An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19
Abstract A high-performing interpretable model is proposed to predict the risk of deterioration in coronavirus disease 2019 (COVID-19) patients. The model was developed using a cohort of 3028 patients diagnosed with COVID-19 and exhibiting common clinical symptoms that were internally verified (AUC...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/c181bf448c074d5eb8ad5f7c833512ad |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:c181bf448c074d5eb8ad5f7c833512ad |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:c181bf448c074d5eb8ad5f7c833512ad2021-12-05T12:13:39ZAn interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-1910.1038/s41598-021-02370-42045-2322https://doaj.org/article/c181bf448c074d5eb8ad5f7c833512ad2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02370-4https://doaj.org/toc/2045-2322Abstract A high-performing interpretable model is proposed to predict the risk of deterioration in coronavirus disease 2019 (COVID-19) patients. The model was developed using a cohort of 3028 patients diagnosed with COVID-19 and exhibiting common clinical symptoms that were internally verified (AUC 0.8517, 95% CI 0.8433, 0.8601). A total of 15 high risk factors for deterioration and their approximate warning ranges were identified. This included prothrombin time (PT), prothrombin activity, lactate dehydrogenase, international normalized ratio, heart rate, body-mass index (BMI), D-dimer, creatine kinase, hematocrit, urine specific gravity, magnesium, globulin, activated partial thromboplastin time, lymphocyte count (L%), and platelet count. Four of these indicators (PT, heart rate, BMI, HCT) and comorbidities were selected for a streamlined combination of indicators to produce faster results. The resulting model showed good predictive performance (AUC 0.7941 95% CI 0.7926, 0.8151). A website for quick pre-screening online was also developed as part of the study.Lijing JiaZijian WeiHeng ZhangJiaming WangRuiqi JiaManhong ZhouXueyan LiHankun ZhangXuedong ChenZheyuan YuZhaohong WangXiucheng LiTingting LiXiangge LiuPei LiuWei ChenJing LiKunlun HeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Lijing Jia Zijian Wei Heng Zhang Jiaming Wang Ruiqi Jia Manhong Zhou Xueyan Li Hankun Zhang Xuedong Chen Zheyuan Yu Zhaohong Wang Xiucheng Li Tingting Li Xiangge Liu Pei Liu Wei Chen Jing Li Kunlun He An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| description |
Abstract A high-performing interpretable model is proposed to predict the risk of deterioration in coronavirus disease 2019 (COVID-19) patients. The model was developed using a cohort of 3028 patients diagnosed with COVID-19 and exhibiting common clinical symptoms that were internally verified (AUC 0.8517, 95% CI 0.8433, 0.8601). A total of 15 high risk factors for deterioration and their approximate warning ranges were identified. This included prothrombin time (PT), prothrombin activity, lactate dehydrogenase, international normalized ratio, heart rate, body-mass index (BMI), D-dimer, creatine kinase, hematocrit, urine specific gravity, magnesium, globulin, activated partial thromboplastin time, lymphocyte count (L%), and platelet count. Four of these indicators (PT, heart rate, BMI, HCT) and comorbidities were selected for a streamlined combination of indicators to produce faster results. The resulting model showed good predictive performance (AUC 0.7941 95% CI 0.7926, 0.8151). A website for quick pre-screening online was also developed as part of the study. |
| format |
article |
| author |
Lijing Jia Zijian Wei Heng Zhang Jiaming Wang Ruiqi Jia Manhong Zhou Xueyan Li Hankun Zhang Xuedong Chen Zheyuan Yu Zhaohong Wang Xiucheng Li Tingting Li Xiangge Liu Pei Liu Wei Chen Jing Li Kunlun He |
| author_facet |
Lijing Jia Zijian Wei Heng Zhang Jiaming Wang Ruiqi Jia Manhong Zhou Xueyan Li Hankun Zhang Xuedong Chen Zheyuan Yu Zhaohong Wang Xiucheng Li Tingting Li Xiangge Liu Pei Liu Wei Chen Jing Li Kunlun He |
| author_sort |
Lijing Jia |
| title |
An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| title_short |
An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| title_full |
An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| title_fullStr |
An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| title_full_unstemmed |
An interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for COVID-19 |
| title_sort |
interpretable machine learning model based on a quick pre-screening system enables accurate deterioration risk prediction for covid-19 |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/c181bf448c074d5eb8ad5f7c833512ad |
| work_keys_str_mv |
AT lijingjia aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zijianwei aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT hengzhang aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT jiamingwang aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT ruiqijia aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT manhongzhou aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xueyanli aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT hankunzhang aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xuedongchen aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zheyuanyu aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zhaohongwang aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xiuchengli aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT tingtingli aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xianggeliu aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT peiliu aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT weichen aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT jingli aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT kunlunhe aninterpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT lijingjia interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zijianwei interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT hengzhang interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT jiamingwang interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT ruiqijia interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT manhongzhou interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xueyanli interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT hankunzhang interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xuedongchen interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zheyuanyu interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT zhaohongwang interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xiuchengli interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT tingtingli interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT xianggeliu interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT peiliu interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT weichen interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT jingli interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 AT kunlunhe interpretablemachinelearningmodelbasedonaquickprescreeningsystemenablesaccuratedeteriorationriskpredictionforcovid19 |
| _version_ |
1718372157086498816 |