breath, a high white blood cell count, low hemoglobin levels, a low lymphocyte count, and a low platelet count. We developed 3 prediction models to classify clinical severity levels. For example, the prediction model with 6 variables yielded a predictive power of >0.93 for the area under the receiver operating characteristic curve. We developed a web-based nomogram, using these models.
ConclusionsOur prediction models, along with the web-based nomogram, are expected to be useful for the assessment of the onset of severe and critical illness among patients with COVID-19 and triage patients upon hospital admission. |
| first_indexed | 2024-12-24T01:04:31Z |
| format | Article |
| id | doaj.art-f2dcd1c9a2354df69a866d9fc170606e |
| institution | Directory Open Access Journal |
| issn | 1438-8871 |
| language | English |
| last_indexed | 2024-12-24T01:04:31Z |
| publishDate | 2021-04-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj.art-f2dcd1c9a2354df69a866d9fc170606e2022-12-21T17:23:16ZengJMIR PublicationsJournal of Medical Internet Research1438-88712021-04-01234e2585210.2196/25852Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort StudyOh, BumjoHwangbo, SuhyunJung, TaeyeongMin, KyunghaLee, ChanheeApio, CatherineLee, HyejinLee, SeungyeounMoon, Min KyongKim, Shin-WooPark, TaesungBackgroundLimited information is available about the present characteristics and dynamic clinical changes that occur in patients with COVID-19 during the early phase of the illness. ObjectiveThis study aimed to develop and validate machine learning models based on clinical features to assess the risk of severe disease and triage for COVID-19 patients upon hospital admission. MethodsThis retrospective multicenter cohort study included patients with COVID-19 who were released from quarantine until April 30, 2020, in Korea. A total of 5628 patients were included in the training and testing cohorts to train and validate the models that predict clinical severity and the duration of hospitalization, and the clinical severity score was defined at four levels: mild, moderate, severe, and critical. ResultsOut of a total of 5601 patients, 4455 (79.5%), 330 (5.9%), 512 (9.1%), and 301 (5.4%) were included in the mild, moderate, severe, and critical levels, respectively. As risk factors for predicting critical patients, we selected older age, shortness of breath, a high white blood cell count, low hemoglobin levels, a low lymphocyte count, and a low platelet count. We developed 3 prediction models to classify clinical severity levels. For example, the prediction model with 6 variables yielded a predictive power of >0.93 for the area under the receiver operating characteristic curve. We developed a web-based nomogram, using these models. ConclusionsOur prediction models, along with the web-based nomogram, are expected to be useful for the assessment of the onset of severe and critical illness among patients with COVID-19 and triage patients upon hospital admission.https://www.jmir.org/2021/4/e25852 |
| spellingShingle | Oh, Bumjo Hwangbo, Suhyun Jung, Taeyeong Min, Kyungha Lee, Chanhee Apio, Catherine Lee, Hyejin Lee, Seungyeoun Moon, Min Kyong Kim, Shin-Woo Park, Taesung Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study Journal of Medical Internet Research |
| title | Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study |
| title_full | Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study |
| title_fullStr | Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study |
| title_full_unstemmed | Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study |
| title_short | Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study |
| title_sort | prediction models for the clinical severity of patients with covid 19 in korea retrospective multicenter cohort study |
| url | https://www.jmir.org/2021/4/e25852 |
| work_keys_str_mv | AT ohbumjo predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT hwangbosuhyun predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT jungtaeyeong predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT minkyungha predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT leechanhee predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT apiocatherine predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT leehyejin predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT leeseungyeoun predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT moonminkyong predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT kimshinwoo predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy AT parktaesung predictionmodelsfortheclinicalseverityofpatientswithcovid19inkorearetrospectivemulticentercohortstudy |